Recent work has shown that Tree Ker- nels (TKs) and Convolutional Neural Net- works (CNNs) obtain the state of the art in answer sentence reranking. Additionally, their combination used in Support Vec- tor Machines (SVMs) is promising as it can exploit both the syntactic patterns cap- tured by TKs and the embeddings learned by CNNs. However, the embeddings are constructed according to a classification function, which is not directly exploitable in the preference ranking algorithm of SVMs. In this work, we propose a new hy- brid approach combining preference rank- ing applied to TKs and pointwise rank- ing applied to CNNs. We show that our approach produces better results on two well-known and rather different datasets: WikiQA for answer sentence selection and SemEval cQA for comment selection in Community Question Answering.

Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model / Timoshenko, Kateryna; Bonadiman, Daniele; Moschitti, Alessandro. - ELETTRONICO. - (2017), pp. 897-902. ((Intervento presentato al convegno Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 tenutosi a Copenhagen, Denmark nel 9-11 September, 2017.

Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model

Daniele Bonadiman;Alessandro Moschitti
2017

Abstract

Recent work has shown that Tree Ker- nels (TKs) and Convolutional Neural Net- works (CNNs) obtain the state of the art in answer sentence reranking. Additionally, their combination used in Support Vec- tor Machines (SVMs) is promising as it can exploit both the syntactic patterns cap- tured by TKs and the embeddings learned by CNNs. However, the embeddings are constructed according to a classification function, which is not directly exploitable in the preference ranking algorithm of SVMs. In this work, we propose a new hy- brid approach combining preference rank- ing applied to TKs and pointwise rank- ing applied to CNNs. We show that our approach produces better results on two well-known and rather different datasets: WikiQA for answer sentence selection and SemEval cQA for comment selection in Community Question Answering.
Proceedings of the 2017 Conference on Empirical Methods in NaturalLanguage Processing, EMNLP 2017, Copenhagen, Denmark, September9-11, 2017
Copenhagen, Denmark
Association for Computational Linguistics (ACL)
978-1-945626-83-8
Timoshenko, Kateryna; Bonadiman, Daniele; Moschitti, Alessandro
Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model / Timoshenko, Kateryna; Bonadiman, Daniele; Moschitti, Alessandro. - ELETTRONICO. - (2017), pp. 897-902. ((Intervento presentato al convegno Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017 tenutosi a Copenhagen, Denmark nel 9-11 September, 2017.
File in questo prodotto:
File Dimensione Formato  
2017_EMNLP.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 296.24 kB
Formato Adobe PDF
296.24 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/11572/195322
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact