Gated Self-Matching Networks for Reading Comprehension and Question Answering

Wang, Wenhui; Yang, Nan; Wei, Furu; Chang, Baobao; Zhou, Ming

doi:10.18653/v1/p17-1018

Cited by 604 publications

(417 citation statements)

References 19 publications

Supporting

Mentioning

417

Contrasting

Order By: Relevance

“…In recent years, researchers have published a large number of annotated MRC datasets such as CNN/Daily Mail (Hermann et al, 2015), SQuAD (Rajpurkar et al, 2016), RACE (Lai et al, 2017), Trivi-aQA (Joshi et al, 2017) and so on. With the blooming of available large-scale MRC datasets, a great number of neural network-based MRC models have been proposed to answer questions for a given document including Attentive Reader (Kadlec et al, 2016), BiDAF (Seo et al, 2017), Interactive AoA Reader (Cui et al, 2017), Gated Attention Reader (Dhingra et al, 2017), R-Net (Wang et al, 2017a), DCN (Xiong et al, 2017), QANet (Yu et al, 2018), and achieve promising results in most existing public MRC datasets.…”

Section: Machine Reading Comprehensionmentioning

confidence: 99%

NumNet: Machine Reading Comprehension with Numerical Reasoning

Ran¹,

Lin²,

Li³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Numerical reasoning, such as addition, subtraction, sorting and counting is a critical skill in human's reading comprehension, which has not been well considered in existing machine reading comprehension (MRC) systems. To address this issue, we propose a numerical MRC model named as NumNet, which utilizes a numerically-aware graph neural network to consider the comparing information and performs numerical reasoning over numbers in the question and passage. Our system achieves an EM-score of 64.56% on the DROP dataset, outperforming all existing machine reading comprehension models by considering the numerical relations among numbers.

show abstract

Section: Machine Reading Comprehensionmentioning

confidence: 99%

NumNet: Machine Reading Comprehension with Numerical Reasoning

Ran¹,

Lin²,

Li³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

“…In reading comprehension literature, self-attention has been investigated. (Wang et al, 2017b) proposed a Gated Self-Matching mechanism which produced context-enhanced token encodings in a document. In this paper, we have a different angle for applying self-attention.…”

Section: Related Workmentioning

confidence: 99%

Read and Comprehend by Gated-Attention Reader with More Belief

Deng¹,

Tam

2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: St

View full text Add to dashboard Cite

Gated-Attention (GA) Reader has been effective for reading comprehension. GA Reader makes two assumptions: (1) a uni-directional attention that uses an input query to gate token encodings of a document; (2) encoding at the cloze position of an input query is considered for answer prediction. In this paper, we propose Collaborative Gating (CG) and Self-Belief Aggregation (SBA) to address the above assumptions respectively. In CG, we first use an input document to gate token encodings of an input query so that the influence of irrelevant query tokens may be reduced. Then the filtered query is used to gate token encodings of an document in a collaborative fashion. In SBA, we conjecture that query tokens other than the cloze token may be informative for answer prediction. We apply self-attention to link the cloze token with other tokens in a query so that the importance of query tokens with respect to the cloze position are weighted. Then their evidences are weighted, propagated and aggregated for better reading comprehension. Experiments show that our approaches advance the state-of-theart results in CNN, Daily Mail, and Who Did What public test sets.

show abstract

“…Several methods have been proposed to apply deep neural networks for effective information retrieval [12,17,30] and question answering [42,47], also with focus on healthcare [25,52]. However, our CDSS scenario poses a unique combination of open challenges to a retrieval system:…”

Section: Introductionmentioning

confidence: 99%

Learning Contextualized Document Representations for Healthcare Answer Retrieval

Arnold

Aken

Grundmann

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

We present Contextual Discourse Vectors (CDV), a distributed document representation for efficient answer retrieval from long healthcare documents. Our approach is based on structured query tuples of entities and aspects from free text and medical taxonomies. Our model leverages a dual encoder architecture with hierarchical LSTM layers and multi-task training to encode the position of clinical entities and aspects alongside the document discourse. We use our continuous representations to resolve queries with short latency using approximate nearest neighbor search on sentence level. We apply the CDV model for retrieving coherent answer passages from nine English public health resources from the Web, addressing both patients and medical professionals. Because there is no end-to-end training data available for all application scenarios, we train our model with self-supervised data from Wikipedia. We show that our generalized model significantly outperforms several state-of-theart baselines for healthcare passage ranking and is able to adapt to heterogeneous domains without additional fine-tuning.

show abstract

Gated Self-Matching Networks for Reading Comprehension and Question Answering

Cited by 604 publications

References 19 publications

NumNet: Machine Reading Comprehension with Numerical Reasoning

NumNet: Machine Reading Comprehension with Numerical Reasoning

Read and Comprehend by Gated-Attention Reader with More Belief

Learning Contextualized Document Representations for Healthcare Answer Retrieval

Contact Info

Product

Resources

About