<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yadav-etal-2021-enhancing">
    <titleInfo>
        <title>Enhancing Interpretable Clauses Semantically using Pretrained Word Representation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rohan</namePart>
        <namePart type="given">Kumar</namePart>
        <namePart type="family">Yadav</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lei</namePart>
        <namePart type="family">Jiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ole-Christoffer</namePart>
        <namePart type="family">Granmo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Morten</namePart>
        <namePart type="family">Goodwin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Tsetlin Machine (TM) is an interpretable pattern recognition algorithm based on propositional logic, which has demonstrated competitive performance in many Natural Language Processing (NLP) tasks, including sentiment analysis, text classification, and Word Sense Disambiguation. To obtain human-level interpretability, legacy TM employs Boolean input features such as bag-of-words (BOW). However, the BOW representation makes it difficult to use any pre-trained information, for instance, word2vec and GloVe word representations. This restriction has constrained the performance of TM compared to deep neural networks (DNNs) in NLP. To reduce the performance gap, in this paper, we propose a novel way of using pre-trained word representations for TM. The approach significantly enhances the performance and interpretability of TM. We achieve this by extracting semantically related words from pre-trained word representations as input features to the TM. Our experiments show that the accuracy of the proposed approach is significantly higher than the previous BOW-based TM, reaching the level of DNN-based models.</abstract>
    <identifier type="citekey">yadav-etal-2021-enhancing</identifier>
    <identifier type="doi">10.18653/v1/2021.blackboxnlp-1.19</identifier>
    <location>
        <url>https://aclanthology.org/2021.blackboxnlp-1.19</url>
    </location>
    <part>
        <date>2021-nov</date>
        <extent unit="page">
            <start>265</start>
            <end>274</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enhancing Interpretable Clauses Semantically using Pretrained Word Representation
%A Yadav, Rohan Kumar
%A Jiao, Lei
%A Granmo, Ole-Christoffer
%A Goodwin, Morten
%S Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F yadav-etal-2021-enhancing
%X Tsetlin Machine (TM) is an interpretable pattern recognition algorithm based on propositional logic, which has demonstrated competitive performance in many Natural Language Processing (NLP) tasks, including sentiment analysis, text classification, and Word Sense Disambiguation. To obtain human-level interpretability, legacy TM employs Boolean input features such as bag-of-words (BOW). However, the BOW representation makes it difficult to use any pre-trained information, for instance, word2vec and GloVe word representations. This restriction has constrained the performance of TM compared to deep neural networks (DNNs) in NLP. To reduce the performance gap, in this paper, we propose a novel way of using pre-trained word representations for TM. The approach significantly enhances the performance and interpretability of TM. We achieve this by extracting semantically related words from pre-trained word representations as input features to the TM. Our experiments show that the accuracy of the proposed approach is significantly higher than the previous BOW-based TM, reaching the level of DNN-based models.
%R 10.18653/v1/2021.blackboxnlp-1.19
%U https://aclanthology.org/2021.blackboxnlp-1.19
%U https://doi.org/10.18653/v1/2021.blackboxnlp-1.19
%P 265-274

Markdown (Informal)

[Enhancing Interpretable Clauses Semantically using Pretrained Word Representation](https://aclanthology.org/2021.blackboxnlp-1.19) (Yadav et al., BlackboxNLP 2021)

• Enhancing Interpretable Clauses Semantically using Pretrained Word Representation (Yadav et al., BlackboxNLP 2021)

ACL

• Rohan Kumar Yadav, Lei Jiao, Ole-Christoffer Granmo, and Morten Goodwin. 2021. Enhancing Interpretable Clauses Semantically using Pretrained Word Representation. In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 265–274, Punta Cana, Dominican Republic. Association for Computational Linguistics.