Өнердің қазіргі жағдайы

We address the problem of sentence align- ment for monolingual corpora, a phe- nomenon distinct from alignment in par- allel corpora. Aligning large compara- ble corpora automatically would provide a …...

Supervised learning methods for WSD yield better performance than unsupervised methods. Yet the availability of clean training data for the former is still a severe challenge. In this paper, we …...

This paper presents an approach for question analysis that defines the question subject and its required answer type by building a trie- based structure from a set of question patterns. …...

Active learning is well-suited to many prob- lems in natural language processing, where unlabeled data may be abundant but annota- tion is slow and expensive. This paper aims to shed …...

We present a random-walk-based approach to learning paraphrases from bilingual parallel corpora. The corpora are represented as a graph in which a node corresponds to a phrase, and an edge …...

Most supervised language processing sys- tems show a significant drop-off in per- formance when they are tested on text that comes from a domain significantly different from the domain of …...

The PECO framework is a knowledge repre- sentation for formulating clinical questions. Queries are decomposed into four aspects, which are Patient-Problem (P), Exposure (E), Comparison (C) and Outcome (O). However, …...

Quote extraction and attribution is the task of automatically extracting quotes from text and attributing each quote to its correct speaker. The present state-of-the-art system uses gold standard information from …...

Taxonomies can serve as browsing tools for document collections. However, given an ar- bitrary collection, pre-constructed taxonomies could not easily adapt to the specific topic/task present in the collection. This …...

Concept-to-text generation refers to the task of automatically producing textual output from non-linguistic input. We present a joint model that captures content selection (“what to say”) and surface realization (“how …...

We propose a novel approach for develop- ing a two-stage document-level discourse parser. Our parser builds a discourse tree by applying an optimal parsing algorithm to probabilities inferred from two …...

This paper proposes a combined model for POS tagging, dependency parsing and co-reference resolution for Bulgarian — a pro-drop Slavic language with rich mor- phosyntax. We formulate an extension of …...

Generation for Focused Meeting Summarization Lu Wang Department of Computer Science Cornell University Ithaca, NY 14853 luwang@cs.cornell.edu Claire Cardie Department of Computer Science Cornell University Ithaca, NY 14853 cardie@cs.cornell.edu Abstract …...

AbstractJoint morphological and syntactic analysis has been proposed as a way of improving parsing accuracy for richly inflected languages. Starting from a transition-based model for joint part-of-speech tagging and dependency …...

We study multi-source transfer parsing for resource-poor target languages; specifically methods for target language adaptation of delexicalized discriminative graph-based de- pendency parsers. We first show how recent insights on selective …...

Scope detection is a key task in information ex- traction. This paper proposes a new approach for tree kernel-based scope detection by using the structured syntactic parse information. In addi- …...

Twitter is the largest source of microblog text, responsible for gigabytes of human discourse every day. Processing microblog text is diffi- cult: the genre is noisy, documents have lit- tle …...

In this paper, we explore the utility of intra- and inter-sentential causal relations between terms or clauses as evidence for answering why-questions. To the best of our knowledge, this is …...

In this paper we present an in-depth study on automatic feature selection for beam-search depen- dency parsers. The search strategy is inherited from the one implemented in MaltOptimizer, but searches …...

While automatic keyphrase extraction has been examined extensively, state-of-the- art performance on this task is still much lower than that on many core natural lan- guage processing tasks. We present …...

AbstractThe past 10 years of event ordering research has focused on learning partial orderings over document events and time expressions. The most popular corpus, the TimeBank, contains a small subset …...

Most existing relation extraction models make predictions for each entity pair lo- cally and individually, while ignoring im- plicit global clues available in the knowl- edge base, sometimes leading to …...

We introduce a supervised model for predicting word importance that incorporates a rich set of features. Our model is superior to prior approaches for identifying words used in human summaries. …...

We present a novel technique for learn- ing semantic representations, which ex- tends the distributional hypothesis to mul- tilingual data and joint-space embeddings. Our models leverage parallel data and learn …...

AbstractAutomatic synonyms and semantically related word extraction is a challenging task, useful in many NLP applications such as question answering, search query expansion, text summarization, etc. While different studies addressed …...

AbstractExtracting instances of sentiment-oriented relations from user-generated web documents is important for online marketing analysis. Unlike previous work, we formulate this extraction task as a structured prediction problem and design …...

Designing measures that capture various aspects of language ability is a central task in the design of systems for auto- matic scoring of spontaneous speech. In this study, we address …...

AbstractThis paper presents an end-to-end automatic processing system for Arabic. The system performs: correction of common spelling errors pertaining to different forms of alef, ta marbouta and ha, and alef …...

Supervised machine learning classifica- tion algorithms assume both train and test data are sampled from the same domain or distribution. However, performance of the algorithms degrade for test data from …...

AbstractMost state-of-the-art systems today produce morphological analysis based only on orthographic patterns. In contrast, we propose a model for unsupervised morphological analysis that integrates orthographic and semantic views of words. …...

Current approaches to cross-lingual informa- tion retrieval (CLIR) rely on standard retrieval models into which query translations by sta- tistical machine translation (SMT) are inte- grated at varying degree. In …...

We approach the task of morphological inflec- tion generation as discriminative string trans- duction. Our supervised system learns to gen- erate word-forms from lemmas accompanied by morphological tags, and refines …...

Implicit discourse relation recognition re- mains a serious challenge due to the ab- sence of discourse connectives. In this pa- per, we propose a Shallow Convolutional Neural Network (SCNN) for …...

Existing timeline generation systems for com- plex events consider only information from traditional media, ignoring the rich social con- text provided by user-generated content that reveals representative public interests or …...

Opinion mining from customer reviews has become pervasive in recent years. Sentences in reviews, however, are usually classified in- dependently, even though they form part of a review’s argumentative structure. …...

AbstractAnswer sentence ranking and answer extraction are two key challenges in question answering that have traditionally been treated in isolation, i.e., as independent tasks. In this article, we (1) explain …...

We study the problem of identifying individu- als based on their characteristic gaze patterns during reading of arbitrary text. The motiva- tion for this problem is an unobtrusive biomet- ric …...

Discourse parsing is considered as one of the most challenging natural language processing (NLP) tasks. Implicit discourse relation clas- sification is the bottleneck for discourse pars- ing. Without the guide …...

How can we enable computers to automat- ically answer questions like “Who created the character Harry Potter”? Carefully built knowledge bases provide rich sources of facts. However, it remains a …...

AbstractWhen processing arguments in online user interactive discourse, it is often necessary to determine their bases of support. In this paper, we describe a supervised approach, based on deep neural …...

The goal of Event extraction is to extract struc- tured information of events that are of interest from unstructured documents. Existing event extractors for social media suffer from two major …...

RST-style document-level discourse parsing remains a difficult task and efficient deep learning models on this task have rarely been presented. In this paper, we propose an attention-based hierarchical neural network …...

AbstractDistributional thesauri are useful in many tasks of Natural Language Processing. In this paper, we address the problem of building and evaluating such thesauri with the help of Information Retrieval …...

Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complemen- tary approaches. Distributional methods, whose supervised variants are the cur- rent best …...

We propose a framework for lexical sub- stitution that is able to perform transfer learning across languages. Datasets for this task are available in at least three languages (English, Italian, …...

We describe a neural shift-reduce parsing model for CCG, factored into four unidirec- tional LSTMs and one bidirectional LSTM. This factorization allows the linearization of the complete parsing history, and …...

Metaphor is a common linguistic tool in communication, making its detection in discourse a crucial task for natural lan- guage understanding. One popular ap- proach to this challenge is to …...

We present EpiReader, a novel model for ma- chine comprehension of text. Machine com- prehension of unstructured, real-world text is a major research goal for natural language pro- cessing. Current …...

Canonical morphological segmentation aims to divide words into a sequence of stan- dardized segments. In this work, we propose a character-based neural encoder- decoder model for this task. Additionally, we …...

Traditional approaches to extractive summarization rely heavily on human- engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a …...

AbstractIn this paper we propose an approach to predict punctuation marks for unsegmented speech transcript. The approach is purely lexical, with pre-trained Word Vectors as the only input. A training …...

We describe TweeTIME, a temporal tagger for recognizing and normalizing time expres- sions in Twitter. Most previous work in so- cial media analysis has to rely on tempo- ral resolvers …...

AbstractAutomatic evaluation of Machine Translation (MT) is typically approached by measuring similarity between the candidate MT and a human reference translation. An important limitation of existing evaluation systems is that …...

AbstractIn cross-lingual dependency annotation projection, information is often lost during transfer because of early decoding. We present an end-to-end graph-based neural network dependency parser that can be trained to reproduce …...

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 …...

AbstractTraditional supervised learning makes the closed-world assumption that the classes appeared in the test data must have appeared in training. This also applies to text learning or text classification. As …...

AbstractSemantic parsing shines at analyzing complex natural language that involves composition and computation over multiple pieces of evidence. However, datasets for semantic parsing contain many factoid questions that can be …...

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 …...

AbstractThis paper proposes to tackle the AMR parsing bottleneck by improving two components of an AMR parser: concept identification and alignment. We first build a Bidirectional LSTM based concept identifier …...

AbstractIn order to determine argument structure in text, one must understand how individual components of the overall argument are linked. This work presents the first neural network-based approach to link …...

AbstractKnowledge base population (KBP) systems take in a large document corpus and extract entities and their relations. Thus far, KBP evaluation has relied on judgements on the pooled predictions of …...

AbstractWe study automatic question generation for sentences from text passages in reading comprehension. We introduce an attention-based sequence learning model for the task and investigate the effect of encoding sentence- …...

AbstractWe present a novel multi-task attention based neural network model to address implicit discourse relationship representation and identification through two types of representation learning, an attention based neural network for …...

AbstractGlobal constraints and reranking have not been used in cognates detection research to date. We propose methods for using global constraints by performing rescoring of the score matrices produced by …...

AbstractWord embeddings seek to recover a Euclidean metric space by mapping words into vectors, starting from words co-occurrences in a corpus. Word embeddings may underestimate the similarity between nearby words, …...

Recently, many studies indicate that charac- ter language model can capture syntactic- semantic word features, resulting in state-of- the-art performance in typical NLP sequence labeling tasks. This paper shows the …...

Supervised models for Word Sense Disambiguation (WSD) currently yield to state-of-the-art results in the most popular benchmarks. Despite the recent...

AbstractWe argue that semantic meanings of a sentence or clause can not be interpreted independently from the rest of a paragraph, or independently from all discourse relations and the overall …...

AbstractThe first stage of every knowledge base question answering approach is to link entities in the input question. We investigate entity linking in the context of question answering task and …...

AbstractAn essential step in FrameNet Semantic Role Labeling is the Frame Identification (FrameId) task, which aims at disambiguating a situation around a predicate. Whilst current FrameId methods rely on textual …...

AbstractVisual Question Answering (VQA) is a well-known and challenging task that requires systems to jointly reason about natural language and vision. Deep learning models in various forms have been the …...

AbstractAlthough transfer learning has been shown to be successful for tasks like object and speech recognition, its applicability to question answering (QA) has yet to be well-studied. In this paper, …...

AbstractWe present a neural model for question generation from knowledge graphs triples in a “Zero-shot” setup, that is generating questions for predicate, subject types or object types that were not …...

AbstractWhile rule-based detection of subject-verb agreement (SVA) errors is sensitive to syntactic parsing errors and irregularities and exceptions to the main rules, neural sequential labelers have a tendency to overfit …...

AbstractWe propose an unsupervised approach for assessing conceptual complexity of texts, based on spreading activation. Using DBpedia knowledge graph as a proxy to long-term memory, mentioned concepts become activated and …...

AbstractThe Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning. In this paper, we show that the performance …...

AbstractThe recently released FEVER dataset provided benchmark results on a fact-checking task in which given a factual claim, the system must extract textual evidence (sets of sentences from Wikipedia pages) …...

AbstractThe success of neural summarization models stems from the meticulous encodings of source articles. To overcome the impediments of limited and sometimes noisy training data, one promising direction is to …...

AbstractKnowledge Bases (KBs) require constant updating to reflect changes to the world they represent. For general purpose KBs, this is often done through Relation Extraction (RE), the task of predicting …...

AbstractVariational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model …...

AbstractWe explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual sentence embeddings; (ii) a …...

AbstractWhile translating between East Asian languages, many works have discovered clear advantages of using characters as the translation unit. Unfortunately, traditional recurrent neural machine translation systems hinder the practical usage …...

AbstractIn order for coreference resolution systems to be useful in practice, they must be able to generalize to new text. In this work, we demonstrate that the performance of the …...

AbstractIn standard NLP pipelines, morphological analysis and disambiguation (MA&D) precedes syntactic and semantic downstream tasks. However, for languages with complex and ambiguous word-internal structure, known as morphologically rich languages (MRLs), …...

AbstractThe lack of word boundaries information has been seen as one of the main obstacles to develop a high performance Chinese named entity recognition (NER) system. Fortunately, the automatically constructed …...

AbstractIn this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, …...

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 …...

AbstractIncorporating domain knowledge is vital in building successful natural language processing (NLP) applications. Many times, cross-domain application of a tool results in poor performance as the tool does not account …...

AbstractWhile contextualized embeddings have produced performance breakthroughs in many Natural Language Processing (NLP) tasks, Word Sense Disambiguation (WSD) has not benefited from them yet. In this paper, we introduce QBERT, …...

AbstractResearch on parsing language to SQL has largely ignored the structure of the database (DB) schema, either because the DB was very simple, or because it was observed at both …...

AbstractRegularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in …...

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. …...

AbstractPrior work has shown that, on small amounts of training data, syntactic neural language models learn structurally sensitive generalisations more successfully than sequential language models. However, their computational complexity renders …...

AbstractExisting models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level. In this paper, we …...

AbstractLexical relations describe how meanings of terms relate to each other. Typical examples include hypernymy, synonymy, meronymy, etc. Automatic distinction of lexical relations is vital for NLP applications, and also …...

AbstractVisual Dialog is a multi-modal task that requires a model to participate in a multi-turn human dialog grounded on an image, and generate correct, human-like responses. In this paper, we …...

AbstractWe report our ongoing work about a new deep architecture working in tandem with a statistical test procedure for jointly training texts and their label descriptions for multi-label and multi-class …...

AbstractUnsupervised relation extraction aims at extracting relations between entities in text. Previous unsupervised approaches are either generative or discriminative. In a supervised setting, discriminative approaches, such as deep neural network …...

AbstractHumans use language to refer to entities in the external world. Motivated by this, in recent years several models that incorporate a bias towards learning entity representations have been proposed. …...

AbstractApplications such as machine translation, speech recognition, and information retrieval require efficient handling of noun compounds as they are one of the possible sources for out of vocabulary words. In-depth …...

AbstractOne of the primary tasks of morphological parsers is the disambiguation of homographs. Particularly difficult are cases of unbalanced ambiguity, where one of the possible analyses is far more frequent …...

AbstractIn historical linguistics, cognate detection is the task of determining whether sets of words have common etymological roots. Inspired by the comparative method used by human linguists, we develop a …...

AbstractAdversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based …...

AbstractThere has been an influx of biomedical domain-specific language models, showing language models pre-trained on biomedical text perform better on biomedical domain benchmarks than those trained on general domain text …...

AbstractCatastrophic forgetting in neural networks indicates the performance decreasing of deep learning models on previous tasks while learning new tasks. To address this problem, we propose a novel Continual Learning …...

AbstractPrevious studies have shown that hierarchical multi-task learning (MTL) can utilize task dependencies by stacking encoders and outperform democratic MTL. However, stacking encoders only considers the dependencies of feature representations …...

AbstractThis paper illustrates Huawei’s submission to the WMT20 low-resource parallel corpus filtering shared task. Our approach focuses on developing a proxy task learner on top of a transformer-based multilingual pre-trained …...

AbstractDialog state tracking (DST) is a core component in task-oriented dialog systems. Existing approaches for DST mainly fall into one of two categories, namely, ontology-based and ontology-free methods. An ontology-based …...

AbstractCurrent summarization systems only produce plain, factual headlines, far from the practical needs for the exposure and memorableness of the articles. We propose a new task, Stylistic Headline Generation (SHG), …...

AbstractWe study the influence of context on sentence acceptability. First we compare the acceptability ratings of sentences judged in isolation, with a relevant context, and with an irrelevant context. Our …...

AbstractContext-dependent text-to-SQL task has drawn much attention in recent years. Previous models on context-dependent text-to-SQL task only concentrate on utilizing historic user inputs. In this work, in addition to using …...

AbstractEvaluating image captions is very challenging partially due to the fact that there are multiple correct captions for every single image. Most of the existing one-to-one metrics operate by penalizing …...

AbstractWe present a novel iterative, edit-based approach to unsupervised sentence simplification. Our model is guided by a scoring function involving fluency, simplicity, and meaning preservation. Then, we iteratively perform word …...

AbstractCross-domain sentiment analysis has received significant attention in recent years, prompted by the need to combat the domain gap between different applications that make use of sentiment analysis. In this …...

AbstractThis paper focuses on tree-based modeling for the sentence classification task. In existing works, aggregating on a syntax tree usually considers local information of sub-trees. In contrast, in addition to …...

AbstractMost previous work on knowledge graph completion conducted single-view prediction or calculation for candidate triple evaluation, based only on the content information of the candidate triples. This paper describes a …...

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 …...

AbstractWeb-crawled data provides a good source of parallel corpora for training machine translation models. It is automatically obtained, but extremely noisy, and recent work shows that neural machine translation systems …...

AbstractAnswering questions in many real-world applications often requires complex and precise information excerpted from texts spanned across a long document. However, currently no such annotated dataset is publicly available, which …...

AbstractModern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfer systems …...

AbstractExisting metonymy resolution approaches rely on features extracted from external resources like dictionaries and hand-crafted lexical resources. In this paper, we propose an end-to-end word-level classification approach based only on …...

AbstractQuality Estimation (QE) is an important component in making Machine Translation (MT) useful in real-world applications, as it is aimed to inform the user on the quality of the MT …...

AbstractZero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning …...

AbstractZero pronoun recovery and resolution aim at recovering the dropped pronoun and pointing out its anaphoric mentions, respectively. We propose to better explore their interaction by solving both tasks together, …...

AbstractEdit-based text simplification systems have attained much attention in recent years due to their ability to produce simplification solutions that are interpretable, as well as requiring less training examples compared …...

Code summarization (CS) is becoming a promising area in recent language understand- ing, which aims to generate sensible human language automatically for programming lan- guage in the format of source …...

AbstractDespite recent promising results on the application of span-based models for event reference interpretation, there is a lack of understanding of what has been improved. We present an empirical analysis …...

AbstractCross-document event coreference resolution (CDCR) is the task of identifying which event mentions refer to the same events throughout a collection of documents. Annotating CDCR data is an arduous and …...

AbstractThis paper presents an empirical study to efficiently build named entity recognition (NER) systems when a small amount of in-domain labeled data is available. Based upon recent Transformer-based self-supervised pre-trained …...

AbstractRetrieval-based dialogue systems display an outstanding performance when pre-trained language models are used, which includes bidirectional encoder representations from transformers (BERT). During the multi-turn response selection, BERT focuses on training …...

Recent progress has been made in using BERT framework for Chinese spelling error correc- tion (CSC). However, most existing methods correct words based on local contextual in- formation, without considering …...

AbstractThis paper studies joint models for selecting correct answer sentences among the top k provided by answer sentence selection (AS2) modules, which are core components of retrieval-based Question Answering (QA) …...

AbstractLexical inference in context (LIiC) is the task of recognizing textual entailment between two very similar sentences, i.e., sentences that only differ in one expression. It can therefore be seen …...

AbstractLack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data …...

We generalize deep self-attention distillation in MINILM (Wang et al., 2020) by only us- ing self-attention relation distillation for task- agnostic compression of pretrained Transform- ers. In particular, we define …...

AbstractRetrieving relevant contexts from a large corpus is a crucial step for tasks such as open-domain question answering and fact checking. Although neural retrieval outperforms traditional methods like tf-idf and …...

AbstractPrior methods to text segmentation are mostly at token level. Despite the adequacy, this nature limits their full potential to capture the long-term dependencies among segments. In this work, we …...

AbstractDespite the impressive successes of generation and dialogue systems, how to endow a text generation system with particular personality traits to deliver more personalized responses remains under-investigated. In this work, …...

AbstractWe present a grounded neural dialogue model that successfully collaborates with people in a partially-observable reference game. We focus on a setting where two agents each observe an overlapping part …...

AbstractAspect-based sentiment analysis (ABSA) task consists of three typical subtasks: aspect term extraction, opinion term extraction, and sentiment polarity classification. These three subtasks are usually performed jointly to save resources …...

AbstractWe present a set of novel neural supervised and unsupervised approaches for determining the readability of documents. In the unsupervised setting, we leverage neural language models, whereas in the supervised …...

AbstractPredicting the subsequent event for an existing event context is an important but challenging task, as it requires understanding the underlying relationship between events. Previous methods propose to retrieve relational …...

AbstractCross-domain sentiment analysis has achieved promising results with the help of pre-trained language models. As GPT-3 appears, prompt tuning has been widely explored to enable better semantic modeling in many …...

AbstractNLP has advanced greatly together with the proliferation of Transformer-based pre-trained language models. To adapt to a downstream task, the pre-trained language models need to be fine-tuned with a sufficient …...

AbstractKnowledge graph integration typically suffers from the widely existing dangling entities that cannot find alignment cross knowledge graphs (KGs). The dangling entity set is unavailable in most real-world scenarios, and …...

AbstractSemantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these …...

Chinese word segmentation has entered the deep learning era which greatly reduces the hassle of feature engineering. Recently, some researchers attempted to treat it as character- level translation, which further …...

AbstractCross-lingual question answering is a thriving field in the modern world, helping people to search information on the web more efficiently. One of the important scenarios is to give an …...

AbstractThis work presents methods for learning cross-lingual sentence representations using paired or unpaired bilingual texts. We hypothesize that the cross-lingual alignment strategy is transferable, and therefore a model trained to …...

AbstractMost existing approaches to Visual Question Answering (VQA) answer questions directly, however, people usually decompose a complex question into a sequence of simple sub questions and finally obtain the answer …...

AbstractPretrained language models have significantly improved the performance of downstream language understanding tasks, including extractive question answering, by providing high-quality contextualized word embeddings. However, training question answering models still requires …...

AbstractWord alignment which aims to extract lexicon translation equivalents between source and target sentences, serves as a fundamental tool for natural language processing. Recent studies in this area have yielded …...

AbstractDue to the limitations of the model structure and pre-training objectives, existing vision-and-language generation models cannot utilize pair-wise images and text through bi-directional generation. In this paper, we propose DU-VLG, …...

AbstractFusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop …...

AbstractPre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems. Despite their success, existing methods often formulate this task as a cascaded generation problem which can lead …...

AbstractThe information in tables can be an important complement to text, making table-based question answering (QA) systems of great value. The intrinsic complexity of handling tables often adds an extra …...

AbstractRecent studies on few-shot intent detection have attempted to formulate the task as a meta-learning problem, where a meta-learning model is trained with a certain capability to quickly adapt to …...

AbstractDiscontinuous constituency parsing is still kept developing for its efficiency and accuracy are far behind its continuous counterparts. Motivated by the observation that a discontinuous constituent tree can be simply …...

AbstractPrompt-based approaches excel at few-shot learning. However, Perez et al. (2021) recently cast doubt on their performance as they had difficulty getting good results in a “true” few-shot setting in …...

AbstractRecent research on multi-criteria Chinese word segmentation (MCCWS) mainly focuses on building complex private structures, adding more handcrafted features, or introducing complex optimization processes. In this work, we show that …...

AbstractOutside-knowledge visual question answering is a challenging task that requires both the acquisition and the use of open-ended real-world knowledge. Some existing solutions draw external knowledge into the cross-modality space …...

AbstractWhile there has been a recent burgeoning of applications at the intersection of natural and programming languages, such as code generation and code summarization, these applications are usually English-centric. This …...

AbstractDirectly learning from complex examples is generally problematic for humans and machines. Indeed, a better strategy is exposing learners to examples in a reasonable, pedagogically-motivated order. Curriculum Learning (CL) has …...

AbstractMany machine learning-based low-code or no-code applications involve generating code that interacts with structured knowledge. For example, one of the most studied tasks in this area is generating SQL code …...

AbstractLarge-scale pre-trained models (PTMs) have been widely used in document-oriented NLP tasks, such as question answering. However, the encoding-task coupling requirement results in the repeated encoding of the same documents …...

AbstractMulti-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows. To step over these …...

AbstractDialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline. Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response …...

AbstractA major issue with using deep learning models in sensitive applications is that they provide no explanation for their output. To address this problem, unsupervised selective rationalization produces rationales alongside …...