# SUper Team at SemEval-2016 Task 3: Building a feature-rich system for community question answering

arXiv: https://arxiv.org/abs/2109.15120 · HTML: https://mlsanity.com/paper/2109.15120/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 36 references that are in the map.
- First posted on arXiv 26 Sep 2021.

## Builds on (most cited first, 7 of 7)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Pairwise Neural Machine Translation Evaluation](https://mlsanity.com/paper/1912.03135/) (2019)
- [SemEval-2015 Task 3: Answer Selection in Community Question Answering](https://mlsanity.com/paper/1911.11403/) (2019)
- [Hunting for Troll Comments in News Community Forums](https://mlsanity.com/paper/1911.08113/) (2019)
- [Global Thread-Level Inference for Comment Classification in Community Question Answering](https://mlsanity.com/paper/1911.08755/) (2019)
- [SemanticZ at SemEval-2016 Task 3: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings](https://mlsanity.com/paper/1911.08743/) (2019)
- [Machine Translation Evaluation Meets Community Question Answering](https://mlsanity.com/paper/1912.02998/) (2019)

## Abstract (arXiv)

We present the system we built for participating in SemEval-2016 Task 3 on Community Question Answering. We achieved the best results on subtask C, and strong results on subtasks A and B, by combining a rich set of various types of features: semantic, lexical, metadata, and user-related. The most important group turned out to be the metadata for the question and for the comment, semantic vectors trained on QatarLiving data and similarities between the question and the comment for subtasks A and C, and between the original and the related question for Subtask B.