Type

Conference Proceedings

Authors

Jennifer Foster
Dasha Bogdanova

Subjects

Linguistics

Topics
machine learning computational linguistics feature vectors state of the art domain engineering training questions

This is how we do it: Answer reranking for open-domain how questions with paragraph vectors and minimal feature engineering (2016)

Abstract We present a simple yet powerful approach to non-factoid answer reranking whereby question-answer pairs are represented by concatenated distributed representation vectors and a multilayer perceptron is used to compute the score for an answer. Despite its simplicity, our approach achieves state-of-the-art performance on a public dataset of How questions, outperforming systems which employ sophisticated feature sets. We attribute this good performance to the use of paragraph instead of word vector representations and to the use of suitable data for training these representations.
Collections Ireland -> Dublin City University -> Publication Type = Conference or Workshop Item
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing: School of Computing
Ireland -> Dublin City University -> Status = Published
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres: National Centre for Language Technology (NCLT)
Ireland -> Dublin City University -> Subject = Computer Science: Computational linguistics
Ireland -> Dublin City University -> Subject = Computer Science: Machine learning

Full list of authors on original publication

Jennifer Foster, Dasha Bogdanova

Experts in our system

1
Jennifer Foster
Dublin City University
Total Publications: 53