Recent neural network approaches to sentence matching compute the probability of two sentences being similar by minimizing a logistic loss. In this paper, we learn sentence representations by means of a siamese network, which: (i) uses encoders that share parameters; and (ii) enables the comparison between two sentences in terms of their euclidean distance, by minimizing a contrastive loss. Moreover, we add a multilayer perceptron in the architecture to simultaneously optimize the contrastive and the logistic losses. This way, our network can exploit a more informative feedback, given by the logistic loss, which is also quantified by the distance that the two sentences have according to their representation in the euclidean space. We show that jointly minimizing the two losses yields higher accuracy than minimizing them independently. We verify this finding by evaluating several baseline architectures in two sentence matching tasks: question paraphrasing and textual entailment recognition. Our network approaches the state of the art, while being much simpler and faster to train, and with less parameters than its competitors.

Accurate Sentence Matching with Hybrid Siamese Networks / Nicosia, Massimo; Moschitti, Alessandro. - ELETTRONICO. - (2017), pp. 2235-2238. [10.1145/3132847.3133156]

Accurate Sentence Matching with Hybrid Siamese Networks

massimo nicosia;alessandro moschitti
2017-01-01

Abstract

Recent neural network approaches to sentence matching compute the probability of two sentences being similar by minimizing a logistic loss. In this paper, we learn sentence representations by means of a siamese network, which: (i) uses encoders that share parameters; and (ii) enables the comparison between two sentences in terms of their euclidean distance, by minimizing a contrastive loss. Moreover, we add a multilayer perceptron in the architecture to simultaneously optimize the contrastive and the logistic losses. This way, our network can exploit a more informative feedback, given by the logistic loss, which is also quantified by the distance that the two sentences have according to their representation in the euclidean space. We show that jointly minimizing the two losses yields higher accuracy than minimizing them independently. We verify this finding by evaluating several baseline architectures in two sentence matching tasks: question paraphrasing and textual entailment recognition. Our network approaches the state of the art, while being much simpler and faster to train, and with less parameters than its competitors.
2017
Massimo Nicosia and Alessandro Moschitti
Proceedings of the 2017 ACM on Conference on Information and Knowledge Management
New York NY, USA
ACM Digital Library
978-1-4503-4918-5
Nicosia, Massimo; Moschitti, Alessandro
Accurate Sentence Matching with Hybrid Siamese Networks / Nicosia, Massimo; Moschitti, Alessandro. - ELETTRONICO. - (2017), pp. 2235-2238. [10.1145/3132847.3133156]
File in questo prodotto:
File Dimensione Formato  
2017_CIKM_Moschitti_Siamese.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 537.24 kB
Formato Adobe PDF
537.24 kB Adobe PDF Visualizza/Apri
3132847.3133156.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 992.5 kB
Formato Adobe PDF
992.5 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/195318
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 13
social impact