Abstract
The automation of tasks in community question answering (cQA) is dominated by machine learning approaches, whose performance is often limited by the number of training examples. Starting from a neural sequence learning approach with attention, we explore the impact of two data augmentation techniques on question ranking performance: a method that swaps reference questions with their paraphrases, and training on examples automatically selected from external datasets. Both methods are shown to lead to substantial gains in accuracy over a strong baseline. Further improvements are obtained by changing the model architecture to mirror the structure seen in the data.- Anthology ID:
- I17-2075
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 442–447
- Language:
- URL:
- https://aclanthology.org/I17-2075
- DOI:
- Cite (ACL):
- Charles Chen and Razvan Bunescu. 2017. An Exploration of Data Augmentation and RNN Architectures for Question Ranking in Community Question Answering. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 442–447, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- An Exploration of Data Augmentation and RNN Architectures for Question Ranking in Community Question Answering (Chen & Bunescu, IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/I17-2075.pdf