This is how we do it: Answer reranking for open-domain how questions with paragraph vectors and minimal feature engineering
Bogdanova, Dasha and Foster, JenniferORCID: 0000-0002-7789-4853
(2016)
This is how we do it: Answer reranking for open-domain how questions with paragraph vectors and minimal feature engineering.
In: The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 16), 12-17 Jun 2016, San Diego, CA..
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.