Abstract
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.
| Original language | English |
|---|---|
| Title of host publication | SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 836-843 |
| Number of pages | 8 |
| ISBN (Electronic) | 9781941643952 |
| Publication status | Published - 1 Jan 2016 |
| Event | 10th International Workshop on Semantic Evaluation, SemEval 2016 - San Diego, United States Duration: 16 Jun 2016 → 17 Jun 2016 |
Other
| Other | 10th International Workshop on Semantic Evaluation, SemEval 2016 |
|---|---|
| Country | United States |
| City | San Diego |
| Period | 16/6/16 → 17/6/16 |
Fingerprint
ASJC Scopus subject areas
- Theoretical Computer Science
- Computational Theory and Mathematics
- Computer Science Applications
Cite this
SUper team at SemEval-2016 task 3 : Building a feature-rich system for community question answering. / Mihaylova, Tsvetomila; Gencheva, Pepa; Boyanov, Martin; Yovcheva, Ivana; Mihaylov, Todor; Hardalov, Momchil; Kiprov, Yasen; Balchev, Daniel; Koychev, Ivan; Nakov, Preslav; Nikolova, Ivelina; Angelova, Galia.
SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings. Association for Computational Linguistics (ACL), 2016. p. 836-843.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - SUper team at SemEval-2016 task 3
T2 - Building a feature-rich system for community question answering
AU - Mihaylova, Tsvetomila
AU - Gencheva, Pepa
AU - Boyanov, Martin
AU - Yovcheva, Ivana
AU - Mihaylov, Todor
AU - Hardalov, Momchil
AU - Kiprov, Yasen
AU - Balchev, Daniel
AU - Koychev, Ivan
AU - Nakov, Preslav
AU - Nikolova, Ivelina
AU - Angelova, Galia
PY - 2016/1/1
Y1 - 2016/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85021698110&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85021698110&partnerID=8YFLogxK
M3 - Conference contribution
SP - 836
EP - 843
BT - SemEval 2016 - 10th International Workshop on Semantic Evaluation, Proceedings
PB - Association for Computational Linguistics (ACL)
ER -