Увеличение данных

We propose a novel data augmentation ap- proach to enhance computational behav- ioral analysis using social media text. In particular, we collect a Twitter corpus of the descriptions of annoying …...

AbstractNowadays, neural networks play an important role in the task of relation classification. By designing different neural architectures, researchers have improved the performance to a large extent in comparison with …...

AbstractRapid progress has been made towards question answering (QA) systems that can extract answers from text. Existing neural approaches make use of expensive bi-directional attention mechanisms or score all possible …...

AbstractWe evaluate a semantic parser based on a character-based sequence-to-sequence model in the context of the SemEval-2017 shared task on semantic parsing for AMRs. With data augmentation, super characters, and …...

AbstractThis paper discusses the approach taken by the UWaterloo team to arrive at a solution for the Fine-Grained Sentiment Analysis problem posed by Task 5 of SemEval 2017. The paper …...

This paper investigates speaker adaptation techniques for bidirectional long short term memory (BLSTM) recurrent neural network based acoustic models (AMs) trained with the connectionist temporal classification (CTC) objective function. BLSTM-CTC …...

Lack of parallel training data influences the rare word problem in Neural Machine Translation (NMT) systems, particularly for under- resourced languages. Using synthetic parallel training data (data augmentation) is a …...

AbstractIn this paper, we study the problem of data augmentation for language understanding in task-oriented dialogue system. In contrast to previous work which augments an utterance without considering its relation …...

AbstractText summarization is considered as a challenging task in the NLP community. The availability of datasets for the task of multilingual text summarization is rare, and such datasets are difficult …...

AbstractNeural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data …...

AbstractIn a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually …...

AbstractState-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of possible transformations scales exponentially with text length, …...

AbstractThis paper describes FBK’s submission to the end-to-end speech translation (ST) task at IWSLT 2019. The task consists in the “direct” translation (i.e. without intermediate discrete representation) of English speech …...

AbstractSpoken Language Understanding (SLU) converts user utterances into structured semantic representations. Data sparsity is one of the main obstacles of SLU due to the high cost of human annotation, especially …...

AbstractLow-resource language pairs with a paucity of parallel data pose challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing a large amount of monolingual data …...

AbstractHierarchical neural networks are often used to model inherent structures within dialogues. For goal-oriented dialogues, these models miss a mechanism adhering to the goals and neglect the distinct conversational patterns …...

AbstractThis paper presents a detailed description of our participation in task 5 on SemEval-2019. This task consists of classifying English and Spanish tweets that contain hate towards women or immigrants. …...

AbstractLexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in generation tasks such as machine translation or monolingual text rewriting. We …...

AbstractMultilingual writers and speakers often alternate between two languages in a single discourse. This practice is called “code-switching”. Existing sentiment detection methods are usually trained on sentiment-labeled monolingual text. Manually …...

AbstractDespite the advancement of question answering (QA) systems and rapid improvements on held-out test sets, their generalizability is a topic of concern. We explore the robustness of QA models to …...

AbstractInsufficient or even unavailable training data of emerging classes is a big challenge of many classification tasks, including text classification. Recognising text documents of classes that have never been seen …...

AbstractMachine reading comprehension with unanswerable questions is a challenging task. In this work, we propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question …...

. This survey takes place in the general context of information extraction and presents more particularly the successive approaches to supervised event extraction from texts. The first rule-based systems and …...

AbstractWe present a simple yet powerful data augmentation method for boosting Neural Machine Translation (NMT) performance by leveraging information retrieved from a Translation Memory (TM). We propose and test two …...

AbstractThis paper describes the participation of the SINAI-DL team at RumourEval (Task 7 in SemEval 2019, subtask A: SDQC). SDQC addresses the challenge of rumour stance classification as an indirect …...

AbstractWhile data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In …...

AbstractInducing diversity in the task of paraphrasing is an important problem in NLP with applications in data augmentation and conversational agents. Previous paraphrasing approaches have mainly focused on the issue …...

. This survey takes place in the general context of information extraction and presents more particularly the successive approaches to supervised event extraction from texts. The first rule-based systems and …...

AbstractMany Data Augmentation (DA) methods have been proposed for neural machine translation. Existing works measure the superiority of DA methods in terms of their performance on a specific test set, …...

AbstractThis work proposes a standalone, complete Chinese discourse parser for practical applications. We approach Chinese discourse parsing from a variety of aspects and improve the shift-reduce parser not only by …...

AbstractDetection of some types of toxic language is hampered by extreme scarcity of labeled training data. Data augmentation – generating new synthetic data from a labeled seed dataset – can …...

AbstractDomain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose …...

AbstractSimple yet effective data augmentation techniques have been proposed for sentence-level and sentence-pair natural language processing tasks. Inspired by these efforts, we design and compare data augmentation for named entity …...

AbstractOne critical issue of zero anaphora resolution (ZAR) is the scarcity of labeled data. This study explores how effectively this problem can be alleviated by data augmentation. We adopt a …...

AbstractThe prior work on natural language inference (NLI) debiasing mainly targets at one or few known biases while not necessarily making the models more robust. In this paper, we focus …...

AbstractAnalogy is assumed to be the cognitive mechanism speakers resort to in order to inflect an unknown form of a lexeme based on knowledge of other words in a language. …...

AbstractLow-resource machine translation suffers from the scarcity of training data and the unavailability of standard evaluation sets. While a number of research efforts target the former, the unavailability of evaluation …...

AbstractModels with a large number of parameters are prone to over-fitting and often fail to capture the underlying input distribution. We introduce Emix, a data augmentation method that uses interpolations …...

AbstractOur goal is to develop an intelligent assistant to support users explore data via visualizations. We have collected a new corpus of conversations, CHICAGO-CRIME-VIS, geared towards supporting data visualization exploration, …...

AbstractCounterfactuals describe events counter to facts and hence naturally involve common sense, knowledge, and reasoning. SemEval 2020 task 5 is focusing on this field. We participate in the subtask 1 …...

AbstractWe participated in all three subtasks. In subtasks A and B, our submissions are based on pretrained language representation models (namely ALBERT) and data augmentation. We experimented with solving the …...

AbstractWe propose a Semi-supervIsed GeNerative Active Learning (SIGNAL) model to address the imbalance, efficiency, and text camouflage problems of Chinese text spam detection task. A “self-diversity” criterion is proposed for …...

AbstractAspect term extraction aims to extract aspect terms from review texts as opinion targets for sentiment analysis. One of the big challenges with this task is the lack of sufficient …...

AbstractWe introduce CGA, a conditional VAE architecture, to control, generate, and augment text. CGA is able to generate natural English sentences controlling multiple semantic and syntactic attributes by combining adversarial …...

AbstractData augmentation techniques have been widely used to improve machine learning performance as they facilitate generalization. In this work, we propose a novel augmentation method to generate high quality synthetic …...

AbstractUtterance classification is a key component in many conversational systems. However, classifying real-world user utterances is challenging, as people may express their ideas and thoughts in manifold ways, and the …...

AbstractData augmentation is proven to be effective in many NLU tasks, especially for those suffering from data scarcity. In this paper, we present a powerful and easy to deploy text …...

AbstractRecent advances in open-domain dialogue systems rely on the success of neural models that are trained on large-scale data. However, collecting large-scale dialogue data is usually time-consuming and labor-intensive. To …...

In the text classification problem, the im- balance of labels in datasets affect the per- formance of the text-classification models. Practically, the data about user comments on social networking sites …...

AbstractWe investigate how to improve quality of low-resource morphological inflection without annotating more data. We examine two methods, language models and data augmentation. We show that the model whose decoder …...

AbstractThe ability of machine translation (MT) models to correctly place markup is crucial to generating high-quality translations of formatted input. This paper compares two commonly used methods of representing markup …...

AbstractNeural Natural Language Generation (NLG) systems are well known for their unreliability. To overcome this issue, we propose a data augmentation approach which allows us to restrict the output of …...

AbstractThe incorporation of data augmentation method in grammatical error correction task has attracted much attention. However, existing data augmentation methods mainly apply noise to tokens, which leads to the lack …...

AbstractTweets are specific text data when compared to general text. Although sentiment analysis over tweets has become very popular in the last decade for English, it is still difficult to …...

AbstractSpoken language understanding (SLU), which converts user requests in natural language to machine-interpretable expressions, is becoming an essential task. The lack of training data is an important problem, especially for …...

AbstractA variety of natural language tasks require processing of textual data which contains a mix of natural language and formal languages such as mathematical expressions. In this paper, we take …...

AbstractModern models of event causality detection (ECD) are mainly based on supervised learning from small hand-labeled corpora. However, hand-labeled training data is expensive to produce, low coverage of causal expressions, …...

AbstractOne of the cardinal tasks in achieving robust medical question answering systems is textual entailment. The existing approaches make use of an ensemble of pre-trained language models or data augmentation, …...

AbstractThis paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples …...

AbstractMixup is a latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by interpolating images at the pixel …...

Recent studies on direct speech translation show continuous improvements by means of data augmentation techniques and bigger deep learning models. While these methods are helping to close the gap between …...

AbstractWe analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing F1 score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce …...

AbstractExisting approaches to disfluency detection heavily depend on human-annotated data. Numbers of data augmentation methods have been proposed to alleviate the dependence on labeled data. However, current augmentation approaches such …...

AbstractThis paper presents a solution for the Span Identification (SI) task in the “Detection of Propaganda Techniques in News Articles” competition at SemEval-2020. The goal of the SI task is …...

In this research, we developed the Taiwanese speech recognition system which used the Kaldi toolkit to implement. The Taiwanese corpus was collected by Taiwan Taiwanese National Reading Competition and Classmate …...

AbstractIn this paper we propose a novel data augmentation approach where guided outputs of a language generation model, e.g. GPT-2, when labeled, can improve the performance of text classifiers through …...

AbstractWhile deep learning models are making fast progress on the task of Natural Language Inference, recent studies have also shown that these models achieve high accuracy by exploiting several dataset …...

AbstractRecent developments in Neural Relation Extraction (NRE) have made significant strides towards Automated Knowledge Base Construction. While much attention has been dedicated towards improvements in accuracy, there have been no …...

AbstractThis paper presents the team TransQuest’s participation in Sentence-Level Direct Assessment shared task in WMT 2020. We introduce a simple QE framework based on cross-lingual transformers, and we use it …...

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 …...

Data augmentation has recently seen increased interest in NLP due to more work in low- resource domains, new tasks, and the popu- larity of large-scale neural networks that re- quire …...

AbstractCoreference resolution is an important compo-nent in analyzing narrative text from admin-istrative data (e.g., clinical or police sources).However, existing coreference models trainedon general language corpora suffer from poortransferability due to …...

AbstractThis paper describes the system of the Cambridge team submitted to the SemEval-2021 shared task on Multilingual and Cross-lingual Word-in-Context Disambiguation. Building on top of a pre-trained masked language model, …...

Cognate prediction is the task of generating, in a given language, the likely cognates of words in a related language, where cognates are words in related languages that have evolved …...

AbstractWe introduce the well-established social scientific concept of social solidarity and its contestation, anti-solidarity, as a new problem setting to supervised machine learning in NLP to assess how European solidarity …...

AbstractFine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual fine-tuning with consistency regularization. Specifically, we use …...

AbstractRecent years have witnessed various types of generative models for natural language generation (NLG), especially RNNs or transformer based sequence-to-sequence models, as well as variational autoencoder (VAE) and generative adversarial …...

AbstractRecent work learns contextual representations of source code by reconstructing tokens from their context. For downstream semantic understanding tasks like code clone detection, these representations should ideally capture program functionality. …...

The performance of state-of-the-art neural rankers can deteriorate substantially when ex- posed to noisy inputs or applied to a new domain. In this paper, we present a novel method for …...

AbstractText Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that are trained end-to-end to …...

AbstractTask-oriented dialogue systems typically rely on large amounts of high-quality training data or require complex handcrafted rules. However, existing datasets are often limited in size con- sidering the complexity of …...

AbstractWe propose a data augmentation method for neural machine translation. It works by interpreting language models and phrasal alignment causally. Specifically, it creates augmented parallel translation corpora by generating (path-specific) …...

AbstractThis paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a …...

AbstractThe automatic detection of hypernymy relationships represents a challenging problem in NLP. The successful application of state-of-the-art supervised approaches using distributed representations has generally been impeded by the limited availability …...

AbstractData augmentation is an effective way to improve the performance of many neural text generation models. However, current data augmentation methods need to define or choose proper data mapping functions …...

AbstractWe introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method …...

AbstractData augmentation aims at expanding training data with clean text using noising schemes to improve the performance of grammatical error correction (GEC). In practice, there are a great number of …...

AbstractData augmentation has attracted a lot of research attention in the deep learning era for its ability in alleviating data sparseness. The lack of labeled data for unseen evaluation databases …...

AbstractConcerning the development of Chinese medical speech recognition technology, this study re-addresses earlier encountered issues in accordance with the process of Machine Learning Engineering for Production (MLOps) from a data …...

AbstractLexical complexity plays an important role in reading comprehension. lexical complexity prediction (LCP) can not only be used as a part of Lexical Simplification systems, but also as a stand-alone …...

AbstractVisual question answering (VQA) is challenging not only because the model has to handle multi-modal information, but also because it is just so hard to collect sufficient training examples — …...

AbstractReranking models enable the integration of rich features to select a better output hypothesis within an n-best list or lattice. These models have a long history in NLP, and we …...

Existing bias mitigation methods to reduce disparities in model outcomes across cohorts have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training. Sep- arately, certified …...

AbstractWe introduce EfficientCL, a memory-efficient continual pretraining method that applies contrastive learning with novel data augmentation and curriculum learning. For data augmentation, we stack two types of operation sequentially: cutoff …...

AbstractBeing able to parse code-switched (CS) utterances, such as Spanish+English or Hindi+English, is essential to democratize task-oriented semantic parsing systems for certain locales. In this work, we focus on Spanglish …...

AbstractWe propose a novel hybrid approach to lemmatization that enhances the seq2seq neural model with additional lemmas extracted from an external lexicon or a rule-based system. During training, the enhanced …...

AbstractWhile state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying …...

AbstractFew-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. …...

AbstractFine-tuning large pre-trained models with task-specific data has achieved great success in NLP. However, it has been demonstrated that the majority of information within the self-attention networks is redundant and …...

AbstractLemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Most prior work on ML based lemmatization has focused on …...

AbstractDeep neural networks have achieved state-of-the-art performances on named entity recognition(NER) with sufficient training data while they perform poorly in low-resource scenarios due to data scarcity. To solve this problem …...

We study calibration in question answering, es- timating whether model correctly predicts an- swer for each question. Unlike prior work which mainly rely on the model’s confidence score, our calibrator …...

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 …...

AbstractQA models based on pretrained language models have achieved remarkable performance on various benchmark datasets. However, QA models do not generalize well to unseen data that falls outside the training …...

AbstractWe describe our approach for SemEval-2021 task 6 on detection of persuasion techniques in multimodal content (memes). Our system combines pretrained multimodal models (CLIP) and chained classifiers. Also, we propose …...

AbstractThis paper describes Maastricht University’s participation in the IWSLT 2021 multilingual speech translation track. The task in this track is to build multilingual speech translation systems in supervised and zero-shot …...

AbstractData augmentation, which refers to manipulating the inputs (e.g., adding random noise,masking specific parts) to enlarge the dataset,has been widely adopted in machine learning. Most data augmentation techniques operate on …...

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, …...

AbstractCommunication between human and mobile agents is getting increasingly important as such agents are widely deployed in our daily lives. Vision-and-Dialogue Navigation is one of the tasks that evaluate the …...

AbstractRecent studies on neural networks with pre-trained weights (i.e., BERT) have mainly focused on a low-dimensional subspace, where the embedding vectors computed from input words (or their contexts) are located. …...

AbstractSound event detection (SED) system outputs sound events and their time boundaries in audio signals. We proposed an RCRNN-based SED system with residual connection and convolution block attention mechanism based …...

AbstractData augmentation and adversarial perturbation approaches have recently achieved promising results in solving the over-fitting problem in many natural language processing (NLP) tasks including sentiment classification. However, existing studies aimed …...

AbstractIn the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim …...

AbstractMost language understanding models in task-oriented dialog systems are trained on a small amount of annotated training data, and evaluated in a small set from the same distribution. However, these …...

AbstractIn open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is adopted to learn dense representations of …...

AbstractTo audit the robustness of named entity recognition (NER) models, we propose RockNER, a simple yet effective method to create natural adversarial examples. Specifically, at the entity level, we replace …...

AbstractA sufficient amount of annotated data is usually required to fine-tune pre-trained language models for downstream tasks. Unfortunately, attaining labeled data can be costly, especially for multiple language varieties and …...

AbstractBoth the issues of data deficiencies and semantic consistency are important for data augmentation. Most of previous methods address the first issue, but ignore the second one. In the cases …...

AbstractOpen-domain question answering has exploded in popularity recently due to the success of dense retrieval models, which have surpassed sparse models using only a few supervised training examples. However, in …...

AbstractWe address the compositionality challenge presented by the SCAN benchmark. Using data augmentation and a modification of the standard seq2seq architecture with attention, we achieve SOTA results on all the …...

AbstractThe goal of stance detection is to identify whether the author of a text is in favor of, neutral or against a specific target. Despite substantial progress on this task, …...

AbstractData augmentation aims to enrich training samples for alleviating the overfitting issue in low-resource or class-imbalanced situations. Traditional methods first devise task-specific operations such as Synonym Substitute, then preset the …...

AbstractThis paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task. We only participate in Task 2 (post-editing effort estimation) of the shared task, focusing on the …...

AbstractThis paper describes the submission of LMU Munich to the WMT 2021 multilingual machine translation task for small track #1, which studies translation between 6 languages (Croatian, Hungarian, Estonian, Serbian, …...

This paper describes the NTNU ASR system participating in the Formosa Speech Recognition Challenge 2020 (FSR-2020) supported by the Formosa Speech in the Wild project (FSW). FSR-2020 aims at fostering …...

AbstractThis paper describes our systems for negation detection and time expression recognition in SemEval 2021 Task 10, Source-Free Domain Adaptation for Semantic Processing. We show that self-training, active learning and …...

AbstractTransfer learning has yielded state-of-the-art (SoTA) results in many supervised NLP tasks. However, annotated data for every target task in every target language is rare, especially for low-resource languages. We …...

The lack of parallel data is an obstacle in data- driven grammatical error correction. Recently, researchers have addressed this problem by exploring data augmentation methods. number of studies have focused …...

AbstractData sharing restrictions are common in NLP, especially in the clinical domain, but there is limited research on adapting models to new domains without access to the original training data, …...

AbstractWe introduce a novel setup for low-resource task-oriented semantic parsing which incorporates several constraints that may arise in real-world scenarios: (1) lack of similar datasets/models from a related domain, (2) …...

AbstractDue to the widespread usage of social media sites and the enormous number of users who utilize irony implicit words in most of their tweets and posts, it has become …...

AbstractThis paper presents a new inflectional resource for Gitksan, a low-resource Indigenous language of Canada. We use Gitksan data in interlinear glossed format, stemming from language documentation efforts, to build …...

AbstractData augmentation techniques have been proven useful in many applications in NLP fields. Most augmentations are task-specific, and cannot be used as a general-purpose tool. In our work, we present …...

AbstractQuality Estimation (QE) models have the potential to change how we evaluate and maybe even train machine translation models. However, these models still lack the robustness to achieve general adoption. …...

AbstractThis paper describes our approach to develop a complex named entity recognition system in SemEval 2022 Task 11: MultiCoNER Multilingual Complex Named Entity Recognition,Track 9 - Chinese. In this task, …...

AbstractKnowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models. Recent years have seen a surge of research aiming to improve KD by leveraging Contrastive Learning, Intermediate …...

AbstractGenerating synthetic data for supervised learning from large-scale pre-trained language models has enhanced performances across several NLP tasks, especially in low-resource scenarios. In particular, many studies of data augmentation employ …...

AbstractFew-shot knowledge graph completion (FKGC) has become a new research focus in the field of knowledge graphs in recent years, which aims to predict the missing links for relations that …...

AbstractContextually aware intelligent agents are often required to understand the users and their surroundings in real-time. Our goal is to build Artificial Intelligence (AI) systems that can assist children in …...

AbstractAutomatic identification of cyberbullying from textual content is known to be a challenging task. The challenges arise from the inherent structure of cyberbullying and the lack of labeled large-scale corpus, …...

AbstractFine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. …...

AbstractRecently, the problem of robustness of pre-trained language models (PrLMs) has received increasing research interest. Latest studies on adversarial attacks achieve high attack success rates against PrLMs, claiming that PrLMs …...

AbstractText-to-SQL parsers typically struggle with databases unseen during the train time. Adapting Text-to-SQL parsers to new database schemas is a challenging problem owing to a vast diversity of schemas and …...

AbstractPreservation of domain knowledge from the source to target is crucial in any translation workflow. It is common in the translation industry to receive highly-specialized projects, where there is hardly …...

AbstractExisting methods on knowledge base question generation (KBQG) learn a one-size-fits-all model by training together all subgraphs without distinguishing the diverse semantics of subgraphs. In this work, we show that …...

AbstractFew-shot language learners adapt knowledge from a pre-trained model to recognize novel classes from a few-labeled sentences. In such settings, fine-tuning a pre-trained language model can cause severe over-fitting. In …...

AbstractLarge-scale pretrained language models have led to significant improvements in Natural Language Processing. Unfortunately, they come at the cost of high computational and storage requirements that complicate their deployment on …...

AbstractRecent studies show that NLP models trained on standard English texts tend to produce biased outcomes against underrepresented English varieties. In this work, we conduct a pioneering study of the …...

AbstractIn an era where social media platform users are growing rapidly, there has been a marked increase in hateful content being generated; to combat this, automatic hate speech detection systems …...

AbstractAutomatizing the process of understanding the global narrative structure of long texts and stories is still a major challenge for state-of-the-art natural language understanding systems, particularly because annotated data is …...

AbstractAutomating the fact checking (FC) process relies on information obtained from external sources. In this work, we posit that it is crucial for FC models to make veracity predictions only …...

Most Word-Sense Disambiguation (WSD) systems rely on machine learning approaches that require large-scale corpora for effective training. So, the quality of a WSD system degrades when trained in a low-resource …...

AbstractThis paper describes our system designed for SemEval-2022 Task 8: Multilingual News Article Similarity. We proposed a linguistics-inspired model trained with a few task-specific strategies. The main techniques of our …...

AbstractThis paper describes the translation systems trained by Huawei translation services center (HW-TSC) for the WMT22 biomedical translation task in five language pairs: English↔German (en↔de), English↔French (en↔fr), English↔Chinese (en↔zh), English↔Russian …...

AbstractPatronizing and Condescending Language is an ever-present problem in our day-to-day lives. There has been a rise in patronizing language on social media platforms manifesting itself in various forms. This …...

AbstractCommonsense knowledge about the typicalfunctions of physical objects allows people tomake inferences during sentence understanding. For example, we infer that “Sam enjoyedthe book” means that Sam enjoyed reading thebook, even …...

AbstractRecently, aspect sentiment quad prediction (ASQP) has become a popular task in the field of aspect-level sentiment analysis. Previous work utilizes a predefined template to paraphrase the original sentence into …...

AbstractNegation is a common linguistic feature that is crucial in many language understanding tasks, yet it remains a hard problem due to diversity in its expression in different types of …...

AbstractEven if recent Transformer-based architectures, such as BERT, achieved impressive results in semantic processing tasks, their fine-tuning stage still requires large scale training resources. Usually, Data Augmentation (DA) techniques can …...

AbstractSemantic Overlap Summarization (SOS) is a novel and relatively under-explored seq-to-seq task which entails summarizing common information from multiple alternate narratives. One of the major challenges for solving this task …...

AbstractData augmentation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as NER, data augmentation methods often suffer from token-label misalignment, which …...

AbstractTo overcome the data sparsity issue in short text topic modeling, existing methods commonly rely on data augmentation or the data characteristic of short texts to introduce more word co-occurrence …...

AbstractTraining with noisy labelled data is known to be detrimental to model performance, especially for high-capacity neural network models in low-resource domains. Our experiments suggest that standard regularisation strategies, such …...

AbstractParaphrasing, i.e., restating the same meaning in different ways, is an important data augmentation approach for natural language processing (NLP). Zhang et al. (2019b) propose to extract sentence-level paraphrases from …...

AbstractWe present the task of PreQuEL, Pre-(Quality-Estimation) Learning. A PreQuEL system predicts how well a given sentence will be translated, without recourse to the actual translation, thus eschewing unnecessary resource …...

AbstractQuestion answering (QA) has recently shown impressive results for answering questions from customized domains. Yet, a common challenge is to adapt QA models to an unseen target domain. In this …...

AbstractAs manually labelling data can be costly, some recent studies tend to augment the training data for improving the generalization power of machine learning models, known as data augmentation (DA). …...

AbstractThis paper introduces a new data augmentation method for neural machine translation that can enforce stronger semantic consistency both within and across languages. Our method is based on Conditional Masked …...

AbstractSentiment analysis is a classical problem of natural language processing. SemEval 2022 sets a problem on the structured sentiment analysis in task 10, which is also a study-worthy topic in …...

AbstractAlthough sequence-to-sequence models often achieve good performance in semantic parsing for i.i.d. data, their performance is still inferior in compositional generalization. Several data augmentation methods have been proposed to alleviate …...

AbstractTable-based fact verification aims to verify whether a statement sentence is trusted or fake. Most existing methods rely on graph feature or data augmentation but fail to investigate evidence correlation …...

AbstractControlled text perturbation is useful for evaluating and improving model generalizability. However, current techniques rely on training a model for every target perturbation, which is expensive and hard to generalize. …...

AbstractThis paper describes Tencent’s multilingual machine translation systems for the WMT22 shared task on Large-Scale Machine Translation Evaluation for African Languages. We participated in the constrained translation track in which …...

AbstractThe ARC-NKUA (“Athena” Research Center - National and Kapodistrian University of Athens) submission to the WMT22 General Machine Translation shared task concerns the unconstrained tracks of the English-Ukrainian and Ukrainian-English …...

AbstractUnderstanding the functional (dis)-similarity of source code is significant for code modeling tasks such as software vulnerability and code clone detection. We present DISCO (DIS-similarity of COde), a novel self-supervised …...

AbstractData augmentation is an effective approach to tackle over-fitting. Many previous works have proposed different data augmentations strategies for NLP, such as noise injection, word replacement, back-translation etc. Though effective, …...

AbstractThis paper presents the approaches and systems of the UA-KO team for the Korean portion of SemEval-2022 Task 11 on Multilingual Complex Named Entity Recognition.We fine-tuned Korean and multilingual BERT …...

AbstractUnsupervised question answering is an attractive task due to its independence on labeled data. Previous works usually make use of heuristic rules as well as pre-trained models to construct data …...

AbstractSarcasm is a term that refers to the use of words to mock, irritate, or amuse someone. It is commonly used on social media. The metaphorical and creative nature of …...

AbstractWe describe the JD Explore Academy’s submission of the WMT 2022 shared general translation task. We participated in all high-resource tracks and one medium-resource track, including Chinese-English, German-English, Czech-English, Russian-English, …...

AbstractDespite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain-specific knowledge. This challenge is magnified in natural language processing, where no general rules exist for data …...

AbstractData Augmentation (DA) is known to improve the generalizability of deep neural networks. Most existing DA techniques naively add a certain number of augmented samples without considering the quality and …...

The grammatical analysis of texts in any written language typically involves a num- ber of basic processing tasks, such as tok- enization, morphological tagging, and de- pendency parsing. State-of-the-art systems …...

AbstractMany natural language processing (NLP) tasks are naturally imbalanced, as some target categories occur much more frequently than others in the real world. In such scenarios, current NLP models tend …...

AbstractThe Explainable Detection of Online Sexism task presents the problem of explainable sexism detection through fine-grained categorisation of sexist cases with three subtasks. Our team experimented with different ways to …...

AbstractNLP has achieved great progress in the past decade through the use of neural models and large labeled datasets. The dependence on abundant data prevents NLP models from being applied …...

AbstractThe objective of this shared task is to gain an understanding of legal texts, and it is beset with difficulties such as the comprehension of lengthy noisy legal documents, domain …...

AbstractWhile pre-trained language models (PLMs) have become a de-facto standard promoting the accuracy of text classification tasks, recent studies find that PLMs often predict over-confidently. Although calibration methods have been …...

AbstractCross-domain aspect-based sentiment analysis (ABSA) aims to perform various fine-grained sentiment analysis tasks on a target domain by transferring knowledge from a source domain. Since labeled data only exists in …...

AbstractThis paper describes the system we submitted to the IWSLT 2023 multilingual speech translation track, with input being English speech and output being text in 10 target languages. Our system …...

AbstractClass imbalance problem can cause machine learning models to produce an undesirable performance on the minority class as well as the whole dataset. Using data augmentation techniques to increase the …...

AbstractIntimacy estimation of a given text has recently gained importance due to the increase in direct interaction of NLP systems with humans. Intimacy is an important aspect of natural language …...

AbstractWe motivate and introduce CHARD: Clinical Health-Aware Reasoning across Dimensions, to investigate the capability of text generation models to act as implicit clinical knowledge bases and generate free-flow textual explanations …...

AbstractIn the article, we present the CodeNLP submission to the SemEval-2023 Task 2: MultiCoNER II Multilingual Complex Named Entity Recognition. Our approach is based on data augmentation by combining various …...

In this research, we utilized the training dataset from the ROCLING 2023 Chinese Multi-genre Named Entity Recognition in the Healthcare Domain, which comprises the Chi- nese HealthNER Corpus (Lee and …...

AbstractState-of-the-art data augmentation methods help improve the generalization of deep learning models. However, these methods often generate examples that contradict the preserving class labels. This is crucial for some natural …...

AbstractIn this research, we studied the relationship between data augmentation and model accuracy for the task of fake review detection. We used data generation methods to augment two different fake …...

AbstractData augmentation is an effective way to enhance the performance of neural machine translation models, especially for low-resource languages. Existing data augmentation methods are either at a token level or …...

AbstractIn our article, we present the systems developed for SemEval-2023 Task 3, which aimed to evaluate the ability of Natural Language Processing (NLP) systems to detect genres and persuasion techniques …...

AbstractWe evaluate the effectiveness of using data augmentation to improve the generalizability of a Named Entity Recognition model for the task of medication identification in clinical notes. We compare disparate …...

AbstractAdvances in natural language processing, such as transfer learning from pre-trained language models, have impacted how models are trained for programming language tasks too. Previous research primarily explored code pre-training …...

AbstractThis paper proposes a novel approach to French patent classification leveraging data-centric strategies. We compare different approaches for the two deepest levels of the IPC hierarchy: the IPC group and …...

AbstractUnsupervised Domain Adaptation (UDA) is a popular technique that aims to reduce the domain shift between two data distributions. It was successfully applied in computer vision and natural language processing. …...

AbstractThis paper describes our participation in SemEval-2023 Task 10, whose goal is the detection of sexism in social media. We explore some of the most popular transformer models such as …...

AbstractThis paper describes the speech translation system submitted as part of the IWSLT 2023 shared task on low resource speech translation. The low resource task aids in building models for …...

AbstractA robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. In this work, we first …...

AbstractNeural machine translation has been shown to outperform all other machine translation paradigms when trained in a high-resource setting. However, it still performs poorly when dealing with low-resource languages, for …...

AbstractAlthough machine translation systems are mostly designed to serve in the general domain, there is a growing tendency to adapt these systems to other domains like literary translation. In this …...

AbstractDetecting harmful content on social media plat-forms is crucial in preventing the negative ef-fects these posts can have on social media users. This paper presents our methodology for tack-ling task …...

AbstractThe most popular approach in grammatical error correction (GEC) is based on sequence-to-sequence (seq2seq) models. Similar to other autoregressive generation tasks, seq2seq GEC also faces the exposure bias problem, i.e., …...

AbstractThis paper presents our system and findings for SemEval 2023 Task 9 Tweet Intimacy Analysis. The main objective of this task was to predict the intimacy of tweets in 10 …...

AbstractOnline social media is rife with offensive and hateful comments, prompting the need for their automatic detection given the sheer amount of posts created every second. Creating high-quality human-labelled datasets …...

AbstractThis paper introduces a data augmentation technique for the task of detecting human values. Our approach involves generating additional examples using metadata that describes the labels in the datasets. We …...

AbstractRecent advances in large pre-trained language models (PLMs) lead to impressive gains on natural language understanding (NLU) tasks with task-specific fine-tuning. However, directly fine-tuning PLMs heavily relies on sufficient labeled …...

AbstractThe web contains an abundance of user- generated content. While this content is useful for many applications, it poses many challenges due to the presence of offensive, biased, and overall …...

AbstractUnsupervised sentence representation learning has progressed through contrastive learning and data augmentation methods such as dropout masking. Despite this progress, sentence encoders are still limited to using only an input …...

AbstractFor many real-world applications, the user-generated inputs usually contain various noises due to speech recognition errors caused by linguistic variations or typographical errors (typos). Thus, it is crucial to test …...

AbstractPrior studies in privacy policies frame the question answering (QA) task as identifying the most relevant text segment or a list of sentences from a policy document given a user …...

AbstractThis paper presents the system developed by the Sartipi-Sedighin team for SemEval 2023 Task 2, which is a shared task focused on multilingual complex named entity recognition (NER), or MultiCoNER …...

AbstractDue to the semantic complexity of the Relation extraction (RE) task, obtaining high-quality human labelled data is an expensive and noisy process. To improve the sample efficiency of the models, …...

AbstractIn this paper, we discuss the methods we applied at SemEval-2023 Task 10: Towards the Explainable Detection of Online Sexism. Given an input text, we perform three classification tasks to …...

AbstractWhile quality estimation (QE) can play an important role in the translation process, its effectiveness relies on the availability and quality of training data. For QE in particular, high-quality labeled …...

AbstractDocument-level machine translation faces the challenge of data sparsity due to its long input length and a small amount of training data, increasing the risk of learning spurious patterns. To …...

AbstractProgress in document-level Machine Translation is hindered by the lack of parallel training data that include context information. In this work, we evaluate the potential of data augmentation techniques to …...

AbstractRecent advances in open-domain question answering (ODQA) have demonstrated impressive accuracy on general-purpose domains like Wikipedia. While some work has been investigating how well ODQA models perform when tested for …...

AbstractThis work presents the participation of the UMUTeam and the SINAI research groups in the SemEval-2023 Task 9: Multilingual Tweet Intimacy Analysis. The goal of this task is to predict …...

AbstractWe present our submission to SemEval-2023 Task 10: Explainable Detection of Online Sexism (EDOS). We address all three tasks: Task A consists of identifying whether a post is sexist. If …...

AbstractIntimacy is an essential element of human relationships and language is a crucial means of conveying it. Textual intimacy analysis can reveal social norms in different contexts and serve as …...