@inproceedings{feng-etal-2020-exploring,
title = "Exploring End-to-End Differentiable Natural Logic Modeling",
author = "Feng, Yufei and
Zheng, Zi{'}ou and
Liu, Quan and
Greenspan, Michael and
Zhu, Xiaodan",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.101",
doi = "10.18653/v1/2020.coling-main.101",
pages = "1172--1185",
abstract = "We explore end-to-end trained differentiable models that integrate natural logic with neural networks, aiming to keep the backbone of natural language reasoning based on the natural logic formalism while introducing subsymbolic vector representations and neural components. The proposed model adapts module networks to model natural logic operations, which is enhanced with a memory component to model contextual information. Experiments show that the proposed framework can effectively model monotonicity-based reasoning, compared to the baseline neural network models without built-in inductive bias for monotonicity-based reasoning. Our proposed model shows to be robust when transferred from upward to downward inference. We perform further analyses on the performance of the proposed model on aggregation, showing the effectiveness of the proposed subcomponents on helping achieve better intermediate aggregation performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2020-exploring">
<titleInfo>
<title>Exploring End-to-End Differentiable Natural Logic Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yufei</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zi’ou</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Greenspan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We explore end-to-end trained differentiable models that integrate natural logic with neural networks, aiming to keep the backbone of natural language reasoning based on the natural logic formalism while introducing subsymbolic vector representations and neural components. The proposed model adapts module networks to model natural logic operations, which is enhanced with a memory component to model contextual information. Experiments show that the proposed framework can effectively model monotonicity-based reasoning, compared to the baseline neural network models without built-in inductive bias for monotonicity-based reasoning. Our proposed model shows to be robust when transferred from upward to downward inference. We perform further analyses on the performance of the proposed model on aggregation, showing the effectiveness of the proposed subcomponents on helping achieve better intermediate aggregation performance.</abstract>
<identifier type="citekey">feng-etal-2020-exploring</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.101</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.101</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>1172</start>
<end>1185</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring End-to-End Differentiable Natural Logic Modeling
%A Feng, Yufei
%A Zheng, Zi’ou
%A Liu, Quan
%A Greenspan, Michael
%A Zhu, Xiaodan
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 dec
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F feng-etal-2020-exploring
%X We explore end-to-end trained differentiable models that integrate natural logic with neural networks, aiming to keep the backbone of natural language reasoning based on the natural logic formalism while introducing subsymbolic vector representations and neural components. The proposed model adapts module networks to model natural logic operations, which is enhanced with a memory component to model contextual information. Experiments show that the proposed framework can effectively model monotonicity-based reasoning, compared to the baseline neural network models without built-in inductive bias for monotonicity-based reasoning. Our proposed model shows to be robust when transferred from upward to downward inference. We perform further analyses on the performance of the proposed model on aggregation, showing the effectiveness of the proposed subcomponents on helping achieve better intermediate aggregation performance.
%R 10.18653/v1/2020.coling-main.101
%U https://aclanthology.org/2020.coling-main.101
%U https://doi.org/10.18653/v1/2020.coling-main.101
%P 1172-1185
Markdown (Informal)
[Exploring End-to-End Differentiable Natural Logic Modeling](https://aclanthology.org/2020.coling-main.101) (Feng et al., COLING 2020)
ACL
- Yufei Feng, Zi’ou Zheng, Quan Liu, Michael Greenspan, and Xiaodan Zhu. 2020. Exploring End-to-End Differentiable Natural Logic Modeling. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1172–1185, Barcelona, Spain (Online). International Committee on Computational Linguistics.