@inproceedings{nogueira-dos-santos-etal-2020-beyond,
title = "Beyond [{CLS}] through Ranking by Generation",
author = "Nogueira dos Santos, Cicero and
Ma, Xiaofei and
Nallapati, Ramesh and
Huang, Zhiheng and
Xiang, Bing",
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.134",
doi = "10.18653/v1/2020.emnlp-main.134",
pages = "1722--1727",
abstract = "Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document{'}s language model, were very successful in various IR tasks in the past. However, with the advent of modern deep neural networks, attention has shifted to discriminative ranking functions that model the semantic similarity of documents and queries instead. Recently, deep generative models such as GPT2 and BART have been shown to be excellent text generators, but their effectiveness as rankers have not been demonstrated yet. In this work, we revisit the generative framework for information retrieval and show that our generative approaches are as effective as state-of-the-art semantic similarity-based discriminative models for the answer selection task. Additionally, we demonstrate the effectiveness of unlikelihood losses for IR.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nogueira-dos-santos-etal-2020-beyond">
<titleInfo>
<title>Beyond [CLS] through Ranking by Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cicero</namePart>
<namePart type="family">Nogueira dos Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaofei</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramesh</namePart>
<namePart type="family">Nallapati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiheng</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Xiang</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>Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document’s language model, were very successful in various IR tasks in the past. However, with the advent of modern deep neural networks, attention has shifted to discriminative ranking functions that model the semantic similarity of documents and queries instead. Recently, deep generative models such as GPT2 and BART have been shown to be excellent text generators, but their effectiveness as rankers have not been demonstrated yet. In this work, we revisit the generative framework for information retrieval and show that our generative approaches are as effective as state-of-the-art semantic similarity-based discriminative models for the answer selection task. Additionally, we demonstrate the effectiveness of unlikelihood losses for IR.</abstract>
<identifier type="citekey">nogueira-dos-santos-etal-2020-beyond</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.134</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.134</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1722</start>
<end>1727</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond [CLS] through Ranking by Generation
%A Nogueira dos Santos, Cicero
%A Ma, Xiaofei
%A Nallapati, Ramesh
%A Huang, Zhiheng
%A Xiang, Bing
%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 nogueira-dos-santos-etal-2020-beyond
%X Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document’s language model, were very successful in various IR tasks in the past. However, with the advent of modern deep neural networks, attention has shifted to discriminative ranking functions that model the semantic similarity of documents and queries instead. Recently, deep generative models such as GPT2 and BART have been shown to be excellent text generators, but their effectiveness as rankers have not been demonstrated yet. In this work, we revisit the generative framework for information retrieval and show that our generative approaches are as effective as state-of-the-art semantic similarity-based discriminative models for the answer selection task. Additionally, we demonstrate the effectiveness of unlikelihood losses for IR.
%R 10.18653/v1/2020.emnlp-main.134
%U https://aclanthology.org/2020.emnlp-main.134
%U https://doi.org/10.18653/v1/2020.emnlp-main.134
%P 1722-1727
Markdown (Informal)
[Beyond [CLS] through Ranking by Generation](https://aclanthology.org/2020.emnlp-main.134) (Nogueira dos Santos et al., EMNLP 2020)
ACL
- Cicero Nogueira dos Santos, Xiaofei Ma, Ramesh Nallapati, Zhiheng Huang, and Bing Xiang. 2020. Beyond [CLS] through Ranking by Generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1722–1727, Online. Association for Computational Linguistics.