Вопросы и ответы

This paper describes the development of QuestionBank, a corpus of 4000 parse- annotated questions for (i) use in training parsers employed in QA, and (ii) evalua- tion of question parsing. …...

Research in Question Answering (QA) has been dominated by the TREC methodology of black-box system evaluation. This makes it difficult to evaluate the effectiveness of in- dividual components and requires …...

A major focus of current work in distri- butional models of semantics is to con- struct phrase representations composition- ally from word representations. However, the syntactic contexts which are modelled …...

Cognitive science researchers have em- phasized the importance of ordering a complex task into a sequence of easy to hard problems. Such an ordering provides an easier path to learning …...

AbstractWe demonstrate the surprising strength of unimodal baselines in multimodal domains, and make concrete recommendations for best practices in future research. Where existing work often compares against random or majority …...

AbstractWe present a novel way of injecting factual knowledge about entities into the pretrained BERT model (Devlin et al., 2019): We align Wikipedia2Vec entity vectors (Yamada et al., 2016) with …...

AbstractMassively multilingual transformers (MMTs) pretrained via language modeling (e.g., mBERT, XLM-R) have become a default paradigm for zero-shot language transfer in NLP, offering unmatched transfer performance. Current evaluations, however, verify …...

AbstractGradient-based analysis methods, such as saliency map visualizations and adversarial input perturbations, have found widespread use in interpreting neural NLP models due to their simplicity, flexibility, and most importantly, the …...

AbstractMany natural language questions require qualitative, quantitative or logical comparisons between two entities or events. This paper addresses the problem of improving the accuracy and consistency of responses to comparison …...

AbstractRecent work by Clark et al. (2020) shows that transformers can act as “soft theorem provers” by answering questions over explicitly provided knowledge in natural language. In our work, we …...

AbstractThere has been significant progress in recent years in the field of Natural Language Processing thanks to the introduction of the Transformer architecture. Current state-of-the-art models, via a large number …...

AbstractEvidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the QA method. We introduce a simple, …...

AbstractLearning what to share between tasks has become a topic of great importance, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important …...

AbstractGeneral pre-trained language models (PLMs), such as BERT, have achieved remarkable performance on various NLP tasks. Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains …...

AbstractTables are often created with hierarchies, but existing works on table reasoning mainly focus on flat tables and neglect hierarchical tables. Hierarchical tables challenge numerical reasoning by complex hierarchical indexing, …...

AbstractThe zero-shot cross-lingual ability of models pretrained on multilingual and even monolingual corpora has spurred many hypotheses to explain this intriguing empirical result. However, due to the costs of pretraining, …...

AbstractFrom pretrained contextual embedding to document-level embedding, the selection and construction of embedding have drawn more and more attention in the NER domain in recent research. This paper aims to …...

AbstractMany text generation applications require the generated text to be factually consistent with input information. Automatic evaluation of factual consistency is challenging. Previous work has developed various metrics that often …...

AbstractPrompt tuning is an efficient method for adapting large language models, and Soft Prompt Transfer (SPoT) further narrows the gap between prompt tuning and full model tuning by transferring prompts …...

AbstractLarge pre-trained language models such as BERT have been widely used as a framework for natural language understanding (NLU) tasks. However, recent findings have revealed that pre-trained language models are …...

AbstractA crucial issue of current text generation models is that they often uncontrollably generate text that is factually inconsistent with inputs. Due to lack of annotated data, existing factual consistency …...