@inproceedings{liu-etal-2022-plog,
title = "{PLOG}: Table-to-Logic Pretraining for Logical Table-to-Text Generation",
author = "Liu, Ao and
Dong, Haoyu and
Okazaki, Naoaki and
Han, Shi and
Zhang, Dongmei",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.373",
doi = "10.18653/v1/2022.emnlp-main.373",
pages = "5531--5546",
abstract = "Logical table-to-text generation is a task that involves generating logically faithful sentences from tables, which requires models to derive logical-level facts from table records via logical inference. It raises a new challenge on the logical-level content planning of table-to-text models. However, directly learning the logical inference knowledge from table-text pairs is very difficult for neural models because of the ambiguity of natural language and the scarcity of parallel data. Hence even large-scale pre-trained language models present low logical fidelity on logical table-to-text. In this work, we propose a Pretrained Logical Form Generator (PLOG) framework to improve generation fidelity. Specifically, PLOG is first pretrained on a table-to-logical-form generation (table-to-logic) task, then finetuned on downstream table-to-text tasks. The logical forms are formally defined with unambiguous semantics. Hence we can collect a large amount of accurate logical forms from tables without human annotation. In addition, PLOG can learn logical inference from table-logic pairs much more reliably than from table-text pairs. To evaluate our model, we further collect a controlled logical table-to-text dataset CONTLOG based on an existing dataset. On two benchmarks, LOGICNLG and CONTLOG, PLOG outperforms strong baselines by a large margin on the logical fidelity, demonstrating the effectiveness of table-to-logic pretraining.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-plog">
<titleInfo>
<title>PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shi</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongmei</namePart>
<namePart type="family">Zhang</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>Logical table-to-text generation is a task that involves generating logically faithful sentences from tables, which requires models to derive logical-level facts from table records via logical inference. It raises a new challenge on the logical-level content planning of table-to-text models. However, directly learning the logical inference knowledge from table-text pairs is very difficult for neural models because of the ambiguity of natural language and the scarcity of parallel data. Hence even large-scale pre-trained language models present low logical fidelity on logical table-to-text. In this work, we propose a Pretrained Logical Form Generator (PLOG) framework to improve generation fidelity. Specifically, PLOG is first pretrained on a table-to-logical-form generation (table-to-logic) task, then finetuned on downstream table-to-text tasks. The logical forms are formally defined with unambiguous semantics. Hence we can collect a large amount of accurate logical forms from tables without human annotation. In addition, PLOG can learn logical inference from table-logic pairs much more reliably than from table-text pairs. To evaluate our model, we further collect a controlled logical table-to-text dataset CONTLOG based on an existing dataset. On two benchmarks, LOGICNLG and CONTLOG, PLOG outperforms strong baselines by a large margin on the logical fidelity, demonstrating the effectiveness of table-to-logic pretraining.</abstract>
<identifier type="citekey">liu-etal-2022-plog</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.373</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.373</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5531</start>
<end>5546</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation
%A Liu, Ao
%A Dong, Haoyu
%A Okazaki, Naoaki
%A Han, Shi
%A Zhang, Dongmei
%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 liu-etal-2022-plog
%X Logical table-to-text generation is a task that involves generating logically faithful sentences from tables, which requires models to derive logical-level facts from table records via logical inference. It raises a new challenge on the logical-level content planning of table-to-text models. However, directly learning the logical inference knowledge from table-text pairs is very difficult for neural models because of the ambiguity of natural language and the scarcity of parallel data. Hence even large-scale pre-trained language models present low logical fidelity on logical table-to-text. In this work, we propose a Pretrained Logical Form Generator (PLOG) framework to improve generation fidelity. Specifically, PLOG is first pretrained on a table-to-logical-form generation (table-to-logic) task, then finetuned on downstream table-to-text tasks. The logical forms are formally defined with unambiguous semantics. Hence we can collect a large amount of accurate logical forms from tables without human annotation. In addition, PLOG can learn logical inference from table-logic pairs much more reliably than from table-text pairs. To evaluate our model, we further collect a controlled logical table-to-text dataset CONTLOG based on an existing dataset. On two benchmarks, LOGICNLG and CONTLOG, PLOG outperforms strong baselines by a large margin on the logical fidelity, demonstrating the effectiveness of table-to-logic pretraining.
%R 10.18653/v1/2022.emnlp-main.373
%U https://aclanthology.org/2022.emnlp-main.373
%U https://doi.org/10.18653/v1/2022.emnlp-main.373
%P 5531-5546
Markdown (Informal)
[PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation](https://aclanthology.org/2022.emnlp-main.373) (Liu et al., EMNLP 2022)
ACL