paper-with-me

Papers

UnitedQA: A Hybrid Approach for Open Domain Question Answering

2021-01-01 · ACL 2021 5 · Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao

To date, most of recent work under the retrieval-reader framework for open-domain QA focuses on either extractive or generative reader exclusively. In this paper, we study a hybrid approach for leveraging the strengths of both models. We apply novel techniques to enhance both extractive and generative readers built upon recent pretrained neural language models, and find that proper training methods can provide large improvement over previous state-of-the-art models. We demonstrate that a simple hybrid approach by combining answers from both readers can efficiently take advantages of extractive and generative answer inference strategies and outperforms single models as well as homogeneous ensembles. Our approach outperforms previous state-of-the-art models by 3.3 and 2.7 points in exact match on NaturalQuestions and TriviaQA respectively.

📄 PDF Abstract BibTeX arXiv:2101.00178

Code (0)

등록된 구현이 없습니다.

Tasks

Open-Domain Question AnsweringQuestion AnsweringRetrievalTriviaQA

Similar Papers 제목 키워드 기반

Reasoning over Hybrid Chain for Table-and-Text Open Domain Question Answering

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Tabular and textual question answering requires systems to perform reasoning over heterogeneous information, considering table structure, and the connections among table and text. In this paper, we propose a ChAin-centri…

Open-Domain Question AnsweringQuestion Answering

Open-Domain Question Answering

2020-07-01 · ACL 2020 6 · Danqi Chen, Wen-tau Yih

This tutorial provides a comprehensive and coherent overview of cutting-edge research in open-domain question answering (QA), the task of answering questions using a large collection of documents of diversified topics. W…

Open-Domain Question AnsweringQuestion Answering

Reasoning over Hybrid Chain for Table-and-Text Open Domain QA

2022-01-15 · Wanjun Zhong, JunJie Huang, Qian Liu, Ming Zhou 외

Tabular and textual question answering requires systems to perform reasoning over heterogeneous information, considering table structure, and the connections among table and text. In this paper, we propose a ChAin-centri…

Open-Domain Question AnsweringQuestion Answering

SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing

2024-06-01 · Heidi C. Zhang, Sina J. Semnani, Farhad Ghassemi, Jialiang Xu 외

We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that utilizes information from heterogeneous knowledg…

Open-Domain Question AnsweringQuestion AnsweringRetrievalSemantic Parsing

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

2021-08-05 · ACL 2021 5 · Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu 외

The current state-of-the-art generative models for open-domain question answering (ODQA) have focused on generating direct answers from unstructured textual information. However, a large amount of world's knowledge is st…

Open-Domain Question AnsweringQuestion Answering