Multi Task Learning

This paper presents a new application of the recently proposed machine learning method Alternating Structure Optimiza- tion (ASO), to word sense disambiguation (WSD). Given a set of WSD problems and …...

We present a novel hierarchical prior struc- ture for supervised transfer learning in named entity recognition, motivated by the common structure of feature spaces for this task across natural language …...

Multi-task learning is the problem of maxi- mizing the performance of a system across a number of related tasks. When applied to mul- tiple domains for the same task, it …...

We propose a new framework for N-best reranking on sparse feature sets. The idea is to reformulate the reranking problem as a Multitask Learning problem, where each N-best list corresponds …...

Distributed representations of words have proven extremely useful in numerous natural lan- guage processing tasks. Their appeal is that they can help alleviate data sparsity problems common to supervised learning. …...

Patent translation is a complex problem due to the highly specialized technical vocab- ulary and the peculiar textual structure of patent documents. In this paper we analyze patents along the …...

We present a dual decomposition frame- work for multi-document summarization, using a model that jointly extracts and compresses sentences. Compared with previous work based on integer linear pro- gramming, our …...

To overcome the shortage of labeled data for implicit discourse relation recogni- tion, previous works attempted to auto- matically generate training data by remov- ing explicit discourse connectives from sentences …...

Domain adaptation for SMT usually adapts models to an individual specific domain. However, it often lacks some correlation among different domains where common knowledge could be shared to improve the …...

Multi-task learning has been shown to be effective in various applications, including discriminative SMT. We present an exper- imental evaluation of the question whether multi-task learning depends on a “natu- …...

Machine Translation (MT) Quality Estimation (QE) aims to automatically measure the quality of MT system output without reference translations. In spite of the progress achieved in re- cent years, current …...

We report results obtained by the UoW method in SemEval-2014’s Task 10 – Mul- tilingual Semantic Textual Similarity. We propose to model Semantic Textual Simi- larity in the context of …...

Social media is a rich source of rumours and corresponding community reactions. Rumours reflect different characteristics, some shared and some individual. We for- mulate the problem of classifying tweet level …...

This paper reports our submissions to seman- tic textual similarity task, i.e., task 2 in Se- mantic Evaluation 2015. We built our sys- tems using various traditional features, such as …...

We present a multi-task learning approach that jointly trains three word alignment mod- els over disjoint bitexts of three languages: source, target and pivot. Our approach builds upon model triangulation, …...

We investigate the problem of predicting the quality of automatic speech recognition (ASR) output under the following rigid con- straints: i) reference transcriptions are not available, ii) confidence information about …...

AbstractThis paper describes a unified neural architecture for identifying and classifying multi-typed semantic relations between words in a sentence. We investigate two typical and well-studied tasks: semantic role labeling (SRL) …...

Existing work on detecting deceptive reviews primarily focuses on feature engineering and applies off-the-shelf supervised classification algorithms to the problem. Then, one real challenge would be to manually recognize plentiful …...

Neural Machine Translation (NMT) based on the encoder-decoder architecture has recently become a new paradigm. Researchers have proven that the target-side monolingual data can greatly enhance the decoder model of …...

AbstractNatural-language processing of historical documents is complicated by the abundance of variant spellings and lack of annotated data. A common approach is to normalize the spelling of historical words to …...

Multitask learning has been proven a useful technique in a number of Natural Language Processing applications where data is scarce and naturally diverse. Examples include learn- ing from data of …...

Motivated by the findings in social sci- ence that people’s opinions are diverse and variable while together they are shaped by evolving social norms, we perform person- alized sentiment classification …...

Conventional word sense induction (WSI) methods usually represent each instance with discrete linguistic features or co- occurrence features, and train a model for each polysemous word individually. In this work, …...

Domain adaptation is an important re- search topic in sentiment analysis area. Existing domain adaptation methods usu- ally transfer sentiment knowledge from only one source domain to target do- main. …...

AbstractTransfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks. Ideally, the linguistic levels of morphology, syntax and semantics would benefit each …...

AbstractNeural network models have shown their promising opportunities for multi-task learning, which focus on learning the shared layers to extract the common and task-invariant features. However, in most existing approaches, …...

AbstractWe present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our …...

Linguistic resources such as part-of- speech (POS) tags have been extensively used in statistical machine translation (SMT) frameworks and have yielded bet- ter performances. However, usage of such linguistic annotations …...

Social media is an important source for news writers. However, extracting useful informa- tion for news writers from the vast amount of social media information is laborious. There- fore, services …...

AbstractThe need for automatic document summarization that can be used for practical applications is increasing rapidly. In this paper, we propose a general framework for summarization that extracts sentences from …...

AbstractPart-of-speech (POS) tagging for morphologically rich languages such as Arabic is a challenging problem because of their enormous tag sets. One reason for this is that in the tagging scheme …...

AbstractLanguage contains information about the author’s demographic attributes as well as their mental state, and has been successfully leveraged in NLP to predict either one alone. However, demographic attributes and …...

AbstractThis paper proposes to tackle open-domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This …...

AbstractThe performance of Neural Machine Translation (NMT) models relies heavily on the availability of sufficient amounts of parallel data, and an efficient and effective way of leveraging the vastly available …...

AbstractMultitask learning has been applied successfully to a range of tasks, mostly morphosyntactic. However, little is known on when MTL works and whether there are data characteristics that help to …...

AbstractAutomatic resolution of rumours is a challenging task that can be broken down into smaller components that make up a pipeline, including rumour detection, rumour tracking and stance classification, leading …...

AbstractThis paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode …...

AbstractThis paper describes our system implementation for subtask V-oc of SemEval-2018 Task 1: affect in tweets. We use multi-task learning method to learn shared representation, then learn the features for …...

AbstractSentence simplification aims to improve readability and understandability, based on several operations such as splitting, deletion, and paraphrasing. However, a valid simplified sentence should also be logically entailed by its …...

AbstractDetection and classification of emotion categories expressed by a sentence is a challenging task due to subjectivity of emotion. To date, most of the models are trained and evaluated on …...

AbstractNon-literal language phenomena such as idioms or metaphors are commonly studied in isolation from each other in NLP. However, often similar definitions and features are being used for different phenomena, …...

AbstractWe take a multi-task learning approach to the shared Task 1 at SemEval-2018. The general idea concerning the model structure is to use as little external data as possible in …...

AbstractNamed-entity Recognition (NER) is an important task in the NLP field , and is widely used to solve many challenges. However, in many scenarios, not all of the entities are …...

AbstractHuman world knowledge contains information about prototypical events and their participants and locations. In this paper, we train the first models using multi-task learning that can both predict missing event …...

AbstractNeural network based multi-task learning has achieved great success on many NLP problems, which focuses on sharing knowledge among tasks by linking some layers to enhance the performance. However, most …...

AbstractWe address the task of joint training of transliteration models for multiple language pairs (multilingual transliteration). This is an instance of multitask learning, where individual tasks (language pairs) benefit from …...

AbstractDealing with ‘open-vocabulary’ slots has been among the challenges in the natural language area. While recent studies on attention-based recurrent neural network (RNN) models have performed well in completing several …...

AbstractThis paper is an initial study on multi-task and multi-lingual joint learning for lexical utterance classification. A major problem in constructing lexical utterance classification modules for spoken dialogue systems is …...

AbstractWe study three general multi-task learning (MTL) approaches on 11 sequence tagging tasks. Our extensive empirical results show that in about 50% of the cases, jointly learning all 11 tasks …...

AbstractWe combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled …...

AbstractGenerating natural language requires conveying content in an appropriate style. We explore two related tasks on generating text of varying formality: monolingual formality transfer and formality-sensitive machine translation. We propose …...

AbstractNeural machine translation requires large amount of parallel training text to learn a reasonable quality translation model. This is particularly inconvenient for language pairs for which enough parallel text is …...

AbstractFor over a decade, machine learning has been used to extract opinion-holder-target structures from text to answer the question “Who expressed what kind of sentiment towards what?”. Recent neural approaches …...

AbstractThis paper describes a warrant classification system for SemEval 2018 Task 12, that attempts to learn semantic representations of reasons, claims and warrants. The system consists of 3 stacked LSTMs: …...

AbstractThis work aims to contribute to our understanding of when multi-task learning through parameter sharing in deep neural networks leads to improvements over single-task learning. We focus on the setting …...

AbstractPredicting the emotional value of lexical items is a well-known problem in sentiment analysis. While research has focused on polarity for quite a long time, meanwhile this early focus has …...

AbstractSemantic role labeling (SRL) aims to identify the predicate-argument structure of a sentence. Inspired by the strong correlation between syntax and semantics, previous works pay much attention to improve SRL …...

AbstractThe mining of adverse drug reaction (ADR) has a crucial role in the pharmacovigilance. The traditional ways of identifying ADR are reliable but time-consuming, non-scalable and offer a very limited …...

AbstractMorphological tagging is challenging for morphologically rich languages due to the large target space and the need for more training data to minimize model sparsity. Dialectal variants of morphologically rich …...

AbstractIn this paper, we present a novel integrated approach for keyphrase generation (KG). Unlike previous works which are purely extractive or generative, we first propose a new multi-task learning framework …...

AbstractQuestion answering (QA) using textual sources for purposes such as reading comprehension (RC) has attracted much attention. This study focuses on the task of explainable multi-hop QA, which requires the …...

AbstractMulti-task learning (MTL) has achieved success over a wide range of problems, where the goal is to improve the performance of a primary task using a set of relevant auxiliary …...

AbstractSequence tagging models for constituent parsing are faster, but less accurate than other types of parsers. In this work, we address the following weaknesses of such constituent parsers: (a) high …...

AbstractWe propose a grounded dialogue state encoder which addresses a foundational issue on how to integrate visual grounding with dialogue system components. As a test-bed, we focus on the GuessWhat?! …...

AbstractThe paper presents Columbia team’s participation in the SemEval 2019 Shared Task 7: RumourEval 2019. Detecting rumour on social networks has been a focus of research in recent years. Previous …...

AbstractMulti-Task Learning (MTL) has been an attractive approach to deal with limited labeled datasets or leverage related tasks, for a variety of NLP problems. We examine the benefit of MTL …...

AbstractEmotion cause extraction (ECE), the task aimed at extracting the potential causes behind certain emotions in text, has gained much attention in recent years due to its wide applications. However, …...

AbstractNeural machine translation systems have become state-of-the-art approaches for Grammatical Error Correction (GEC) task. In this paper, we propose a copy-augmented architecture for the GEC task by copying the unchanged …...

AbstractStories generated with neural language models have shown promise in grammatical and stylistic consistency. However, the generated stories are still lacking in common sense reasoning, e.g., they often contain sentences …...

AbstractIn this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be …...

AbstractNamed entity recognition (NER) identifies typed entity mentions in raw text. While the task is well-established, there is no universally used tagset: often, datasets are annotated for use in downstream …...

AbstractBilingual word embeddings have been widely used to capture the correspondence of lexical semantics in different human languages. However, the cross-lingual correspondence between sentences and words is less studied, despite …...

AbstractWe address the task of assessing discourse coherence, an aspect of text quality that is essential for many NLP tasks, such as summarization and language assessment. We propose a hierarchical …...

AbstractAn event-noun is a noun that has an argument structure similar to a predicate. Recent works, including those considered state-of-the-art, ignore event-nouns or build a single model for solving both …...

AbstractRelated tasks often have inter-dependence on each other and perform better when solved in a joint framework. In this paper, we present a deep multi-task learning framework that jointly performs …...

AbstractWe propose a multi-task learning framework to learn a joint Machine Reading Comprehension (MRC) model that can be applied to a wide range of MRC tasks in different domains. Inspired …...

AbstractWe present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task domain …...

AbstractIn Semantic Dependency Parsing (SDP), semantic relations form directed acyclic graphs, rather than trees. We propose a new iterative predicate selection (IPS) algorithm for SDP. Our IPS algorithm combines the …...

AbstractLanguages evolve and diverge over time. Their evolutionary history is often depicted in the shape of a phylogenetic tree. Assuming parsing models are representations of their languages grammars, their evolution …...

AbstractIn this study, we propose a new multi-task learning approach for rumor detection and stance classification tasks. This neural network model has a shared layer and two task specific layers. …...

AbstractWe use parsing as sequence labeling as a common framework to learn across constituency and dependency syntactic abstractions. To do so, we cast the problem as multitask learning (MTL). First, …...

AbstractA widespread approach to processing spoken language is to first automatically transcribe it into text. An alternative is to use an end-to-end approach: recent works have proposed to learn semantic …...

AbstractDistributions of the senses of words are often highly skewed and give a strong influence of the domain of a document. This paper follows the assumption and presents a method …...

AbstractCollaboratively constructed knowledge bases play an important role in information systems, but are essentially always incomplete. Thus, a large number of models has been developed for Knowledge Base Completion, the …...

AbstractLearning from social-media conversations has gained significant attention recently because of its applications in areas like rumor detection. In this research, we propose a new way to represent social-media conversations …...

AbstractWhile evaluating an answer choice for Reading Comprehension task, other answer choices available for the question and the answers of related questions about the same paragraph often provide valuable information. …...

AbstractStory generation, namely, generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural …...

AbstractWe present a large-scale corpus of e-mail conversations with domain-agnostic and two-level dialogue act (DA) annotations towards the goal of a better understanding of asynchronous conversations. We annotate over 6,000 …...

AbstractEvaluation discrepancy and overcorrection phenomenon are two common problems in neural machine translation (NMT). NMT models are generally trained with word-level learning objective, but evaluated by sentence-level metrics. Moreover, the …...

Abstract(T)ACSA tasks, including aspect-category sentiment analysis (ACSA) and targeted aspect-category sentiment analysis (TACSA), aims at identifying sentiment polarity on predefined categories. Incremental learning on new categories is necessary for (T)ACSA …...

AbstractThe state-of-the-art Aspect-based Sentiment Analysis (ABSA) approaches are mainly based on either detecting aspect terms and their corresponding sentiment polarities, or co-extracting aspect and opinion terms. However, the extraction of …...

AbstractRecent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to their …...

AbstractIn this paper, we describe our mUlti-task learNIng for cOmmonsense reasoNing (UNION) system submitted for Task C of the SemEval2020 Task 4, which is to generate a reason explaining why …...

AbstractPrevious studies in multimodal sentiment analysis have used limited datasets, which only contain unified multimodal annotations. However, the unified annotations do not always reflect the independent sentiment of single modalities …...

AbstractWe consider detection of the span of antecedents and consequents in argumentative prose a structural, grammatical task. Our system comprises a set of stacked Bi-LSTMs trained on two complementary linguistic …...

AbstractThe prevalent use of social media enables rapid spread of rumors on a massive scale, which leads to the emerging need of automatic rumor verification (RV). A number of previous …...

AbstractRecent dialogue coherence models use the coherence features designed for monologue texts, e.g. nominal entities, to represent utterances and then explicitly augment them with dialogue-relevant features, e.g., dialogue act labels. …...

AbstractBuilding general reading comprehension systems, capable of solving multiple datasets at the same time, is a recent aspirational goal in the research community. Prior work has focused on model architecture …...

AbstractTemporal relation classification is the pair-wise task for identifying the relation of a temporal link (TLINKs) between two mentions, i.e. event, time and document creation time (DCT). It leads to …...

AbstractApproaching named entities transliteration as a Neural Machine Translation (NMT) problem is common practice. While many have applied various NMT techniques to enhance machine transliteration models, few focus on the …...

AbstractMulti-task learning (MTL) and transfer learning (TL) are techniques to overcome the issue of data scarcity when training state-of-the-art neural networks. However, finding beneficial auxiliary datasets for MTL or TL …...

AbstractRecognition of the mental state of a human character in text is a major challenge in natural language processing. In this study, we investigate the efficacy of the narrative context …...

AbstractThis paper studies the task of Relation Extraction (RE) that aims to identify the semantic relations between two entity mentions in text. In the deep learning models for RE, it …...

AbstractNatural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, …...

AbstractThis paper describes our approach to “DeftEval: Extracting Definitions from Free Text in Textbooks” competition held as a part of Semeval 2020. The task was devoted to finding and labeling …...

AbstractThe gaze behaviour of a reader is helpful in solving several NLP tasks such as automatic essay grading. However, collecting gaze behaviour from readers is costly in terms of time …...

AbstractGiven a sentence and its relevant answer, how to ask good questions is a challenging task, which has many real applications. Inspired by human’s paraphrasing capability to ask questions of …...

AbstractThis paper presents our work in the WMT 2020 Word and Sentence-Level Post-Editing Quality Estimation (QE) Shared Task. Our system follows standard Predictor-Estimator architecture, with a pre-trained Transformer as the …...

AbstractExisting studies on using social media for deriving mental health status of users focus on the depression detection task. However, for case management and referral to psychiatrists, health-care workers require …...

AbstractIn this paper, we describe the participation of IITP-AINLPML team in the SemEval-2020 SharedTask 12 on Offensive Language Identification and Target Categorization in English Twitter data. Our proposed model learns …...

AbstractIn the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good …...

AbstractImage captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning …...

AbstractWe address the task of automatically grading the language proficiency of spontaneous speech based on textual features from automatic speech recognition transcripts. Motivated by recent advances in multi-task learning, we …...

AbstractThe rise of online communication platforms has been accompanied by some undesirable effects, such as the proliferation of aggressive and abusive behaviour online. Aiming to tackle this problem, the natural …...

AbstractEmotion recognition in textual conversations (ERTC) plays an important role in a wide range of applications, such as opinion mining, recommender systems, and so on. ERTC, however, is a challenging …...

AbstractPrevious studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training …...

AbstractNowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task. In this paper, we build an offensive language detection system, …...

AbstractRecently, large-scale datasets have vastly facilitated the development in nearly all domains of Natural Language Processing. However, there is currently no cross-task dataset in NLP, which hinders the development of …...

AbstractNamed entity recognition is a key component of many text processing pipelines and it is thus essential for this component to be robust to different types of input. However, domain …...

AbstractWhile monolingual data has been shown to be useful in improving bilingual neural machine translation (NMT), effectively and efficiently leveraging monolingual data for Multilingual NMT (MNMT) systems is a less …...

AbstractWe study the zero-shot transfer capabilities of text matching models on a massive scale, by self-supervised training on 140 source domains from community question answering forums in English. We investigate …...

AbstractWe describe a method for developing broad-coverage semantic dependency parsers for languages for which no semantically annotated resource is available. We leverage a multitask learning framework coupled with annotation projection. …...

AbstractWe propose a multi task learning-based neural model for resolving bridging references tackling two key challenges. The first challenge is the lack of large corpora annotated with bridging references. To …...

AbstractNamed entity recognition is a critical task in the natural language processing field. Most existing methods for this task can only exploit contextual information within a sentence. However, their performance …...

AbstractThe emergence of a variety of graph-based meaning representations (MRs) has sparked an important conversation about how to adequately represent semantic structure. MRs exhibit structural differences that reflect different theoretical …...

AbstractThis paper presents our hierarchical multi-task learning (HMTL) and multi-task learning (MTL) approaches for improving the text encoder in Sub-tasks A, B, and C of Multilingual Offensive Language Identification in …...

AbstractReading comprehension (RC) on social media such as Twitter is a critical and challenging task due to its noisy, informal, but informative nature. Most existing RC models are developed on …...

AbstractDialog state tracking (DST) suffers from severe data sparsity. While many natural language processing (NLP) tasks benefit from transfer learning and multi-task learning, in dialog these methods are limited by …...

AbstractWe present a multi-task learning framework to enable the training of one universal incremental dialogue processing model with four tasks of disfluency detection, language modelling, part-of-speech tagging and utterance segmentation …...

AbstractThe idea of using multi-task learning approaches to address the joint extraction of entity and relation is motivated by the relatedness between the entity recognition task and the relation classification …...

AbstractWe introduce Room-Across-Room (RxR), a new Vision-and-Language Navigation (VLN) dataset. RxR is multilingual (English, Hindi, and Telugu) and larger (more paths and instructions) than other VLN datasets. It emphasizes the …...

AbstractSocial media platforms such as Twitter have become a breeding ground for unverified information or rumors. These rumors can threaten people’s health, endanger the economy, and affect the stability of …...

AbstractAlthough neural table-to-text models have achieved remarkable progress with the help of large-scale datasets, they suffer insufficient learning problem with limited training data. Recently, pre-trained language models show potential in …...

AbstractMulti-task Learning methods have achieved great progress in text classification. However, existing methods assume that multi-task text classification problems are convex multiobjective optimization problems, which is unrealistic in real-world applications. …...

AbstractAdvanced pre-trained models for text representation have achieved state-of-the-art performance on various text classification tasks. However, the discrepancy between the semantic similarity of texts and labelling standards affects classifiers, i.e. …...

AbstractThis paper describes the submissions of the NiuTrans Team to the WMT 2020 Quality Estimation Shared Task. We participated in all tasks and all language pairs. We explored the combination …...

AbstractThe standard neural machine translation model can only decode with the same depth configuration as training. Restricted by this feature, we have to deploy models of various sizes to maintain …...

AbstractBy predicting chemical compound structures from their names, we can better comprehend chemical compounds written in text and identify the same chemical compound given different notations for database creation. Previous …...

AbstractThe translation quality estimation (QE) task, particularly the QE as a Metric task, aims to evaluate the general quality of a translation based on the translation and the source sentence …...

AbstractExtracting structured knowledge from product profiles is crucial for various applications in e-Commerce. State-of-the-art approaches for knowledge extraction were each designed for a single category of product, and thus do …...

AbstractThis study tackles unsupervised domain adaptation of reading comprehension (UDARC). Reading comprehension (RC) is a task to learn the capability for question answering with textual sources. State-of-the-art models on RC …...

AbstractSentence complexity assessment is a relatively new task in Natural Language Processing. One of its aims is to highlight in a text which sentences are more complex to support the …...

AbstractIn this paper we present a character-level sequence-to-sequence lemmatization model, utilizing several subword features in multiple configurations. In addition to generic n-gram embeddings (using FastText), we experiment with concatenative (stems) …...

AbstractOur goal is to explain the effects of perturbations in procedural text, e.g., given a passage describing a rabbit’s life cycle, explain why illness (the perturbation) may reduce the rabbit …...

AbstractVisual referring expression recognition is a challenging task that requires natural language understanding in the context of an image. We critically examine RefCOCOg, a standard benchmark for this task, using …...

AbstractSpeech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, …...

AbstractExtracting rationales can help human understand which information the model utilizes and how it makes the prediction towards better interpretability. However, annotating rationales requires much effort and only few datasets …...

AbstractDetecting arguments in online interactions is useful to understand how conflicts arise and get resolved. Users often use figurative language, such as sarcasm, either as persuasive devices or to attack …...

AbstractMillions of hashtags are created on social media every day to cross-refer messages concerning similar topics. To help people find the topics they want to discuss, this paper characterizes a …...

AbstractEnd-to-end relation extraction aims to identify named entities and extract relations between them. Most recent work models these two subtasks jointly, either by casting them in one structured prediction framework, …...

AbstractUsers of medical question answering systems often submit long and detailed questions, making it hard to achieve high recall in answer retrieval. To alleviate this problem, we propose a novel …...

Multi-target stance detection aims to identify the stance taken toward a pair of different tar- gets from the same text, and typically, there are multiple target pairs per dataset. Existing …...

AbstractDisease is one of the fundamental entities in biomedical research. Recognizing such entities from biomedical text and then normalizing them to a standardized disease vocabulary offer a tremendous opportunity for …...

AbstractConditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We …...

AbstractSequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks; however, they suffer from catastrophic forgetting and difficulties in dataset balancing. To address these shortcomings, we …...

Using multiple treebanks to improve parsing performance has shown positive results. How- ever, to what extent similar, yet competing an- notation decisions play in parser behavior is unclear. We investigate …...

AbstractWhen we are interested in a certain domain, we can collect and analyze data from the Internet. The newly collected data is not labeled, so the use of labeled data …...

AbstractThis paper describes our submission to the SemEval-2021 shared task on Lexical Complexity Prediction. We approached it as a regression problem and present an ensemble combining four systems, one feature-based …...

AbstractAutomated systems that negotiate with humans have broad applications in pedagogy and conversational AI. To advance the development of practical negotiation systems, we present CaSiNo: a novel corpus of over …...

AbstractIn this paper, we introduce the task of political coalition signal prediction from text, that is, the task of recognizing from the news coverage leading up to an election the …...

AbstractContinual learning in task-oriented dialogue systems allows the system to add new domains and functionalities overtime after deployment, without incurring the high cost of retraining the whole system each time. …...

AbstractHumor detection has become a topic of interest for several research teams, especially those involved in socio-psychological studies, with the aim to detect the humor and the temper of a …...

AbstractConversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to handle conversational structural information. …...

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understand- ing tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which …...

Simultaneous speech-to-text translation is widely useful in many scenarios. The con- ventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and …...

AbstractThis paper describes Edinburgh’s submissions to the IWSLT2021 multilingual speech translation (ST) task. We aim at improving multilingual translation and zero-shot performance in the constrained setting (without using any extra …...

AbstractThe problem of detecting psychological stress in online posts, and more broadly, of detecting people in distress or in need of help, is a sensitive application for which the ability …...

AbstractCurrent state-of-the-art systems for joint entity relation extraction (Luan et al., 2019; Wad-den et al., 2019) usually adopt the multi-task learning framework. However, annotations for these additional tasks such as …...

AbstractPrevious works on key information extraction from visually rich documents (VRDs) mainly focus on labeling the text within each bounding box (i.e.,semantic entity), while the relations in-between are largely unexplored. …...

AbstractIn this paper, we investigate how to use limited code-switching data to implement a code-switching speech recognition system. We utilize the Transformer end-to-end model to develop our code switching speech …...

This paper studies how to automatically gen- erate a natural language text that describes the facts in knowledge graph (KG). Considering the few-shot setting, we leverage the excel- lent capacities …...

AbstractConversation disentanglement, the task to identify separate threads in conversations, is an important pre-processing step in multi-party conversational NLP applications such as conversational question answering and con-versation summarization. Framing it …...

AbstractThis paper describes our submission to SemEval-2021 Task 1: predicting the complexity score for single words. Our model leverages standard morphosyntactic and frequency-based features that proved helpful for Complex Word …...

AbstractPretraining and multitask learning are widely used to improve the speech translation performance. In this study, we are interested in training a speech translation model along with an auxiliary text …...

Rhetorical implicit emotion identification is one of important and challenging tasks in nat- ural language processing. We observe that each rhetoric may express certain evidence of semantic and syntactic patterns. …...

AbstractSemEval-2021 Task 8: MeasEval aims at improving the machine understanding of measurements in scientific texts through a set of entity and semantic relation extraction sub-tasks on identifying quantity spans along …...

AbstractIn this paper, we propose to study language modelling as a multi-task problem, bringing together three strands of research: multi-task learning, linguistics, and interpretability. Based on hypotheses derived from linguistic …...

AbstractRelation schemas are often pre-defined for each relation dataset. Relation types can be related from different datasets and have overlapping semantics. We hypothesize we can combine these datasets according to …...

AbstractThis work describes our approach for subtasks of SemEval-2021 Task 8: MeasEval: Counts and Measurements which took the official first place in the competition. To solve all subtasks we use …...

AbstractA recent topic of research in natural language generation has been the development of automatic response generation modules that can automatically respond to a user’s utterance in an empathetic manner. …...

AbstractEmotion cause analysis (ECA) aims to identify the potential causes behind certain emotions intext. Lots of ECA models have been designed to extract the emotion cause at the clause level. …...

Detecting what emotions are expressed in text is a well-studied problem in natural lan- guage processing. However, research on finer- grained emotion analysis such as what causes an emotion is …...

AbstractThe majority of work in targeted sentiment analysis has concentrated on finding better methods to improve the overall results. Within this paper we show that these models are not robust …...

AbstractThis paper describes the system submitted to the IWSLT 2021 Multilingual Speech Translation (MultiST) task from Huawei Noah’s Ark Lab. We use a unified transformer architecture for our MultiST model, …...

AbstractThe #MeToo movement on social media platforms initiated discussions over several facets of sexual harassment in our society. Prior work by the NLP community for automated identification of the narratives …...

AbstractAs labeling schemas evolve over time, small differences can render datasets following older schemas unusable. This prevents researchers from building on top of previous annotation work and results in the …...

AbstractWe propose pre-finetuning, an additional large-scale learning stage between language model pre-training and fine-tuning. Pre-finetuning is massively multi-task learning (around 50 datasets, over 4.8 million total labeled examples), and is …...

AbstractThe capability to automatically detect human stress can benefit artificial intelligent agents involved in affective computing and human-computer interaction. Stress and emotion are both human affective states, and stress has …...

AbstractWe propose an ensemble model for predicting the lexical complexity of words and multiword expressions (MWEs). The model receives as input a sentence with a target word or MWE and …...

AbstractAlthough recent developments in neural architectures and pre-trained representations have greatly increased state-of-the-art model performance on fully-supervised semantic role labeling (SRL), the task remains challenging for languages where supervised SRL …...

AbstractSemantic parsers map natural language utterances to meaning representations. The lack of a single standard for meaning representations led to the creation of a plethora of semantic parsing datasets. To …...

AbstractState-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model. However, such modules are trained separately for each task and thus do not …...

AbstractUnderstanding voluminous historical records provides clues on the past in various aspects, such as social and political issues and even natural science facts. However, it is generally difficult to fully …...

AbstractQuestion answering over knowledge bases (KBQA) usually involves three sub-tasks, namely topic entity detection, entity linking and relation detection. Due to the large number of entities and relations inside knowledge …...

AbstractThe Lottery Ticket Hypothesis suggests that an over-parametrized network consists of ”lottery tickets”, and training a certain collection of them (i.e., a subnetwork) can match the performance of the full …...

AbstractDarknet market forums are frequently used to exchange illegal goods and services between parties who use encryption to conceal their identities. The Tor network is used to host these markets, …...

AbstractMulti-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a question still remains whether or …...

AbstractDue to the scarcity of annotated data, Abstract Meaning Representation (AMR) research is relatively limited and challenging for languages other than English. Upon the availability of English AMR dataset and …...

AbstractWhile relation extraction is an essential task in knowledge acquisition and representation, and new-generated relations are common in the real world, less effort is made to predict unseen relations that …...

AbstractMulti-intent natural language understanding (NLU) has recently gained attention. It detects multiple intents in an utterance, which is better suited to real-world scenarios. However, the state-of-the-art joint NLU models mainly …...

AbstractThanks to the development of pre-trained language models, multitask learning (MTL) methods achieve a great success in natural language understanding area. However, current MTL methods pay more attention to task …...

Millions of reviews are generated on e- commerce platforms and analyzing them deeply brings a lot of useful information for sellers and buyers. This paper deals with the aspect-based sentiment …...

AbstractIn this paper we describe our work towards building a generic framework for both multi-modal embedding and multi-label binary classification tasks, while participating in task 5 (Multimedia Automatic Misogyny Identification) …...

AbstractRecently introduced language model prompting methods can achieve high accuracy in zero- and few-shot settings while requiring few to no learned task-specific parameters. Nevertheless, these methods still often trail behind …...

AbstractCross-domain NER is a practical yet challenging problem since the data scarcity in the real-world scenario. A common practice is first to learn a NER model in a rich-resource general …...

AbstractMany recent sentence-level event detection efforts focus on enriching sentence semantics, e.g., via multi-task or prompt-based learning. Despite the promising performance, these methods commonly depend on label-extensive manual annotations or …...

AbstractProviding conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where …...

AbstractLarge-scale pre-trained language models have attracted extensive attentions in the research community and shown promising results on various tasks of natural language processing. However, the attention maps, which record the …...

AbstractRecent model-based reference-free metrics for open-domain dialogue evaluation exhibit promising correlations with human judgment. However, they either perform turn-level evaluation or look at a single dialogue quality dimension. One would …...

AbstractRecently, non-autoregressive (NAR) neural machine translation models have received increasing attention due to their efficient parallel decoding. However, the probabilistic framework of NAR models necessitates conditional independence assumption on target …...

AbstractMany populous countries including India are burdened with a considerable backlog of legal cases. Development of automated systems that could process legal documents and augment legal practitioners can mitigate this. …...

AbstractWe propose a novel multitask learning method for diacritization which trains a model to both diacritize and translate. Our method addresses data sparsity by exploiting large, readily available bitext corpora. …...

AbstractDependency tree-based methods might be susceptible to the dependency tree due to that they inevitably introduce noisy information and neglect the rich relation information between words. In this paper, we …...

AbstractExplaining the reasoning of neural models has attracted attention in recent years. Providing highly-accessible and comprehensible explanations in natural language is useful for humans to understand model’s prediction results. In …...

AbstractQuestion answering over knowledge bases (KBQA) for complex questions is a challenging task in natural language processing. Recently, generation-based methods that translate natural language questions to executable logical forms have …...

AbstractPrevious work on multi-task learning in Natural Language Processing (NLP) oftenincorporated carefully selected tasks as well as carefully tuning ofarchitectures to share information across tasks. Recently, it has shown thatfor …...

AbstractWe introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of …...

AbstractTask weighting, which assigns weights on the including tasks during training, significantly matters the performance of Multi-task Learning (MTL); thus, recently, there has been an explosive interest in it. However, …...

AbstractIn this paper, we propose to leverage the unique characteristics of dialogues sharing commonsense knowledge across participants, to resolve the difficulties in summarizing them. We present SICK, a framework that …...

AbstractTo address the Conversational Question Answering (ORConvQA) task, previous work has considered an effective three-stage architecture, consisting of a retriever, a reranker, and a reader to extract the answers. In …...

Abstract“Medical named entity recognition (NER), a fundamental task of medical information extraction, is crucial for medical knowledge graph construction, medical question answering, and automatic medical record analysis, etc. Compared with …...

AbstractMulti-task learning, in which several tasks are jointly learned by a single model, allows NLP models to share information from multiple annotations and may facilitate better predictions when the tasks …...

AbstractWe present a multi-task learning framework for cross-lingual abstractive summarization to augment training data. Recent studies constructed pseudo cross-lingual abstractive summarization data to train their neural encoder-decoders. Meanwhile, we introduce …...

AbstractParaphrase generation using deep learning has been a research hotspot of natural language processing in the past few years. While previous studies tackle the problem from different aspects, the essence …...

AbstractThis paper presents submissions of the NJUNLP team in WMT 2022Quality Estimation shared task 1, where the goal is to predict the sentence-level and word-level quality for target machine translations. …...

AbstractThis paper describes our system used in the SemEval-2022 Task 5: Multimedia Automatic Misogyny Identification (MAMI). Multimedia automatic misogyny recognition consists of the identification of misogynous memes, taking advantage of …...

AbstractNeural Chat Translation (NCT) aims to translate conversational text into different languages. Existing methods mainly focus on modeling the bilingual dialogue characteristics (e.g., coherence) to improve chat translation via multi-task …...

AbstractFew-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which …...

AbstractWith the increasing popularity of online chatting, stickers are becoming important in our online communication. Selecting appropriate stickers in open-domain dialogue requires a comprehensive understanding of both dialogues and stickers, …...

AbstractWe present a multi-modal deep learning system for the Multimedia Automatic Misogyny Identification (MAMI) challenge, a SemEval task of identifying and classifying misogynistic messages in online memes. We adapt multi-task …...

AbstractMulti-task learning with an unbalanced data distribution skews model learning towards high resource tasks, especially when model capacity is fixed and fully shared across all tasks. Sparse scaling architectures, such …...

AbstractIn this work, we describe a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition. The proposed method utilizes multi-task learning to …...

AbstractMulti-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalities and differences. Nevertheless, it is still …...

AbstractIn this system paper, we describe our submission for the 11th task of SemEval2023: Learning with Disagreements, or Le-Wi-Di for short. In the task, the assumption that there is a …...

AbstractThe widespread popularity of social media has led to an increase in hateful, abusive, and sexist language, motivating methods for the automatic detection of such phenomena. The goal of the …...

AbstractPretraining has been shown to scale well with compute, data size and data diversity. Multitask learning trains on a mixture of supervised datasets and produces improved performance compared to self-supervised …...

AbstractThis paper presents the submissions of the DH-FBK team for the three tasks of Task 10 at SemEval 2023. The Explainable Detection of Online Sexism (EDOS) task aims at detecting …...

AbstractDeceptive text poses a significant threat to users, resulting in widespread misinformation and disorder. While researchers have created numerous cutting-edge techniques for detecting deception in domain-specific settings, whether there is …...

AbstractMulti-task learning (MTL) has emerged as a promising approach for sharing inductive bias across multiple tasks to enable more efficient learning in text classification. However, training all tasks simultaneously often …...

AbstractWe propose an explainable approach for relation extraction that mitigates the tension between generalization and explainability by jointly training for the two goals. Our approach uses a multi-task learning architecture, …...

AbstractMisogyny and sexism are growing problems in social media. Advances have been made in online sexism detection but the systems are often uninterpretable. SemEval-2023 Task 10 on Explainable Detection of …...

AbstractOnline articles using striking headlines that promise intriguing information are often used to attract readers. Most of the time, the information provided in the text is disappointing to the reader …...

AbstractResearch on fake reviews detection and review helpfulness prediction is prevalent, yet most studies tend to focus solely on either fake reviews detection or review helpfulness prediction, considering them separate …...

AbstractThis paper describes our system used in the SemEval-2023 Task 10: Towards ExplainableDetection of Online Sexism (Kirk et al., 2023). The harmful effects of sexism on the internet have impacted …...

AbstractEvaluating open-domain dialogue systems is challenging for reasons such as the one-to-many problem, i.e., many appropriate responses other than just the golden response. As of now, automatic evaluation methods need …...

AbstractWith the increasing number of clinical trial reports generated every day, it is becoming hard to keep up with novel discoveries that inform evidence-based healthcare recommendations. To help automate this …...

AbstractMulti-task learning (MTL) aims at achieving a better model by leveraging data and knowledge from multiple tasks. However, MTL does not always work – sometimes negative transfer occurs between tasks, …...