@inproceedings{lovon-melgarejo-etal-2022-guide,
title = "Can We Guide a Multi-Hop Reasoning Language Model to Incrementally Learn at Each Single-Hop?",
author = "Lovon-Melgarejo, Jesus and
Moreno, Jose G. and
Besan{\c{c}}on, Romaric and
Ferret, Olivier and
Tamine, Lynda",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.125/",
pages = "1455--1466",
abstract = "Despite the success of state-of-the-art pre-trained language models (PLMs) on a series of multi-hop reasoning tasks, they still suffer from their limited abilities to transfer learning from simple to complex tasks and vice-versa. We argue that one step forward to overcome this limitation is to better understand the behavioral trend of PLMs at each hop over the inference chain. Our critical underlying idea is to mimic human-style reasoning: we envision the multi-hop reasoning process as a sequence of explicit single-hop reasoning steps. To endow PLMs with incremental reasoning skills, we propose a set of inference strategies on relevant facts and distractors allowing us to build automatically generated training datasets. Using the SHINRA and ConceptNet resources jointly, we empirically show the effectiveness of our proposal on multiple-choice question answering and reading comprehension, with a relative improvement in terms of accuracy of 68.4{\%} and 16.0{\%} w.r.t. classic PLMs, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lovon-melgarejo-etal-2022-guide">
<titleInfo>
<title>Can We Guide a Multi-Hop Reasoning Language Model to Incrementally Learn at Each Single-Hop?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jesus</namePart>
<namePart type="family">Lovon-Melgarejo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Romaric</namePart>
<namePart type="family">Besançon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Ferret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lynda</namePart>
<namePart type="family">Tamine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the success of state-of-the-art pre-trained language models (PLMs) on a series of multi-hop reasoning tasks, they still suffer from their limited abilities to transfer learning from simple to complex tasks and vice-versa. We argue that one step forward to overcome this limitation is to better understand the behavioral trend of PLMs at each hop over the inference chain. Our critical underlying idea is to mimic human-style reasoning: we envision the multi-hop reasoning process as a sequence of explicit single-hop reasoning steps. To endow PLMs with incremental reasoning skills, we propose a set of inference strategies on relevant facts and distractors allowing us to build automatically generated training datasets. Using the SHINRA and ConceptNet resources jointly, we empirically show the effectiveness of our proposal on multiple-choice question answering and reading comprehension, with a relative improvement in terms of accuracy of 68.4% and 16.0% w.r.t. classic PLMs, respectively.</abstract>
<identifier type="citekey">lovon-melgarejo-etal-2022-guide</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.125/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>1455</start>
<end>1466</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can We Guide a Multi-Hop Reasoning Language Model to Incrementally Learn at Each Single-Hop?
%A Lovon-Melgarejo, Jesus
%A Moreno, Jose G.
%A Besançon, Romaric
%A Ferret, Olivier
%A Tamine, Lynda
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F lovon-melgarejo-etal-2022-guide
%X Despite the success of state-of-the-art pre-trained language models (PLMs) on a series of multi-hop reasoning tasks, they still suffer from their limited abilities to transfer learning from simple to complex tasks and vice-versa. We argue that one step forward to overcome this limitation is to better understand the behavioral trend of PLMs at each hop over the inference chain. Our critical underlying idea is to mimic human-style reasoning: we envision the multi-hop reasoning process as a sequence of explicit single-hop reasoning steps. To endow PLMs with incremental reasoning skills, we propose a set of inference strategies on relevant facts and distractors allowing us to build automatically generated training datasets. Using the SHINRA and ConceptNet resources jointly, we empirically show the effectiveness of our proposal on multiple-choice question answering and reading comprehension, with a relative improvement in terms of accuracy of 68.4% and 16.0% w.r.t. classic PLMs, respectively.
%U https://aclanthology.org/2022.coling-1.125/
%P 1455-1466
Markdown (Informal)
[Can We Guide a Multi-Hop Reasoning Language Model to Incrementally Learn at Each Single-Hop?](https://aclanthology.org/2022.coling-1.125/) (Lovon-Melgarejo et al., COLING 2022)
ACL