Zoho at SemEval-2019 Task 9: Semi-supervised Domain Adaptation using Tri-training for Suggestion Mining

Sai Prasanna, Sri Ananda Seelan


Abstract
This paper describes our submission for the SemEval-2019 Suggestion Mining task. A simple Convolutional Neural Network (CNN) classifier with contextual word representations from a pre-trained language model was used for sentence classification. The model is trained using tri-training, a semi-supervised bootstrapping mechanism for labelling unseen data. Tri-training proved to be an effective technique to accommodate domain shift for cross-domain suggestion mining (Subtask B) where there is no hand labelled training data. For in-domain evaluation (Subtask A), we use the same technique to augment the training set. Our system ranks thirteenth in Subtask A with an F1-score of 68.07 and third in Subtask B with an F1-score of 81.94.
Anthology ID:
S19-2225
Volume:
Proceedings of the 13th International Workshop on Semantic Evaluation
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota, USA
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1282–1286
Language:
URL:
https://aclanthology.org/S19-2225
DOI:
10.18653/v1/S19-2225
Bibkey:
Cite (ACL):
Sai Prasanna and Sri Ananda Seelan. 2019. Zoho at SemEval-2019 Task 9: Semi-supervised Domain Adaptation using Tri-training for Suggestion Mining. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 1282–1286, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
Cite (Informal):
Zoho at SemEval-2019 Task 9: Semi-supervised Domain Adaptation using Tri-training for Suggestion Mining (Prasanna & Seelan, SemEval 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/S19-2225.pdf
Software:
 S19-2225.Software.zip
Poster:
 S19-2225.Poster.pdf