@inproceedings{tielin-etal-2021-ns,
title = "{NS}-Hunter: {BERT}-Cloze Based Semantic Denoising for Distantly Supervised Relation Classification",
author = "Tielin, Shen and
Daling, Wang and
Shi, Feng and
Yifei, Zhang",
editor = "Li, Sheng and
Sun, Maosong and
Liu, Yang and
Wu, Hua and
Liu, Kang and
Che, Wanxiang and
He, Shizhu and
Rao, Gaoqi",
booktitle = "Proceedings of the 20th Chinese National Conference on Computational Linguistics",
month = aug,
year = "2021",
address = "Huhhot, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2021.ccl-1.99/",
pages = "1109--1120",
language = "eng",
abstract = "Distant supervision can generate large-scale relation classification data quickly and economi-cally. However a great number of noise sentences are introduced which can not express their labeled relations. By means of pre-trained language model BERT`s powerful function in this paper we propose a BERT-based semantic denoising approach for distantly supervised relation classification. In detail we define an entity pair as a source entity and a target entity. For the specific sentences whose target entities in BERT-vocabulary (one-token word) we present the differences of dependency between two entities for noise and non-noise sentences. For general sentences whose target entity is multi-token word we further present the differences of last hid-den states of [MASK]-entity (MASK-lhs for short) in BERT for noise and non-noise sentences. We regard the dependency and MASK-lhs in BERT as two semantic features of sentences. With BERT we capture the dependency feature to discriminate specific sentences first then capturethe MASK-lhs feature to denoise distant supervision datasets. We propose NS-Hunter a noveldenoising model which leverages BERT-cloze ability to capture the two semantic features andintegrates above functions. According to the experiment on NYT data our NS-Hunter modelachieves the best results in distant supervision denoising and sentence-level relation classification. Keywords: Distant supervision relation classification semantic denoisingIntroduction"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tielin-etal-2021-ns">
<titleInfo>
<title>NS-Hunter: BERT-Cloze Based Semantic Denoising for Distantly Supervised Relation Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shen</namePart>
<namePart type="family">Tielin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Daling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Yifei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</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>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Huhhot, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Distant supervision can generate large-scale relation classification data quickly and economi-cally. However a great number of noise sentences are introduced which can not express their labeled relations. By means of pre-trained language model BERT‘s powerful function in this paper we propose a BERT-based semantic denoising approach for distantly supervised relation classification. In detail we define an entity pair as a source entity and a target entity. For the specific sentences whose target entities in BERT-vocabulary (one-token word) we present the differences of dependency between two entities for noise and non-noise sentences. For general sentences whose target entity is multi-token word we further present the differences of last hid-den states of [MASK]-entity (MASK-lhs for short) in BERT for noise and non-noise sentences. We regard the dependency and MASK-lhs in BERT as two semantic features of sentences. With BERT we capture the dependency feature to discriminate specific sentences first then capturethe MASK-lhs feature to denoise distant supervision datasets. We propose NS-Hunter a noveldenoising model which leverages BERT-cloze ability to capture the two semantic features andintegrates above functions. According to the experiment on NYT data our NS-Hunter modelachieves the best results in distant supervision denoising and sentence-level relation classification. Keywords: Distant supervision relation classification semantic denoisingIntroduction</abstract>
<identifier type="citekey">tielin-etal-2021-ns</identifier>
<location>
<url>https://aclanthology.org/2021.ccl-1.99/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1109</start>
<end>1120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NS-Hunter: BERT-Cloze Based Semantic Denoising for Distantly Supervised Relation Classification
%A Tielin, Shen
%A Daling, Wang
%A Shi, Feng
%A Yifei, Zhang
%Y Li, Sheng
%Y Sun, Maosong
%Y Liu, Yang
%Y Wu, Hua
%Y Liu, Kang
%Y Che, Wanxiang
%Y He, Shizhu
%Y Rao, Gaoqi
%S Proceedings of the 20th Chinese National Conference on Computational Linguistics
%D 2021
%8 August
%I Chinese Information Processing Society of China
%C Huhhot, China
%G eng
%F tielin-etal-2021-ns
%X Distant supervision can generate large-scale relation classification data quickly and economi-cally. However a great number of noise sentences are introduced which can not express their labeled relations. By means of pre-trained language model BERT‘s powerful function in this paper we propose a BERT-based semantic denoising approach for distantly supervised relation classification. In detail we define an entity pair as a source entity and a target entity. For the specific sentences whose target entities in BERT-vocabulary (one-token word) we present the differences of dependency between two entities for noise and non-noise sentences. For general sentences whose target entity is multi-token word we further present the differences of last hid-den states of [MASK]-entity (MASK-lhs for short) in BERT for noise and non-noise sentences. We regard the dependency and MASK-lhs in BERT as two semantic features of sentences. With BERT we capture the dependency feature to discriminate specific sentences first then capturethe MASK-lhs feature to denoise distant supervision datasets. We propose NS-Hunter a noveldenoising model which leverages BERT-cloze ability to capture the two semantic features andintegrates above functions. According to the experiment on NYT data our NS-Hunter modelachieves the best results in distant supervision denoising and sentence-level relation classification. Keywords: Distant supervision relation classification semantic denoisingIntroduction
%U https://aclanthology.org/2021.ccl-1.99/
%P 1109-1120
Markdown (Informal)
[NS-Hunter: BERT-Cloze Based Semantic Denoising for Distantly Supervised Relation Classification](https://aclanthology.org/2021.ccl-1.99/) (Tielin et al., CCL 2021)
ACL