<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-liu-2017-non">
    <titleInfo>
        <title>A non-DNN Feature Engineering Approach to Dependency Parsing – FBAML at CoNLL 2017 Shared Task</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xian</namePart>
        <namePart type="family">Qian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jan</namePart>
            <namePart type="family">Hajič</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dan</namePart>
            <namePart type="family">Zeman</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>For this year’s multilingual dependency parsing shared task, we developed a pipeline system, which uses a variety of features for each of its components. Unlike the recent popular deep learning approaches that learn low dimensional dense features using non-linear classifier, our system uses structured linear classifiers to learn millions of sparse features. Specifically, we trained a linear classifier for sentence boundary prediction, linear chain conditional random fields (CRFs) for tokenization, part-of-speech tagging and morph analysis. A second order graph based parser learns the tree structure (without relations), and fa linear tree CRF then assigns relations to the dependencies in the tree. Our system achieves reasonable performance – 67.87% official averaged macro F1 score</abstract>
    <identifier type="citekey">qian-liu-2017-non</identifier>
    <identifier type="doi">10.18653/v1/K17-3015</identifier>
    <location>
        <url>https://aclanthology.org/K17-3015</url>
    </location>
    <part>
        <date>2017-08</date>
        <extent unit="page">
            <start>143</start>
            <end>151</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A non-DNN Feature Engineering Approach to Dependency Parsing – FBAML at CoNLL 2017 Shared Task
%A Qian, Xian
%A Liu, Yang
%Y Hajič, Jan
%Y Zeman, Dan
%S Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F qian-liu-2017-non
%X For this year’s multilingual dependency parsing shared task, we developed a pipeline system, which uses a variety of features for each of its components. Unlike the recent popular deep learning approaches that learn low dimensional dense features using non-linear classifier, our system uses structured linear classifiers to learn millions of sparse features. Specifically, we trained a linear classifier for sentence boundary prediction, linear chain conditional random fields (CRFs) for tokenization, part-of-speech tagging and morph analysis. A second order graph based parser learns the tree structure (without relations), and fa linear tree CRF then assigns relations to the dependencies in the tree. Our system achieves reasonable performance – 67.87% official averaged macro F1 score
%R 10.18653/v1/K17-3015
%U https://aclanthology.org/K17-3015
%U https://doi.org/10.18653/v1/K17-3015
%P 143-151

Markdown (Informal)

[A non-DNN Feature Engineering Approach to Dependency Parsing – FBAML at CoNLL 2017 Shared Task](https://aclanthology.org/K17-3015) (Qian & Liu, CoNLL 2017)

• A non-DNN Feature Engineering Approach to Dependency Parsing – FBAML at CoNLL 2017 Shared Task (Qian & Liu, CoNLL 2017)

ACL

• Xian Qian and Yang Liu. 2017. A non-DNN Feature Engineering Approach to Dependency Parsing – FBAML at CoNLL 2017 Shared Task. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 143–151, Vancouver, Canada. Association for Computational Linguistics.