MS-Ranker: Accumulating Evidence from Potentially Correct Candidates for Answer Selection

by   Yingxue Zhang, et al.

As conventional answer selection (AS) methods generally match the question with each candidate answer independently, they suffer from the lack of matching information between the question and the candidate. To address this problem, we propose a novel reinforcement learning (RL) based multi-step ranking model, named MS-Ranker, which accumulates information from potentially correct candidate answers as extra evidence for matching the question with a candidate. In specific, we explicitly consider the potential correctness of candidates and update the evidence with a gating mechanism. Moreover, as we use a listwise ranking reward, our model learns to pay more attention to the overall performance. Experiments on two benchmarks, namely WikiQA and SemEval-2016 CQA, show that our model significantly outperforms existing methods that do not rely on external resources.


page 1

page 2

page 3

page 4


Graph-Based Tri-Attention Network for Answer Ranking in CQA

In community-based question answering (CQA) platforms, automatic answer ...

Attention-based Pairwise Multi-Perspective Convolutional Neural Network for Answer Selection in Question Answering

Over the past few years, question answering and information retrieval sy...

Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning

Most successful information extraction systems operate with access to a ...

Hierarchical Ranking for Answer Selection

Answer selection is a task to choose the positive answers from a pool of...

Double Retrieval and Ranking for Accurate Question Answering

Recent work has shown that an answer verification step introduced in Tra...

Lessons Learned Addressing Dataset Bias in Model-Based Candidate Generation at Twitter

Traditionally, heuristic methods are used to generate candidates for lar...

NPCs Vote! Changing Voter Reactions Over Time Using the Extreme AI Personality Engine

Can non-player characters have human-realistic personalities, changing o...