<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fei-etal-2022-proofinfer">
    <titleInfo>
        <title>ProofInfer: Generating Proof via Iterative Hierarchical Inference</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zichu</namePart>
        <namePart type="family">Fei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qi</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xin</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tao</namePart>
        <namePart type="family">Gui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xuanjing</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Proof generation focuses on deductive reasoning: given a hypothesis and a set of theories, including some supporting facts and logical rules expressed in natural language, the model generates a proof tree indicating how to deduce the hypothesis from given theories. Current models with state-of-the-art performance employ the stepwise method that adds an individual node to the proof step-by-step. However, these methods actually focus on generating several proof paths rather than a whole tree. During generation, they focus on the most relevant areas of the currently generated node while neglecting the rest of the proof tree. To address this problem, we propose ProofInfer, which generates the proof tree via iterative hierarchical inference. At each step, ProofInfer adds the entire layer to the proof, where all nodes in this layer are generated simultaneously. Since the conventional autoregressive generation architecture cannot simultaneously predict multiple nodes, ProofInfer employs text-to-text paradigm. To this end, we propose a divide-and-conquer algorithm to encode the proof tree as the plain text without losing structure information. Experimental results show that ProofInfer significantly improves performance on several widely-used datasets. In addition, ProofInfer still performs well with data-limited, achieving comparable performance to the state-of-the-art model with about 40% of the training data.</abstract>
    <identifier type="citekey">fei-etal-2022-proofinfer</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.747</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.747</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>10883</start>
            <end>10892</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ProofInfer: Generating Proof via Iterative Hierarchical Inference
%A Fei, Zichu
%A Zhang, Qi
%A Zhou, Xin
%A Gui, Tao
%A Huang, Xuanjing
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F fei-etal-2022-proofinfer
%X Proof generation focuses on deductive reasoning: given a hypothesis and a set of theories, including some supporting facts and logical rules expressed in natural language, the model generates a proof tree indicating how to deduce the hypothesis from given theories. Current models with state-of-the-art performance employ the stepwise method that adds an individual node to the proof step-by-step. However, these methods actually focus on generating several proof paths rather than a whole tree. During generation, they focus on the most relevant areas of the currently generated node while neglecting the rest of the proof tree. To address this problem, we propose ProofInfer, which generates the proof tree via iterative hierarchical inference. At each step, ProofInfer adds the entire layer to the proof, where all nodes in this layer are generated simultaneously. Since the conventional autoregressive generation architecture cannot simultaneously predict multiple nodes, ProofInfer employs text-to-text paradigm. To this end, we propose a divide-and-conquer algorithm to encode the proof tree as the plain text without losing structure information. Experimental results show that ProofInfer significantly improves performance on several widely-used datasets. In addition, ProofInfer still performs well with data-limited, achieving comparable performance to the state-of-the-art model with about 40% of the training data.
%R 10.18653/v1/2022.emnlp-main.747
%U https://aclanthology.org/2022.emnlp-main.747
%U https://doi.org/10.18653/v1/2022.emnlp-main.747
%P 10883-10892

Markdown (Informal)

[ProofInfer: Generating Proof via Iterative Hierarchical Inference](https://aclanthology.org/2022.emnlp-main.747) (Fei et al., EMNLP 2022)

• ProofInfer: Generating Proof via Iterative Hierarchical Inference (Fei et al., EMNLP 2022)

ACL

• Zichu Fei, Qi Zhang, Xin Zhou, Tao Gui, and Xuanjing Huang. 2022. ProofInfer: Generating Proof via Iterative Hierarchical Inference. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10883–10892, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.