Қарсыласу оқыту

AbstractTwo types of data shift common in practice are 1. transferring from synthetic data to live user data (a deployment shift), and 2. transferring from stale data to current data …...

AbstractWe apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning problem …...

AbstractAdversarial training is a mean of regularizing classification algorithms by generating adversarial noise to the training data. We apply adversarial training in relation extraction within the multi-instance multi-label learning framework. …...

AbstractWe address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input …...

AbstractDomain Adaptation arises when we aim at learning from source domain a model that can perform acceptably well on a different target domain. It is especially crucial for Natural Language …...

AbstractWe present two categories of model-agnostic adversarial strategies that reveal the weaknesses of several generative, task-oriented dialogue models: Should-Not-Change strategies that evaluate over-sensitivity to small and semantics-preserving edits, as well …...

AbstractAdversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their …...

AbstractStory generation is a challenging problem in artificial intelligence (AI) and has received a lot of interests in the natural language processing (NLP) community. Most previous work tried to solve …...

AbstractThe use of machine learning for NLP generally requires resources for training. Tasks performed in a low-resource language usually rely on labeled data in another, typically resource-rich, language. However, there …...

AbstractRelation classification is an important task in natural language processing fields. State-of-the-art methods usually concentrate on building deep neural networks based classification models on the training data in which the …...

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 …...

AbstractWe address the problem of speech act recognition (SAR) in asynchronous conversations (forums, emails). Unlike synchronous conversations (e.g., meetings, phone), asynchronous domains lack large labeled datasets to train an effective …...

AbstractIn this paper, we propose a neural network-based approach, namely Adversarial Attention Network, to the task of multi-dimensional emotion regression, which automatically rates multiple emotion dimension scores for an input …...

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 …...

AbstractThe automatic detection of satire vs. regular news is relevant for downstream applications (for instance, knowledge base population) and to improve the understanding of linguistic characteristics of satire. Recent approaches …...

AbstractGenerating high-quality paraphrases is a fundamental yet challenging natural language processing task. Despite the effectiveness of previous work based on generative models, there remain problems with exposure bias in recurrent …...

AbstractGenerating intriguing question is a key step towards building human-like open-domain chatbots. Although some recent works have focused on this task, compared with questions raised by humans, significant gaps remain …...

AbstractMulti-hop question answering requires a model to connect multiple pieces of evidence scattered in a long context to answer the question. In this paper, we show that in the multi-hop …...

AbstractTo combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier. Our word recognition models build upon the RNN semi-character architecture, introducing several …...

AbstractCross-lingual transfer learning has become an important weapon to battle the unavailability of annotated resources for low-resource languages. One of the fundamental techniques to transfer across languages is learning language-agnostic …...

AbstractAutomatic topic-to-essay generation is a challenging task since it requires generating novel, diverse, and topic-consistent paragraph-level text with a set of topics as input. Previous work tends to perform essay …...

AbstractRecent research has demonstrated that goal-oriented dialogue agents trained on large datasets can achieve striking performance when interacting with human users. In real world applications, however, it is important to …...

AbstractIn online discussion fora, speakers often make arguments for or against something, say birth control, by highlighting certain aspects of the topic. In social science, this is referred to as …...

AbstractLanguage use varies across different demographic factors, such as gender, age, and geographic location. However, most existing document classification methods ignore demographic variability. In this study, we examine empirically how …...

AbstractAdversarial examples — perturbations to the input of a model that elicit large changes in the output — have been shown to be an effective way of assessing the robustness …...

AbstractAdversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for …...

AbstractTransfer learning is effective for improving the performance of tasks that are related, and Multi-task learning (MTL) and Cross-lingual learning (CLL) are important instances. This paper argues that hard-parameter sharing, …...

AbstractVisual modifications to text are often used to obfuscate offensive comments in social media (e.g., “!d10t”) or as a writing style (“1337” in “leet speak”), among other scenarios. We consider …...

AbstractDespite impressive performance on many text classification tasks, deep neural networks tend to learn frequent superficial patterns that are specific to the training data and do not always generalize well. …...

AbstractCross-domain sentiment classification aims to address the lack of massive amounts of labeled data. It demands to predict sentiment polarity on a target domain utilizing a classifier learned from a …...

AbstractReading comprehension models often overfit to nuances of training datasets and fail at adversarial evaluation. Training with adversarially augmented dataset improves robustness against those adversarial attacks but hurts generalization of …...

AbstractNatural Language Inference (NLI) datasets contain annotation artefacts resulting in spurious correlations between the natural language utterances and their respective entailment classes. These artefacts are exploited by neural networks even …...

AbstractNLP models are shown to suffer from robustness issues, i.e., a model’s prediction can be easily changed under small perturbations to the input. In this work, we present a Controlled …...

AbstractDespite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the …...

AbstractAutomatic content scoring systems are widely used on short answer tasks to save human effort. However, the use of these systems can invite cheating strategies, such as students writing irrelevant …...

AbstractAdversarial training (AT) has shown strong regularization effects on deep learning algorithms by introducing small input perturbations to improve model robustness. In language tasks, adversarial training brings word-level robustness by …...

AbstractCorporate mergers and acquisitions (M&A) account for billions of dollars of investment globally every year and offer an interesting and challenging domain for artificial intelligence. However, in these highly sensitive …...

AbstractWe present our HABERTOR model for detecting hatespeech in large scale user-generated content. Inspired by the recent success of the BERT model, we propose several modifications to BERT to enhance …...

AbstractA sequence-to-sequence (seq2seq) learning with neural networks empirically shows to be an effective framework for grammatical error correction (GEC), which takes a sentence with errors as input and outputs the …...

AbstractCode switching is a linguistic phenomenon which may occur within a multilingual setting where speakers share more than one language. With the increasing communication between groups with different languages, this …...

AbstractSentiment analysis is a widely researched NLP problem with state-of-the-art solutions capable of attaining human-like accuracies for various languages. However, these methods rely heavily on large amounts of labeled data …...

AbstractIn this paper, we present a multi-level alignment pretraining method in a unified architecture formulti-lingual semantic parsing. In this architecture, we use an adversarial training method toalign the space of …...

AbstractUnsupervised neural machine translation (UNMT) has recently attracted great interest in the machine translation community. The main advantage of the UNMT lies in its easy collection of required large training …...

AbstractAspect-based sentiment analysis (ABSA) aims to predict the sentiment towards a specific aspect in the text. However, existing ABSA test sets cannot be used to probe whether a model can …...

Previous work on adversarial attacks on depen- dency parsers has mostly focused on attack methods, as opposed to the quality of adver- sarial examples, which in previous work has been …...

AbstractThe flexibility of the inference process in Variational Autoencoders (VAEs) has recently led to revising traditional probabilistic topic models giving rise to Neural Topic Models (NTM). Although these approaches have …...

AbstractAdversarial training (AT) as a regularization method has proved its effectiveness on various tasks. Though there are successful applications of AT on some NLP tasks, the distinguishing characteristics of NLP …...

AbstractRepresentations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a range of downstream tasks. In this paper we …...

AbstractThis paper introduces the result of Team Grenzlinie’s experiment in SemEval-2021 task 7: HaHackathon: Detecting and Rating Humor and Offense. This task has two subtasks. Subtask1 includes the humor detection …...

AbstractThis paper introduces our system at SemEval-2021 Task 5: Toxic Spans Detection. The task aims to accurately locate toxic spans within a text. Using BIO tagging scheme, we model the …...

Recent work has proposed several efficient ap- proaches for generating gradient-based adver- sarial perturbations on embeddings and proved that the model’s performance and robustness can be improved when they are …...

AbstractThis paper describes the winning system in the End-to-end Pipeline phase for the NLPContributionGraph task. The system is composed of three BERT-based models and the three models are used to …...

AbstractDistantly supervised relation extraction (RE) automatically aligns unstructured text with relation instances in a knowledge base (KB). Due to the incompleteness of current KBs, sentences implying certain relations may be …...

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 …...

AbstractFor task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for …...

AbstractRecently, there has been significant progress in studying neural networks to translate text descriptions into SQL queries. Despite achieving good performance on some public benchmarks, existing text-to-SQL models typically rely …...

AbstractWe propose a method to distill language-agnostic meaning embeddings from multilingual sentence encoders for unsupervised quality estimation of machine translation. Our method facilitates that the meaning embeddings focus on semantics …...

AbstractWe propose an enhanced adversarial training algorithm for fine-tuning transformer-based language models (i.e., RoBERTa) and apply it to the temporal reasoning task. Current adversarial training approaches for NLP add the …...

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 …...

AbstractThis study uses training and validation data from the “ROCLING 2022 Chinese Health Care Named Entity Recognition Task” for modeling. The modeling process adopts technologies such as data augmentation and …...

AbstractThis work demonstrates that Legal Judgement Prediction systems without expert-informed adjustments can be vulnerable to shallow, distracting surface signals that arise from corpus construction, case distribution, and confounding factors. To …...

AbstractAdversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs). However, this approach is typically more expensive than traditional fine-tuning because of …...

AbstractAdversarial robustness has attracted much attention recently, and the mainstream solution is adversarial training. However, the tradition of generating adversarial perturbations for each input embedding (in the settings of NLP) …...

AbstractRecent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness. However, we observe that a too large number of search …...

AbstractRecent work in black-box adversarial attacks for NLP systems has attracted attention. Prior black-box attacks assume that attackers can observe output labels from target models based on selected inputs. 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 …...

AbstractDespite the remarkable success deep models have achieved in Textual Matching (TM) tasks, it still remains unclear whether they truly understand language or measure the semantic similarity of texts by …...

AbstractNeural networks are vulnerable to adversarial examples. The adversary can successfully attack a model even without knowing model architecture and parameters, i.e., under a black-box scenario. Previous works on word-level …...

AbstractAdversarial training, which minimizes the loss of adversarially perturbed examples, has received considerable attention. However, these methods require modifying all model parameters and optimizing the model from scratch, which is …...

AbstractStyle control, content preservation, and fluency determine the quality of text style transfer models. To train on a nonparallel corpus, several existing approaches aim to deceive the style discriminator with …...

AbstractRecently, more and more pre-trained language models are released as a cloud service. It allows users who lack computing resources to perform inference with a powerful model by uploading data …...

AbstractRecent research in cross-lingual learning has found that combining large-scale pretrained multilingual language models with machine translation can yield good performance. We explore this idea for cross-lingual event extraction with …...

AbstractAlong with the successful deployment of deep neural networks in several application domains, the need to unravel the black-box nature of these networks has seen a significant increase recently. Several …...

AbstractThis paper presents our proposed method for SemEval-2023 Task 12, which focuses on sentiment analysis for low-resource African languages. Our method utilizes a language-centric domain adaptation approach which is based …...

AbstractText-guided image inpainting (TGII) aims to restore missing regions based on a given text in a damaged image. Existing methods are based on a strong vision encoder and a cross-modal …...

AbstractThis paper describes SemEval-2022’s shared task “Explainable Detection of Online Sexism”. The fine-grained classification of sexist content plays a major role in building explainable frameworks for online sexism detection. We …...