@inproceedings{qi-etal-2022-syntactically,
title = "Syntactically Robust Training on Partially-Observed Data for Open Information Extraction",
author = "Qi, Ji and
Chen, Yuxiang and
Hou, Lei and
Li, Juanzi and
Xu, Bin",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.465",
doi = "10.18653/v1/2022.findings-emnlp.465",
pages = "6245--6257",
abstract = "Open Information Extraction models have shown promising results with sufficient supervision. However, these models face a fundamental challenge that the syntactic distribution of training data is partially observable in comparison to the real world. In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation. To tackle the intrinsic problem of knowledge deformation of paraphrasing, two algorithms based on semantic similarity matching and syntactic tree walking are used to restore the expressionally transformed knowledge. The training framework can be generally applied to other syntactic partial observable domains. Based on the proposed framework, we build a new evaluation set called CaRB-AutoPara, a syntactically diverse dataset consistent with the real-world setting for validating the robustness of the models. Experiments including a thorough analysis show that the performance of the model degrades with the increase of the difference in syntactic distribution, while our framework gives a robust boundary.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2022-syntactically">
<titleInfo>
<title>Syntactically Robust Training on Partially-Observed Data for Open Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxiang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juanzi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Open Information Extraction models have shown promising results with sufficient supervision. However, these models face a fundamental challenge that the syntactic distribution of training data is partially observable in comparison to the real world. In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation. To tackle the intrinsic problem of knowledge deformation of paraphrasing, two algorithms based on semantic similarity matching and syntactic tree walking are used to restore the expressionally transformed knowledge. The training framework can be generally applied to other syntactic partial observable domains. Based on the proposed framework, we build a new evaluation set called CaRB-AutoPara, a syntactically diverse dataset consistent with the real-world setting for validating the robustness of the models. Experiments including a thorough analysis show that the performance of the model degrades with the increase of the difference in syntactic distribution, while our framework gives a robust boundary.</abstract>
<identifier type="citekey">qi-etal-2022-syntactically</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.465</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.465</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6245</start>
<end>6257</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Syntactically Robust Training on Partially-Observed Data for Open Information Extraction
%A Qi, Ji
%A Chen, Yuxiang
%A Hou, Lei
%A Li, Juanzi
%A Xu, Bin
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F qi-etal-2022-syntactically
%X Open Information Extraction models have shown promising results with sufficient supervision. However, these models face a fundamental challenge that the syntactic distribution of training data is partially observable in comparison to the real world. In this paper, we propose a syntactically robust training framework that enables models to be trained on a syntactic-abundant distribution based on diverse paraphrase generation. To tackle the intrinsic problem of knowledge deformation of paraphrasing, two algorithms based on semantic similarity matching and syntactic tree walking are used to restore the expressionally transformed knowledge. The training framework can be generally applied to other syntactic partial observable domains. Based on the proposed framework, we build a new evaluation set called CaRB-AutoPara, a syntactically diverse dataset consistent with the real-world setting for validating the robustness of the models. Experiments including a thorough analysis show that the performance of the model degrades with the increase of the difference in syntactic distribution, while our framework gives a robust boundary.
%R 10.18653/v1/2022.findings-emnlp.465
%U https://aclanthology.org/2022.findings-emnlp.465
%U https://doi.org/10.18653/v1/2022.findings-emnlp.465
%P 6245-6257
Markdown (Informal)
[Syntactically Robust Training on Partially-Observed Data for Open Information Extraction](https://aclanthology.org/2022.findings-emnlp.465) (Qi et al., Findings 2022)
ACL