An important asset of using Deep Neu- ral Networks (DNNs) for text applica- tions is their ability to automatically engi- neer features. Unfortunately, DNNs usu- ally require a lot of training data, espe- cially for high-level semantic tasks such as community Question Answering (cQA). In this paper, we tackle the problem of data scarcity by learning the target DNN together with two auxiliary tasks in a mul- titask learning setting. We exploit the strong semantic connection between se- lection of comments relevant to (i) new questions and (ii) forum questions. This enables a global representation for com- ments, new and previous questions. The experiments of our model on a SemEval challenge dataset for cQA show a 20% rel- ative improvement over standard DNNs.

Effective shared representations with Multitask Learning for Community Question Answering / Bonadiman, Daniele; Uva, Antonio; Moschitti, Alessandro. - ELETTRONICO. - (2017), pp. 726-732. ((Intervento presentato al convegno EACL 2017 tenutosi a Valencia, Spain nel 3-7April , 2017 [10.18653/v1/e17-2115].

Effective shared representations with Multitask Learning for Community Question Answering

Daniele Bonadiman;Antonio Uva;Alessandro Moschitti
2017

Abstract

An important asset of using Deep Neu- ral Networks (DNNs) for text applica- tions is their ability to automatically engi- neer features. Unfortunately, DNNs usu- ally require a lot of training data, espe- cially for high-level semantic tasks such as community Question Answering (cQA). In this paper, we tackle the problem of data scarcity by learning the target DNN together with two auxiliary tasks in a mul- titask learning setting. We exploit the strong semantic connection between se- lection of comments relevant to (i) new questions and (ii) forum questions. This enables a global representation for com- ments, new and previous questions. The experiments of our model on a SemEval challenge dataset for cQA show a 20% rel- ative improvement over standard DNNs.
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, EACL 2017
Daniele Bonadiman, Antonio Uva, Alessandro Moschitti
USA
Association for Computational Linguistics (ACL)
978-1-945626-35-7
Bonadiman, Daniele; Uva, Antonio; Moschitti, Alessandro
Effective shared representations with Multitask Learning for Community Question Answering / Bonadiman, Daniele; Uva, Antonio; Moschitti, Alessandro. - ELETTRONICO. - (2017), pp. 726-732. ((Intervento presentato al convegno EACL 2017 tenutosi a Valencia, Spain nel 3-7April , 2017 [10.18653/v1/e17-2115].
File in questo prodotto:
File Dimensione Formato  
2017_EACL_Moschitti_Effective_Shared_Representations.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 195.23 kB
Formato Adobe PDF
195.23 kB Adobe PDF Visualizza/Apri
E17-2115.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 174.61 kB
Formato Adobe PDF
174.61 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: http://hdl.handle.net/11572/195343
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? ND
social impact