English

SemanticZ at SemEval-2016 Task 3: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings

Computation and Language 2019-11-21 v1 Artificial Intelligence Information Retrieval

Abstract

We describe our system for finding good answers in a community forum, as defined in SemEval-2016, Task 3 on Community Question Answering. Our approach relies on several semantic similarity features based on fine-tuned word embeddings and topics similarities. In the main Subtask C, our primary submission was ranked third, with a MAP of 51.68 and accuracy of 69.94. In Subtask A, our primary submission was also third, with MAP of 77.58 and accuracy of 73.39.

Keywords

Cite

@article{arxiv.1911.08743,
  title  = {SemanticZ at SemEval-2016 Task 3: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings},
  author = {Todor Mihaylov and Preslav Nakov},
  journal= {arXiv preprint arXiv:1911.08743},
  year   = {2019}
}

Comments

community question answering, semantic similarity