DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison

Christos Baziotis, Nikos Pelekis, Christos Doulkeridis


Abstract
In this paper we present a deep-learning system that competed at SemEval-2017 Task 6 "#HashtagWars: Learning a Sense of Humor”. We participated in Subtask A, in which the goal was, given two Twitter messages, to identify which one is funnier. We propose a Siamese architecture with bidirectional Long Short-Term Memory (LSTM) networks, augmented with an attention mechanism. Our system works on the token-level, leveraging word embeddings trained on a big collection of unlabeled Twitter messages. We ranked 2nd in 7 teams. A post-completion improvement of our model, achieves state-of-the-art results on #HashtagWars dataset.
Anthology ID:
S17-2065
Volume:
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Steven Bethard, Marine Carpuat, Marianna Apidianaki, Saif M. Mohammad, Daniel Cer, David Jurgens
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
390–395
Language:
URL:
https://aclanthology.org/S17-2065
DOI:
10.18653/v1/S17-2065
Bibkey:
Cite (ACL):
Christos Baziotis, Nikos Pelekis, and Christos Doulkeridis. 2017. DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 390–395, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison (Baziotis et al., SemEval 2017)
Copy Citation:
PDF:
https://aclanthology.org/S17-2065.pdf