INESC-ID@ASSIN: Medição de Similaridade Semântica e Reconhecimento de Inferência Textual

Pedro Fialho, Ricardo Marques, Bruno Martins, Luísa Coheur, Paulo Quaresma

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

In this article we present INESC-ID@ASSIN, a system that competed in the 2016 joint evaluation effort entitled Avaliação de Similaridade Semântica e Inferência Textual (ASSIN), in the tasks of semantic similarity and textual entailment recognition. INESC-ID@ASSIN addresses the problem of detecting sentence similarity as a regression task, and it addresses textual entailment as a classification task. Although INESC-ID@ASSIN relies mainly on simple lexical features for detecting paraphrases and recognizing textual entailment, promising results were achieved in this joint evaluation.
Original languageMultiple
Pages (from-to)33-42
JournalLinguamatica
Volume8
Issue number2
Publication statusPublished - 1 Nov 2016
Externally publishedYes

Fingerprint

Entailment
Evaluation
Semantic Similarity
Paraphrase

Keywords

  • aprendizagem supervisionada
  • regressão
  • classificação

Cite this

Fialho, P., Marques, R., Martins, B., Coheur, L., & Quaresma, P. (2016). INESC-ID@ASSIN: Medição de Similaridade Semântica e Reconhecimento de Inferência Textual. Linguamatica, 8(2), 33-42.
Fialho, Pedro ; Marques, Ricardo ; Martins, Bruno ; Coheur, Luísa ; Quaresma, Paulo. / INESC-ID@ASSIN: Medição de Similaridade Semântica e Reconhecimento de Inferência Textual. In: Linguamatica. 2016 ; Vol. 8, No. 2. pp. 33-42.
@article{cd7fe88137e047b894c28a645ac6cb2b,
title = "INESC-ID@ASSIN: Medi{\cc}{\~a}o de Similaridade Sem{\^a}ntica e Reconhecimento de Infer{\^e}ncia Textual",
abstract = "In this article we present INESC-ID@ASSIN, a system that competed in the 2016 joint evaluation effort entitled Avalia{\cc}{\~a}o de Similaridade Sem{\^a}ntica e Infer{\^e}ncia Textual (ASSIN), in the tasks of semantic similarity and textual entailment recognition. INESC-ID@ASSIN addresses the problem of detecting sentence similarity as a regression task, and it addresses textual entailment as a classification task. Although INESC-ID@ASSIN relies mainly on simple lexical features for detecting paraphrases and recognizing textual entailment, promising results were achieved in this joint evaluation.",
keywords = "aprendizagem supervisionada, regress{\~a}o, classifica{\cc}{\~a}o",
author = "Pedro Fialho and Ricardo Marques and Bruno Martins and Lu{\'i}sa Coheur and Paulo Quaresma",
year = "2016",
month = "11",
day = "1",
language = "Multiple",
volume = "8",
pages = "33--42",
journal = "Linguamatica",
issn = "1647-0818",
publisher = "Universidade do Minho",
number = "2",

}

Fialho, P, Marques, R, Martins, B, Coheur, L & Quaresma, P 2016, 'INESC-ID@ASSIN: Medição de Similaridade Semântica e Reconhecimento de Inferência Textual', Linguamatica, vol. 8, no. 2, pp. 33-42.

INESC-ID@ASSIN: Medição de Similaridade Semântica e Reconhecimento de Inferência Textual. / Fialho, Pedro; Marques, Ricardo; Martins, Bruno; Coheur, Luísa; Quaresma, Paulo.

In: Linguamatica, Vol. 8, No. 2, 01.11.2016, p. 33-42.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - INESC-ID@ASSIN: Medição de Similaridade Semântica e Reconhecimento de Inferência Textual

AU - Fialho, Pedro

AU - Marques, Ricardo

AU - Martins, Bruno

AU - Coheur, Luísa

AU - Quaresma, Paulo

PY - 2016/11/1

Y1 - 2016/11/1

N2 - In this article we present INESC-ID@ASSIN, a system that competed in the 2016 joint evaluation effort entitled Avaliação de Similaridade Semântica e Inferência Textual (ASSIN), in the tasks of semantic similarity and textual entailment recognition. INESC-ID@ASSIN addresses the problem of detecting sentence similarity as a regression task, and it addresses textual entailment as a classification task. Although INESC-ID@ASSIN relies mainly on simple lexical features for detecting paraphrases and recognizing textual entailment, promising results were achieved in this joint evaluation.

AB - In this article we present INESC-ID@ASSIN, a system that competed in the 2016 joint evaluation effort entitled Avaliação de Similaridade Semântica e Inferência Textual (ASSIN), in the tasks of semantic similarity and textual entailment recognition. INESC-ID@ASSIN addresses the problem of detecting sentence similarity as a regression task, and it addresses textual entailment as a classification task. Although INESC-ID@ASSIN relies mainly on simple lexical features for detecting paraphrases and recognizing textual entailment, promising results were achieved in this joint evaluation.

KW - aprendizagem supervisionada

KW - regressão

KW - classificação

M3 - Article

VL - 8

SP - 33

EP - 42

JO - Linguamatica

JF - Linguamatica

SN - 1647-0818

IS - 2

ER -

Fialho P, Marques R, Martins B, Coheur L, Quaresma P. INESC-ID@ASSIN: Medição de Similaridade Semântica e Reconhecimento de Inferência Textual. Linguamatica. 2016 Nov 1;8(2):33-42.