<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="du-etal-2018-multi">
    <titleInfo>
        <title>Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinhua</namePart>
        <namePart type="family">Du</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jingguang</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andy</namePart>
        <namePart type="family">Way</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dadong</namePart>
        <namePart type="family">Wan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ellen</namePart>
            <namePart type="family">Riloff</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Chiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Hockenmaier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun’ichi</namePart>
            <namePart type="family">Tsujii</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Attention mechanism is often used in deep neural networks for distantly supervised relation extraction (DS-RE) to distinguish valid from noisy instances. However, traditional 1-D vector attention model is insufficient for learning of different contexts in the selection of valid instances to predict the relationship for an entity pair. To alleviate this issue, we propose a novel multi-level structured (2-D matrix) self-attention mechanism for DS-RE in a multi-instance learning (MIL) framework using bidirectional recurrent neural networks (BiRNN). In the proposed method, a structured word-level self-attention learns a 2-D matrix where each row vector represents a weight distribution for different aspects of an instance regarding two entities. Targeting the MIL issue, the structured sentence-level attention learns a 2-D matrix where each row vector represents a weight distribution on selection of different valid instances. Experiments conducted on two publicly available DS-RE datasets show that the proposed framework with multi-level structured self-attention mechanism significantly outperform baselines in terms of PR curves, P@N and F1 measures.</abstract>
    <identifier type="citekey">du-etal-2018-multi</identifier>
    <identifier type="doi">10.18653/v1/D18-1245</identifier>
    <location>
        <url>https://aclanthology.org/D18-1245</url>
    </location>
    <part>
        <date>2018-oct-nov</date>
        <extent unit="page">
            <start>2216</start>
            <end>2225</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction
%A Du, Jinhua
%A Han, Jingguang
%A Way, Andy
%A Wan, Dadong
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F du-etal-2018-multi
%X Attention mechanism is often used in deep neural networks for distantly supervised relation extraction (DS-RE) to distinguish valid from noisy instances. However, traditional 1-D vector attention model is insufficient for learning of different contexts in the selection of valid instances to predict the relationship for an entity pair. To alleviate this issue, we propose a novel multi-level structured (2-D matrix) self-attention mechanism for DS-RE in a multi-instance learning (MIL) framework using bidirectional recurrent neural networks (BiRNN). In the proposed method, a structured word-level self-attention learns a 2-D matrix where each row vector represents a weight distribution for different aspects of an instance regarding two entities. Targeting the MIL issue, the structured sentence-level attention learns a 2-D matrix where each row vector represents a weight distribution on selection of different valid instances. Experiments conducted on two publicly available DS-RE datasets show that the proposed framework with multi-level structured self-attention mechanism significantly outperform baselines in terms of PR curves, P@N and F1 measures.
%R 10.18653/v1/D18-1245
%U https://aclanthology.org/D18-1245
%U https://doi.org/10.18653/v1/D18-1245
%P 2216-2225

Markdown (Informal)

[Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction](https://aclanthology.org/D18-1245) (Du et al., EMNLP 2018)

• Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction (Du et al., EMNLP 2018)

ACL

• Jinhua Du, Jingguang Han, Andy Way, and Dadong Wan. 2018. Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2216–2225, Brussels, Belgium. Association for Computational Linguistics.