@inproceedings{davison-etal-2019-commonsense,
title = "Commonsense Knowledge Mining from Pretrained Models",
author = "Davison, Joe and
Feldman, Joshua and
Rush, Alexander",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1109",
doi = "10.18653/v1/D19-1109",
pages = "1173--1178",
abstract = "Inferring commonsense knowledge is a key challenge in machine learning. Due to the sparsity of training data, previous work has shown that supervised methods for commonsense knowledge mining underperform when evaluated on novel data. In this work, we develop a method for generating commonsense knowledge using a large, pre-trained bidirectional language model. By transforming relational triples into masked sentences, we can use this model to rank a triple{'}s validity by the estimated pointwise mutual information between the two entities. Since we do not update the weights of the bidirectional model, our approach is not biased by the coverage of any one commonsense knowledge base. Though we do worse on a held-out test set than models explicitly trained on a corresponding training set, our approach outperforms these methods when mining commonsense knowledge from new sources, suggesting that our unsupervised technique generalizes better than current supervised approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="davison-etal-2019-commonsense">
<titleInfo>
<title>Commonsense Knowledge Mining from Pretrained Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joe</namePart>
<namePart type="family">Davison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Rush</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Inferring commonsense knowledge is a key challenge in machine learning. Due to the sparsity of training data, previous work has shown that supervised methods for commonsense knowledge mining underperform when evaluated on novel data. In this work, we develop a method for generating commonsense knowledge using a large, pre-trained bidirectional language model. By transforming relational triples into masked sentences, we can use this model to rank a triple’s validity by the estimated pointwise mutual information between the two entities. Since we do not update the weights of the bidirectional model, our approach is not biased by the coverage of any one commonsense knowledge base. Though we do worse on a held-out test set than models explicitly trained on a corresponding training set, our approach outperforms these methods when mining commonsense knowledge from new sources, suggesting that our unsupervised technique generalizes better than current supervised approaches.</abstract>
<identifier type="citekey">davison-etal-2019-commonsense</identifier>
<identifier type="doi">10.18653/v1/D19-1109</identifier>
<location>
<url>https://aclanthology.org/D19-1109</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1173</start>
<end>1178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Commonsense Knowledge Mining from Pretrained Models
%A Davison, Joe
%A Feldman, Joshua
%A Rush, Alexander
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F davison-etal-2019-commonsense
%X Inferring commonsense knowledge is a key challenge in machine learning. Due to the sparsity of training data, previous work has shown that supervised methods for commonsense knowledge mining underperform when evaluated on novel data. In this work, we develop a method for generating commonsense knowledge using a large, pre-trained bidirectional language model. By transforming relational triples into masked sentences, we can use this model to rank a triple’s validity by the estimated pointwise mutual information between the two entities. Since we do not update the weights of the bidirectional model, our approach is not biased by the coverage of any one commonsense knowledge base. Though we do worse on a held-out test set than models explicitly trained on a corresponding training set, our approach outperforms these methods when mining commonsense knowledge from new sources, suggesting that our unsupervised technique generalizes better than current supervised approaches.
%R 10.18653/v1/D19-1109
%U https://aclanthology.org/D19-1109
%U https://doi.org/10.18653/v1/D19-1109
%P 1173-1178
Markdown (Informal)
[Commonsense Knowledge Mining from Pretrained Models](https://aclanthology.org/D19-1109) (Davison et al., EMNLP-IJCNLP 2019)
ACL
- Joe Davison, Joshua Feldman, and Alexander Rush. 2019. Commonsense Knowledge Mining from Pretrained Models. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1173–1178, Hong Kong, China. Association for Computational Linguistics.