@inproceedings{guo-etal-2020-understanding,
title = "Understanding Unnatural Questions Improves Reasoning over Text",
author = "Guo, Xiaoyu and
Li, Yuan-Fang and
Haffari, Gholamreza",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.434",
doi = "10.18653/v1/2020.coling-main.434",
pages = "4949--4955",
abstract = "Complex question answering (CQA) over raw text is a challenging task. A prominent approach to this task is based on the programmer-interpreter framework, where the programmer maps the question into a sequence of reasoning actions and the interpreter then executes these actions on the raw text. Learning an effective CQA model requires large amounts of human-annotated data, consisting of the ground-truth sequence of reasoning actions, which is time-consuming and expensive to collect at scale. In this paper, we address the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machine-generated questions which are more convenient to parse. We firstly generate synthetic (question, action sequence) pairs by a data generator, and train a semantic parser that associates synthetic questions with their corresponding action sequences. To capture the diversity when applied to natural questions, we learn a projection model to map natural questions into their most similar unnatural questions for which the parser can work well. Without any natural training data, our projection model provides high-quality action sequences for the CQA task. Experimental results show that the QA model trained exclusively with synthetic data outperforms its state-of-the-art counterpart trained on human-labeled data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2020-understanding">
<titleInfo>
<title>Understanding Unnatural Questions Improves Reasoning over Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan-Fang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Complex question answering (CQA) over raw text is a challenging task. A prominent approach to this task is based on the programmer-interpreter framework, where the programmer maps the question into a sequence of reasoning actions and the interpreter then executes these actions on the raw text. Learning an effective CQA model requires large amounts of human-annotated data, consisting of the ground-truth sequence of reasoning actions, which is time-consuming and expensive to collect at scale. In this paper, we address the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machine-generated questions which are more convenient to parse. We firstly generate synthetic (question, action sequence) pairs by a data generator, and train a semantic parser that associates synthetic questions with their corresponding action sequences. To capture the diversity when applied to natural questions, we learn a projection model to map natural questions into their most similar unnatural questions for which the parser can work well. Without any natural training data, our projection model provides high-quality action sequences for the CQA task. Experimental results show that the QA model trained exclusively with synthetic data outperforms its state-of-the-art counterpart trained on human-labeled data.</abstract>
<identifier type="citekey">guo-etal-2020-understanding</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.434</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.434</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4949</start>
<end>4955</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding Unnatural Questions Improves Reasoning over Text
%A Guo, Xiaoyu
%A Li, Yuan-Fang
%A Haffari, Gholamreza
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F guo-etal-2020-understanding
%X Complex question answering (CQA) over raw text is a challenging task. A prominent approach to this task is based on the programmer-interpreter framework, where the programmer maps the question into a sequence of reasoning actions and the interpreter then executes these actions on the raw text. Learning an effective CQA model requires large amounts of human-annotated data, consisting of the ground-truth sequence of reasoning actions, which is time-consuming and expensive to collect at scale. In this paper, we address the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machine-generated questions which are more convenient to parse. We firstly generate synthetic (question, action sequence) pairs by a data generator, and train a semantic parser that associates synthetic questions with their corresponding action sequences. To capture the diversity when applied to natural questions, we learn a projection model to map natural questions into their most similar unnatural questions for which the parser can work well. Without any natural training data, our projection model provides high-quality action sequences for the CQA task. Experimental results show that the QA model trained exclusively with synthetic data outperforms its state-of-the-art counterpart trained on human-labeled data.
%R 10.18653/v1/2020.coling-main.434
%U https://aclanthology.org/2020.coling-main.434
%U https://doi.org/10.18653/v1/2020.coling-main.434
%P 4949-4955
Markdown (Informal)
[Understanding Unnatural Questions Improves Reasoning over Text](https://aclanthology.org/2020.coling-main.434) (Guo et al., COLING 2020)
ACL