SemEval-2016 Task 3: Community Question Answering

TL;DR

This paper presents the SemEval-2016 Task 3 on Community Question Answering, involving multiple subtasks in English and Arabic, with diverse approaches leading to significant performance improvements over baselines.

Contribution

It introduces a new shared task with multiple subtasks in community question answering for English and Arabic, and reports state-of-the-art results from participating systems.

Findings

Best systems achieved MAP scores of 79.19, 76.70, 55.41, and 45.83 for the four subtasks.

Participating systems used diverse approaches and features.

Systems significantly outperformed baseline scores.

Abstract

This paper describes the SemEval--2016 Task 3 on Community Question Answering, which we offered in English and Arabic. For English, we had three subtasks: Question--Comment Similarity (subtask A), Question--Question Similarity (B), and Question--External Comment Similarity (C). For Arabic, we had another subtask: Rerank the correct answers for a new question (D). Eighteen teams participated in the task, submitting a total of 95 runs (38 primary and 57 contrastive) for the four subtasks. A variety of approaches and features were used by the participating systems to address the different subtasks, which are summarized in this paper. The best systems achieved an official score (MAP) of 79.19, 76.70, 55.41, and 45.83 in subtasks A, B, C, and D, respectively. These scores are significantly better than those for the baselines that we provided. For subtask A, the best system improved over the 2015 winner by 3 points absolute in terms of Accuracy.