@inproceedings{cibu-marginean-2020-commonsense,
title = "Commonsense Statements Identification and Explanation with Transformer-based Encoders",
author = "Cibu, Sonia and
Marginean, Anca",
editor = "Agirre, Eneko and
Apidianaki, Marianna and
Vuli{\'c}, Ivan",
booktitle = "Proceedings of Deep Learning Inside Out (DeeLIO): The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.deelio-1.10/",
doi = "10.18653/v1/2020.deelio-1.10",
pages = "80--88",
abstract = "In this work, we present our empirical attempt to identify the proper strategy of using Transformer Language Models to identify sentences consistent with commonsense. We tackle the first two tasks from the ComVE competition. The starting point for our work is the BERT assumption according to which a large number of NLP tasks can be solved with pre-trained Transformers with no substantial task-specific changes of the architecture. However, our experiments show that the encoding strategy can have a great impact on the quality of the fine-tuning. The combination between cross-encoding and multi-input models worked better than one cross-encoder and allowed us to achieve comparable results with the state-of-the-art without the use of any external data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cibu-marginean-2020-commonsense">
<titleInfo>
<title>Commonsense Statements Identification and Explanation with Transformer-based Encoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sonia</namePart>
<namePart type="family">Cibu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anca</namePart>
<namePart type="family">Marginean</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Deep Learning Inside Out (DeeLIO): The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</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">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we present our empirical attempt to identify the proper strategy of using Transformer Language Models to identify sentences consistent with commonsense. We tackle the first two tasks from the ComVE competition. The starting point for our work is the BERT assumption according to which a large number of NLP tasks can be solved with pre-trained Transformers with no substantial task-specific changes of the architecture. However, our experiments show that the encoding strategy can have a great impact on the quality of the fine-tuning. The combination between cross-encoding and multi-input models worked better than one cross-encoder and allowed us to achieve comparable results with the state-of-the-art without the use of any external data.</abstract>
<identifier type="citekey">cibu-marginean-2020-commonsense</identifier>
<identifier type="doi">10.18653/v1/2020.deelio-1.10</identifier>
<location>
<url>https://aclanthology.org/2020.deelio-1.10/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>80</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Commonsense Statements Identification and Explanation with Transformer-based Encoders
%A Cibu, Sonia
%A Marginean, Anca
%Y Agirre, Eneko
%Y Apidianaki, Marianna
%Y Vulić, Ivan
%S Proceedings of Deep Learning Inside Out (DeeLIO): The First Workshop on Knowledge Extraction and Integration for Deep Learning Architectures
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F cibu-marginean-2020-commonsense
%X In this work, we present our empirical attempt to identify the proper strategy of using Transformer Language Models to identify sentences consistent with commonsense. We tackle the first two tasks from the ComVE competition. The starting point for our work is the BERT assumption according to which a large number of NLP tasks can be solved with pre-trained Transformers with no substantial task-specific changes of the architecture. However, our experiments show that the encoding strategy can have a great impact on the quality of the fine-tuning. The combination between cross-encoding and multi-input models worked better than one cross-encoder and allowed us to achieve comparable results with the state-of-the-art without the use of any external data.
%R 10.18653/v1/2020.deelio-1.10
%U https://aclanthology.org/2020.deelio-1.10/
%U https://doi.org/10.18653/v1/2020.deelio-1.10
%P 80-88
Markdown (Informal)
[Commonsense Statements Identification and Explanation with Transformer-based Encoders](https://aclanthology.org/2020.deelio-1.10/) (Cibu & Marginean, DeeLIO 2020)
ACL