<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abzianidze-2020-learning">
    <titleInfo>
        <title>Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lasha</namePart>
        <namePart type="family">Abzianidze</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Iryna</namePart>
            <namePart type="family">Gurevych</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marianna</namePart>
            <namePart type="family">Apidianaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Manaal</namePart>
            <namePart type="family">Faruqui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Tackling Natural Language Inference with a logic-based method is becoming less and less common. While this might have been counterintuitive several decades ago, nowadays it seems pretty obvious. The main reasons for such a conception are that (a) logic-based methods are usually brittle when it comes to processing wide-coverage texts, and (b) instead of automatically learning from data, they require much of manual effort for development. We make a step towards to overcome such shortcomings by modeling learning from data as abduction: reversing a theorem-proving procedure to abduce semantic relations that serve as the best explanation for the gold label of an inference problem. In other words, instead of proving sentence-level inference relations with the help of lexical relations, the lexical relations are proved taking into account the sentence-level inference relations. We implement the learning method in a tableau theorem prover for natural language and show that it improves the performance of the theorem prover on the SICK dataset by 1.4% while still maintaining high precision (\textgreater94%). The obtained results are competitive with the state of the art among logic-based systems.</abstract>
    <identifier type="citekey">abzianidze-2020-learning</identifier>
    <location>
        <url>https://aclanthology.org/2020.starsem-1.3</url>
    </location>
    <part>
        <date>2020-12</date>
        <extent unit="page">
            <start>20</start>
            <end>31</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference
%A Abzianidze, Lasha
%Y Gurevych, Iryna
%Y Apidianaki, Marianna
%Y Faruqui, Manaal
%S Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics
%D 2020
%8 December
%I Association for Computational Linguistics
%C Barcelona, Spain (Online)
%F abzianidze-2020-learning
%X Tackling Natural Language Inference with a logic-based method is becoming less and less common. While this might have been counterintuitive several decades ago, nowadays it seems pretty obvious. The main reasons for such a conception are that (a) logic-based methods are usually brittle when it comes to processing wide-coverage texts, and (b) instead of automatically learning from data, they require much of manual effort for development. We make a step towards to overcome such shortcomings by modeling learning from data as abduction: reversing a theorem-proving procedure to abduce semantic relations that serve as the best explanation for the gold label of an inference problem. In other words, instead of proving sentence-level inference relations with the help of lexical relations, the lexical relations are proved taking into account the sentence-level inference relations. We implement the learning method in a tableau theorem prover for natural language and show that it improves the performance of the theorem prover on the SICK dataset by 1.4% while still maintaining high precision (\textgreater94%). The obtained results are competitive with the state of the art among logic-based systems.
%U https://aclanthology.org/2020.starsem-1.3
%P 20-31

Markdown (Informal)

[Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference](https://aclanthology.org/2020.starsem-1.3) (Abzianidze, *SEM 2020)

• Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference (Abzianidze, *SEM 2020)

ACL

• Lasha Abzianidze. 2020. Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference. In Proceedings of the Ninth Joint Conference on Lexical and Computational Semantics, pages 20–31, Barcelona, Spain (Online). Association for Computational Linguistics.