A Study of Latent Structured Prediction Approaches to Passage Reranking

Iryna Haponchyk, Alessandro Moschitti


Abstract
The structured output framework provides a helpful tool for learning to rank problems. In this paper, we propose a structured output approach which regards rankings as latent variables. Our approach addresses the complex optimization of Mean Average Precision (MAP) ranking metric. We provide an inference procedure to find the max-violating ranking based on the decomposition of the corresponding loss. The results of our experiments on WikiQA and TREC13 datasets show that our reranking based on structured prediction is a promising research direction.
Anthology ID:
N19-1183
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1847–1857
Language:
URL:
https://aclanthology.org/N19-1183
DOI:
10.18653/v1/N19-1183
Bibkey:
Cite (ACL):
Iryna Haponchyk and Alessandro Moschitti. 2019. A Study of Latent Structured Prediction Approaches to Passage Reranking. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1847–1857, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
A Study of Latent Structured Prediction Approaches to Passage Reranking (Haponchyk & Moschitti, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1183.pdf
Data
WikiQA