First Steps in Recognizing Relational Entailment – Experimental
Corpus and Baselines

D 2019

First Steps in Recognizing Relational Entailment – Experimental Corpus and Baselines

VÍTA, Martin and Jakub KLÍMEK

Basic information

Original name

First Steps in Recognizing Relational Entailment – Experimental Corpus and Baselines

Authors

VÍTA, Martin (203 Czech Republic, belonging to the institution) and Jakub KLÍMEK

Edition

Poznań, Human Language Technologies as a Challenge for Computer Science and Linguistics – 2019, p. 143-147, 5 pp. 2019

Publisher

Wydawnictwo Nauka i Innowacje

Other information

Language

English

Type of outcome

Proceedings paper

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Poland

Confidentiality degree

is not subject to a state or trade secret

Publication form

printed version "print"

RIV identification code

RIV/00216224:14330/19:00110583

Organization unit

Faculty of Informatics

ISBN

978-83-65988-31-7

Keywords in English

NLI; relational entailment; textual entailment; annotated corpus

Abstract

V originále

Recently, a task of recognizing relational entailment (RRE) was introduced as a task to decide whether the meaning of a given textual $n$-tuple $t$, i. e., the semantic relationship expressed by $t$, can be inferred from a given text $T$. Since then-tuples are obtained from theopen information extraction process, this task naturally connects two NLP fields: natural language inference (NLI) and open information extraction (open IE). The task has a “practical” counterpart: checking/proving facts stored in open knowledge bases. However, no corresponding annotated corpus has been available yet as well as baselines for this task. In this paper, we present a corpus derived fromthe well known SNLI corpus and provide baselines based on LSTM architectures and state also a baseline using “hypothesis-only”-like approach.

Links

MUNI/A/1018/2018, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VIII.

Investor: Masaryk University, Category A

Citovat

VÍTA, Martin and Jakub KLÍMEK. First Steps in Recognizing Relational Entailment – Experimental Corpus and Baselines. In Zygmunt Vetulani, Patrick Paroubek. Human Language Technologies as a Challenge for Computer Science and Linguistics – 2019. Poznań: Wydawnictwo Nauka i Innowacje, 2019, p. 143-147. ISBN 978-83-65988-31-7.

@inproceedings{1552597,
   author = {Víta, Martin and Klímek, Jakub},
   address = {Poznań},
   booktitle = {Human Language Technologies as a Challenge for Computer Science and Linguistics – 2019},
   editor = {Zygmunt Vetulani, Patrick Paroubek},
   keywords = {NLI; relational entailment; textual entailment; annotated corpus},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Poznań},
   isbn = {978-83-65988-31-7},
   pages = {143-147},
   publisher = {Wydawnictwo Nauka i Innowacje},
   title = {First Steps in Recognizing Relational Entailment – Experimental Corpus and Baselines},
   year = {2019}
}

TY  - CONF
ID  - 1552597
AU  - Víta, Martin - Klímek, Jakub
PY  - 2019
TI  - First Steps in Recognizing Relational Entailment – Experimental Corpus and Baselines
PB  - Wydawnictwo Nauka i Innowacje
CY  - Poznań
SN  - 9788365988317
KW  - NLI
KW  - relational entailment
KW  - textual entailment
KW  - annotated corpus
N2  - Recently, a task of recognizing relational entailment (RRE) was introduced as a task to decide whether the meaning of a given textual $n$-tuple $t$, i. e., the semantic relationship expressed by $t$, can be inferred from a given text $T$. Since then-tuples are obtained from theopen information extraction process, this task naturally connects two NLP fields: natural language inference (NLI) and open information extraction (open IE). The task has a “practical” counterpart: checking/proving facts stored in open knowledge bases. However, no corresponding annotated corpus has been available yet as well as baselines for this task. In this paper, we present a corpus derived fromthe well known SNLI corpus and provide baselines based on LSTM architectures and state also a baseline using “hypothesis-only”-like approach.
ER  -

VÍTA, Martin and Jakub KLÍMEK. First Steps in Recognizing Relational Entailment – Experimental Corpus and Baselines. In Zygmunt Vetulani, Patrick Paroubek. \textit{Human Language Technologies as a Challenge for Computer Science and Linguistics – 2019}. Pozna\'n: Wydawnictwo Nauka i Innowacje, 2019, p.~143-147. ISBN~978-83-65988-31-7.

Přehled o publikaci