Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

Godbole, Ameya; Kavarthapu, Dilip; Das, Raj; Gong, Zhiyu; Singhal, Abhishek; Zamani, Hamed; Yu, Mei; Gao, Tian; Guo, Xinwen; Zaheer, Manzil; McCallum, Andrew

doi:10.48550/arxiv.1909.07598

Cited by 4 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baselines We compare HGN with both published and unpublished work in both settings. For the Model Ans Sup Joint EM F1 EM F1 EM F1 TPReasoner (Xiong et al, 2019) 36.04 47.43 ----Baseline Model 23.95 32.89 3.86 37.71 1.85 16.15 QFE (Nishida et al, 2019) 28.66 38.06 14.20 44.35 8.69 23.10 MUPPET (Feldman and El-Yaniv, 2019) 30.61 40.26 16.65 47.33 10.85 27.01 Cognitive Graph (Ding et al, 2019) 37.12 48.87 22.82 57.69 12.42 34.92 PR-BERT † 43.33 53.79 21.90 59.63 14.50 39.11 Golden Retriever (Qi et al, 2019) 37.92 48.58 30.69 64.24 18.04 39.13 Entity-centric BERT (Godbole et al, 2019) 41 Distractor setting, we compare with DFGN (Xiao et al, 2019), QFE (Nishida et al, 2019), the official baseline , and DecompRC (Min et al, 2019b). Unpublished work includes TAP2, EPS+BERT, SAE, P-BERT, LQR-net (Anonymous, 2020a), and ChainEx .…”

Section: Methodsmentioning

confidence: 99%

“…For the Fullwiki setting, the published baselines include SemanticRetrievalMRS (Yixin Nie, 2019), Entity-centric BERT (Godbole et al, 2019), GoldEn Retriever (Qi et al, 2019), Cognitive Graph (Ding et al, 2019), MUPPET (Feldman and El-Yaniv, 2019), QFE (Nishida et al, 2019), and the official baseline . Unpublished work includes Graph-based Recurrent Retriever (Anonymous, 2020b), MIR+EPS+BERT, Transformer-XH (Anonymous, 2020c), PR-BERT, and TPReasoner (Xiong et al, 2019).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Hierarchical Graph Network for Multi-hop Question Answering

Fang¹,

Sun²,

Gan³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

114

120

View full text Add to dashboard Cite

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical graph is created by constructing nodes on different levels of granularity (questions, paragraphs, sentences, entities), the representations of which are initialized with pre-trained contextual encoders. Given this hierarchical graph, the initial node representations are updated through graph propagation, and multihop reasoning is performed via traversing through the graph edges for each subsequent sub-task (e.g., paragraph selection, supporting facts extraction, answer prediction). By weaving heterogeneous nodes into an integral unified graph, this hierarchical differentiation of node granularity enables HGN to support different question answering sub-tasks simultaneously. Experiments on the HotpotQA benchmark demonstrate that the proposed model achieves new state of the art, outperforming existing multi-hop QA approaches. 1

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Hierarchical Graph Network for Multi-hop Question Answering

Fang¹,

Sun²,

Gan³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

114

120

View full text Add to dashboard Cite

show abstract

“…The original task requires to find evidence passages from abstract paragraphs of all Wikipedia pages to support a multi-hop question. For each q, we collect 50 relevant passages based on bigram BM25 (Godbole et al, 2019). Two positive evidence passages to each question are provided by human annotators as the ground truth.…”

Section: Settingsmentioning

confidence: 99%

Complementary Evidence Identification in Open-Domain Question Answering

Mou

Chang

et al. 2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Self Cite

View full text Add to dashboard Cite

This paper proposes a new problem of complementary evidence identification for opendomain question answering (QA). The problem aims to efficiently find a small set of passages that covers full evidence from multiple aspects as to answer a complex question. To this end, we proposes a method that learns vector representations of passages and models the sufficiency and diversity within the selected set, in addition to the relevance between the question and passages. Our experiments demonstrate that our method considers the dependence within the supporting evidence and significantly improves the accuracy of complementary evidence selection in QA domain.

show abstract

“…Lin et al [18] constructed a schema graph between QA-concept pairs for commonsense reasoning. In order to retrieve reasoning paths over Wikipedia, Godbole et al [13] used entity linking for multi-hop retrieval. Asai et al [1] utilized the wikipedia hyperlinks to construct the Wikipedia graph which helps to identify the reasoning path.…”

Section: Knowledge In Retrieval-based Qa Modelsmentioning

confidence: 99%

Knowledge-Aided Open-Domain Question Answering

Zhou,

Shi,

Huang

et al. 2020

Preprint

View full text Add to dashboard Cite

Open-domain question answering (QA) aims to find the answer to a question from a large collection of documents. Though many models for single-document machine comprehension have achieved strong performance, there is still much room for improving opendomain QA systems since document retrieval and answer reranking are still unsatisfactory. Golden documents that contain the correct answers may not be correctly scored by the retrieval component, and the correct answers that have been extracted may be wrongly ranked after other candidate answers by the reranking component. One of the reasons is derived from the independent principle in which each candidate document (or answer) is scored independently without considering its relationship to other documents (or answers) [28].In this work, we propose a knowledge-aided open-domain QA (KAQA) method which targets at improving relevant document retrieval and candidate answer reranking by considering the relationship between a question and the documents (termed as questiondocument graph), and the relationship between candidate documents (termed as document-document graph). The graphs are built using knowledge triples from external knowledge resources. During document retrieval, a candidate document is scored by considering its relationship to the question and other documents. During answer reranking, a candidate answer is reranked using not only its own context but also the clues from other documents. The experimental results show that our proposed method improves document retrieval and answer reranking, and thereby enhances the overall performance of open-domain question answering.

show abstract

Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering

Cited by 4 publications

References 13 publications

Hierarchical Graph Network for Multi-hop Question Answering

Hierarchical Graph Network for Multi-hop Question Answering

Complementary Evidence Identification in Open-Domain Question Answering

Knowledge-Aided Open-Domain Question Answering

Contact Info

Product

Resources

About