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

Kateryna Tymoshenko, Daniele Bonadiman, Alessandro Moschitti


Abstract
Recent work has shown that Tree Kernels (TKs) and Convolutional Neural Networks (CNNs) obtain the state of the art in answer sentence reranking. Additionally, their combination used in Support Vector Machines (SVMs) is promising as it can exploit both the syntactic patterns captured 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 hybrid approach combining preference ranking applied to TKs and pointwise ranking 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.
Anthology ID:
D17-1093
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
897–902
Language:
URL:
https://aclanthology.org/D17-1093
DOI:
10.18653/v1/D17-1093
Bibkey:
Cite (ACL):
Kateryna Tymoshenko, Daniele Bonadiman, and Alessandro Moschitti. 2017. Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 897–902, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model (Tymoshenko et al., EMNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/D17-1093.pdf
Data
WikiQA