@inproceedings{groeneveld-etal-2020-simple,
title = "A Simple Yet Strong Pipeline for {H}otpot{QA}",
author = "Groeneveld, Dirk and
Khot, Tushar and
Mausam and
Sabharwal, Ashish",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.711/",
doi = "10.18653/v1/2020.emnlp-main.711",
pages = "8839--8845",
abstract = "State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named entity recognition, graph-based reasoning, and question decomposition. However, does their strong performance on popular multi-hop datasets really justify this added design complexity? Our results suggest that the answer may be no, because even our simple pipeline based on BERT, named , performs surprisingly well. Specifically, on HotpotQA, Quark outperforms these models on both question answering and support identification (and achieves performance very close to a RoBERTa model). Our pipeline has three steps: 1) use BERT to identify potentially relevant sentences \textit{independently} of each other; 2) feed the set of selected sentences as context into a standard BERT span prediction model to choose an answer; and 3) use the sentence selection model, now with the chosen answer, to produce supporting sentences. The strong performance of Quark resurfaces the importance of carefully exploring simple model designs before using popular benchmarks to justify the value of complex techniques."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="groeneveld-etal-2020-simple">
<titleInfo>
<title>A Simple Yet Strong Pipeline for HotpotQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Groeneveld</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tushar</namePart>
<namePart type="family">Khot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Mausam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Sabharwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named entity recognition, graph-based reasoning, and question decomposition. However, does their strong performance on popular multi-hop datasets really justify this added design complexity? Our results suggest that the answer may be no, because even our simple pipeline based on BERT, named , performs surprisingly well. Specifically, on HotpotQA, Quark outperforms these models on both question answering and support identification (and achieves performance very close to a RoBERTa model). Our pipeline has three steps: 1) use BERT to identify potentially relevant sentences independently of each other; 2) feed the set of selected sentences as context into a standard BERT span prediction model to choose an answer; and 3) use the sentence selection model, now with the chosen answer, to produce supporting sentences. The strong performance of Quark resurfaces the importance of carefully exploring simple model designs before using popular benchmarks to justify the value of complex techniques.</abstract>
<identifier type="citekey">groeneveld-etal-2020-simple</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.711</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.711/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>8839</start>
<end>8845</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Simple Yet Strong Pipeline for HotpotQA
%A Groeneveld, Dirk
%A Khot, Tushar
%A Sabharwal, Ashish
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%A Mausam
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F groeneveld-etal-2020-simple
%X State-of-the-art models for multi-hop question answering typically augment large-scale language models like BERT with additional, intuitively useful capabilities such as named entity recognition, graph-based reasoning, and question decomposition. However, does their strong performance on popular multi-hop datasets really justify this added design complexity? Our results suggest that the answer may be no, because even our simple pipeline based on BERT, named , performs surprisingly well. Specifically, on HotpotQA, Quark outperforms these models on both question answering and support identification (and achieves performance very close to a RoBERTa model). Our pipeline has three steps: 1) use BERT to identify potentially relevant sentences independently of each other; 2) feed the set of selected sentences as context into a standard BERT span prediction model to choose an answer; and 3) use the sentence selection model, now with the chosen answer, to produce supporting sentences. The strong performance of Quark resurfaces the importance of carefully exploring simple model designs before using popular benchmarks to justify the value of complex techniques.
%R 10.18653/v1/2020.emnlp-main.711
%U https://aclanthology.org/2020.emnlp-main.711/
%U https://doi.org/10.18653/v1/2020.emnlp-main.711
%P 8839-8845
Markdown (Informal)
[A Simple Yet Strong Pipeline for HotpotQA](https://aclanthology.org/2020.emnlp-main.711/) (Groeneveld et al., EMNLP 2020)
ACL
- Dirk Groeneveld, Tushar Khot, Mausam, and Ashish Sabharwal. 2020. A Simple Yet Strong Pipeline for HotpotQA. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8839–8845, Online. Association for Computational Linguistics.