@inproceedings{bevilacqua-etal-2020-generationary,
title = "Generationary or {``}How We Went beyond Word Sense Inventories and Learned to Gloss{''}",
author = "Bevilacqua, Michele and
Maru, Marco and
Navigli, Roberto",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.585",
doi = "10.18653/v1/2020.emnlp-main.585",
pages = "7207--7221",
abstract = "Mainstream computational lexical semantics embraces the assumption that word senses can be represented as discrete items of a predefined inventory. In this paper we show this needs not be the case, and propose a unified model that is able to produce contextually appropriate definitions. In our model, Generationary, we employ a novel span-based encoding scheme which we use to fine-tune an English pre-trained Encoder-Decoder system to generate glosses. We show that, even though we drop the need of choosing from a predefined sense inventory, our model can be employed effectively: not only does Generationary outperform previous approaches in the generative task of Definition Modeling in many settings, but it also matches or surpasses the state of the art in discriminative tasks such as Word Sense Disambiguation and Word-in-Context. Finally, we show that Generationary benefits from training on data from multiple inventories, with strong gains on various zero-shot benchmarks, including a novel dataset of definitions for free adjective-noun phrases. The software and reproduction materials are available at \url{http://generationary.org}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bevilacqua-etal-2020-generationary">
<titleInfo>
<title>Generationary or “How We Went beyond Word Sense Inventories and Learned to Gloss”</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Bevilacqua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Maru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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 the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Mainstream computational lexical semantics embraces the assumption that word senses can be represented as discrete items of a predefined inventory. In this paper we show this needs not be the case, and propose a unified model that is able to produce contextually appropriate definitions. In our model, Generationary, we employ a novel span-based encoding scheme which we use to fine-tune an English pre-trained Encoder-Decoder system to generate glosses. We show that, even though we drop the need of choosing from a predefined sense inventory, our model can be employed effectively: not only does Generationary outperform previous approaches in the generative task of Definition Modeling in many settings, but it also matches or surpasses the state of the art in discriminative tasks such as Word Sense Disambiguation and Word-in-Context. Finally, we show that Generationary benefits from training on data from multiple inventories, with strong gains on various zero-shot benchmarks, including a novel dataset of definitions for free adjective-noun phrases. The software and reproduction materials are available at http://generationary.org.</abstract>
<identifier type="citekey">bevilacqua-etal-2020-generationary</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.585</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.585</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>7207</start>
<end>7221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generationary or “How We Went beyond Word Sense Inventories and Learned to Gloss”
%A Bevilacqua, Michele
%A Maru, Marco
%A Navigli, Roberto
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F bevilacqua-etal-2020-generationary
%X Mainstream computational lexical semantics embraces the assumption that word senses can be represented as discrete items of a predefined inventory. In this paper we show this needs not be the case, and propose a unified model that is able to produce contextually appropriate definitions. In our model, Generationary, we employ a novel span-based encoding scheme which we use to fine-tune an English pre-trained Encoder-Decoder system to generate glosses. We show that, even though we drop the need of choosing from a predefined sense inventory, our model can be employed effectively: not only does Generationary outperform previous approaches in the generative task of Definition Modeling in many settings, but it also matches or surpasses the state of the art in discriminative tasks such as Word Sense Disambiguation and Word-in-Context. Finally, we show that Generationary benefits from training on data from multiple inventories, with strong gains on various zero-shot benchmarks, including a novel dataset of definitions for free adjective-noun phrases. The software and reproduction materials are available at http://generationary.org.
%R 10.18653/v1/2020.emnlp-main.585
%U https://aclanthology.org/2020.emnlp-main.585
%U https://doi.org/10.18653/v1/2020.emnlp-main.585
%P 7207-7221
Markdown (Informal)
[Generationary or “How We Went beyond Word Sense Inventories and Learned to Gloss”](https://aclanthology.org/2020.emnlp-main.585) (Bevilacqua et al., EMNLP 2020)
ACL