Устойчивость

This paper describes Picky, a probabilistic agenda-based chart parsing algorithm which uses a technique called p~'ob- abilistic prediction to predict which grammar rules are likely to lead to an acceptable …...

JANUS is a multi-lingual speech-to- speech translation system designed to facilitate communication between two parties engaged in a spontaneous con- versation in a limited domain. In an attempt to achieve …...

Word sense induction and discrimination (WSID) identifies the senses of an am- biguous word and assigns instances of this word to one of these senses. We have build a WSID …...

We use the NLP toolchain that is used to con- struct the Groningen Meaning Bank to address the task of detecting negation cue and scope, as defined in the shared …...

Argumentation mining is considered as a key technology for future search engines and au- tomated decision making. In such applica- tions, argumentative text segments have to be mined from large …...

AbstractThis paper presents the results of systematic experimentation on the impact in duplicate question detection of different types of questions across both a number of established approaches and a novel, …...

AbstractWe propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to …...

This paper investigates the robustness of NLP against perturbed word forms. While neural approaches can achieve (almost) human-like accuracy for certain tasks and conditions, they often are sensitive to small …...

AbstractTo bridge the gap between Machine Reading Comprehension (MRC) models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, in this paper, …...

AbstractWe address the problem of adversarial attacks on text classification, which is rarely studied comparing to attacks on image classification. The challenge of this task is to generate adversarial examples …...

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 …...

AbstractIn this paper, we focus on quantifying model stability as a function of random seed by investigating the effects of the induced randomness on model performance and the robustness of …...

AbstractComprehending multi-turn spoken conversations is an emerging research area, presenting challenges different from reading comprehension of passages due to the interactive nature of information exchange from at least two speakers. …...

AbstractJoint intent detection and slot filling has recently achieved tremendous success in advancing the performance of utterance understanding. However, many joint models still suffer from the robustness problem, especially on …...

AbstractSeveral recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail …...

AbstractTo assess the robustness of NER systems, we propose an evaluation method that focuses on subsets of tokens that represent specific sources of errors: unknown words and label shift or …...

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 …...

AbstractNLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task. Recently proposed debiasing methods are shown to be effective in mitigating this tendency. However, …...

AbstractDiscrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to a prediction error. While such attacks have been extensively explored for the …...

AbstractRobustness and counterfactual bias are usually evaluated on a test dataset. However, are these evaluations robust? If the test dataset is perturbed slightly, will the evaluation results keep the same? …...

AbstractHigh-performance neural language models have obtained state-of-the-art results on a wide range of Natural Language Processing (NLP) tasks. However, results for common benchmark datasets often do not reflect model reliability …...

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 …...

AbstractBuilding robust multimodal models are crucial for achieving reliable deployment in the wild. Despite its importance, less attention has been paid to identifying and improving the robustness of Multimodal Sentiment …...

AbstractDespite their progress in high-resource language settings, unsupervised bilingual lexicon induction (UBLI) models often fail on corpora with low-resource distant language pairs due to insufficient initialization. In this work, we …...

AbstractGenerating adversarial examples for Neural Machine Translation (NMT) with single Round-Trip Translation (RTT) has achieved promising results by releasing the meaning-preserving restriction. However, a potential pitfall for this approach is …...

AbstractPre-trained language models (LMs) struggle with consistent reasoning; recently, prompting LMs to generate explanations that self-guide the inference has emerged as a promising direction to amend this. However, these approaches …...

AbstractAs NLP models achieved state-of-the-art performances over benchmarks and gained wide applications, it has been increasingly important to ensure the safe deployment of these models in the real world, e.g., …...

AbstractThe quality of Natural Language Processing (NLP) models is typically measured by the accuracy or error rate of a predefined test set. Because the evaluation and optimization of these measures …...

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 …...

AbstractExisting Math Word Problem (MWP) solvers have achieved high accuracy on benchmark datasets. However, prior works have shown that such solvers do not generalize well and rely on superficial cues …...

AbstractFew-shot Text Classification predicts the semantic label of a given text with a handful of supporting instances. Current meta-learning methods have achieved satisfying results in various few-shot situations. Still, they …...

AbstractDeep neural models have become the mainstream in answer selection, yielding state-of-the-art performance. However, these models tend to rely on spurious correlations between prediction labels and input features, which in …...

AbstractDeep NLP models have been shown to be brittle to input perturbations. Recent work has shown that data augmentation using counterfactuals — i.e. minimally perturbed inputs — can help ameliorate …...

Abstract“With the development of deep learning in recent years, text classification research has achieved remarkable results. However, text classification task often requires a large amount of annotated data, and data …...

AbstractTransfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers …...

Abstract“Recent advances in the field of abstractive summarization leverage pre-trained language models rather than train a model from scratch. However, such models are sluggish to train and accompanied by a …...

AbstractGenerative Spoken Language Modeling research focuses on optimizing speech Language Models (LMs) using raw audio recordings without accessing any textual supervision. Such speech LMs usually operate over discrete units obtained …...

AbstractWe tackle the task of automatically discriminating between human and machine translations. As opposed to most previous work, we perform experiments in a multilingual setting, considering multiple languages and multilingual …...

AbstractDocument-level relation extraction (DocRE) attracts more research interest recently. While models achieve consistent performance gains in DocRE, their underlying decision rules are still understudied: Do they make the right predictions …...

AbstractDiscrete prompts have been used for fine-tuning Pre-trained Language Models for diverse NLP tasks. In particular, automatic methods that generate discrete prompts from a small set of training instances have …...

AbstractDespite the strong performance of current NLP models, they can be brittle against adversarial attacks. To enable effective learning against adversarial inputs, we introduce the use of rationale models that …...

AbstractAdversarial attacks on deep neural networks keep raising security concerns in natural language processing research. Existing defenses focus on improving the robustness of the victim model in the training stage. …...

AbstractRecent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models. However, these contents are …...