Simple and Effective Multi-Paragraph Reading Comprehension

Clark, Christopher; Gardner, Matt

doi:10.18653/v1/p18-1078

Cited by 345 publications

(371 citation statements)

References 30 publications

Supporting

Mentioning

359

Contrasting

Order By: Relevance

“…Previous work has dealt with this setting by detecting spans in the document through text matching (Joshi et al, 2017;Clark and Gardner, 2018). Following previous approaches, we define a solution z as a span in the document.…”

Section: Multi-mention Reading Comprehensionmentioning

confidence: 99%

See 1 more Smart Citation

A Discrete Hard EM Approach for Weakly Supervised Question Answering

Min¹,

Chen²,

Hajishirzi³

et al. 2019

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

130

150

View full text Add to dashboard Cite

Many question answering (QA) tasks only provide weak supervision for how the answer should be computed. For example, TRIVIAQA answers are entities that can be mentioned multiple times in supporting documents, while DROP answers can be computed by deriving many different equations from numbers in the reference text. In this paper, we show it is possible to convert such tasks into discrete latent variable learning problems with a precomputed, task-specific set of possible solutions (e.g. different mentions or equations) that contains one correct option. We then develop a hard EM learning scheme that computes gradients relative to the most likely solution at each update. Despite its simplicity, we show that this approach significantly outperforms previous methods on six QA tasks, including absolute gains of 2-10%, and achieves the stateof-the-art on five of them. Using hard updates instead of maximizing marginal likelihood is key to these results as it encourages the model to find the one correct answer, which we show through detailed qualitative analysis. 1is used to compute the objective as follows:However, there are two major problems in the MML objective in our settings. First, MML can be

show abstract

Section: Multi-mention Reading Comprehensionmentioning

confidence: 99%

“…by selecting the first answer span in TRIVIAQA (Joshi et al, 2017;Tay et al, 2018;Talmor and Berant, 2019)). Some models are trained with maximum marginal likelihood (MML) (Kadlec et al, 2016;Swayamdipta et al, 2018;Clark and Gardner, 2018;, but it is unclear if it gives a meaningful improvement over the heuristics.…”

Section: Introductionmentioning

confidence: 99%

A Discrete Hard EM Approach for Weakly Supervised Question Answering

Min¹,

Chen²,

Hajishirzi³

et al. 2019

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

130

150

View full text Add to dashboard Cite

show abstract

“…Machine Reading at Scale First proposed and formalized in Chen et al (2017), MRS has gained popularity with increasing amount of work on both dataset collection (Joshi et al, 2017; and MRS model developments (Wang et al, 2018;Clark and Gardner, 2017;Htut et al, 2018). In some previous work , paragraph-level retrieval modules were mainly for improving the recall of required information, while in some other works (Yang et al, 2018), sentence-level retrieval modules were merely for solving the auxiliary sentence selection task.…”

Section: Related Workmentioning

confidence: 99%

Revealing the Importance of Semantic Retrieval for Machine Reading at Scale

Nie¹,

Wang²,

Bansal³

2019

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

116

103

View full text Add to dashboard Cite

Machine Reading at Scale (MRS) is a challenging task in which a system is given an input query and is asked to produce a precise output by "reading" information from a large knowledge base. The task has gained popularity with its natural combination of information retrieval (IR) and machine comprehension (MC). Advancements in representation learning have led to separated progress in both IR and MC; however, very few studies have examined the relationship and combined design of retrieval and comprehension at different levels of granularity, for development of MRS systems. In this work, we give general guidelines on system design for MRS by proposing a simple yet effective pipeline system with special consideration on hierarchical semantic retrieval at both paragraph and sentence level, and their potential effects on the downstream task. The system is evaluated on both fact verification and open-domain multihop QA, achieving state-of-the-art results on the leaderboard test sets of both FEVER and HOTPOTQA. To further demonstrate the importance of semantic retrieval, we present ablation and analysis studies to quantify the contribution of neural retrieval modules at both paragraph-level and sentence-level, and illustrate that intermediate semantic retrieval modules are vital for not only effectively filtering upstream information and thus saving downstream computation, but also for shaping upstream data distribution and providing better data for downstream modeling. 1

show abstract

“…Work in that direction includes (Watanabe et al, 2017) which present a neural information retrieval system to retrieve a sufficiently small paragraph and (Geva and Berant, 2018) which employ a Deep Q-Network (DQN) to solve the task by learning to navigate over an intra-document tree. A similar approach is chosen by (Clark and Gardner, 2017). However, instead of operating on document structure, they adopt a sampling technique to make the model more robust towards multi-paragraph documents.…”

Section: Related Workmentioning

confidence: 99%

Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks

Thayaparan¹,

Valentino²,

Schlegel³

et al. 2019

Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)

View full text Add to dashboard Cite

Recent advances in reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text. However, complex Question Answering (QA) typically requires multi-hop reasoning -i.e. the integration of supporting facts from different sources, to infer the correct answer.This paper proposes Document Graph Network (DGN), a message passing architecture for the identification of supporting facts over a graph-structured representation of text.The evaluation on HotpotQA shows that DGN obtains competitive results when compared to a reading comprehension baseline operating on raw text, confirming the relevance of structured representations for supporting multi-hop reasoning.

show abstract

Simple and Effective Multi-Paragraph Reading Comprehension

Cited by 345 publications

References 30 publications

A Discrete Hard EM Approach for Weakly Supervised Question Answering

A Discrete Hard EM Approach for Weakly Supervised Question Answering

Revealing the Importance of Semantic Retrieval for Machine Reading at Scale

Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks

Contact Info

Product

Resources

About