Abstract
In this paper, we propose a new few-shot text classification method. Compared with supervised learning methods which require a large corpus of labeled documents, our method aims to make it possible to classify unlabeled text with few labeled data. To achieve this goal, we take advantage of advanced pre-trained language model to extract the semantic features of each document. Furthermore, we utilize an edge-labeling graph neural network to implicitly models the intra-cluster similarity and the inter-cluster dissimilarity of the documents. Finally, we take the results of the graph neural network as the input of a prototypical network to classify the unlabeled texts. We verify the effectiveness of our method on a sentiment analysis dataset and a relation classification dataset and achieve the state-of-the-art performance on both tasks.- Anthology ID:
- 2020.coling-main.485
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 5547–5552
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.485
- DOI:
- 10.18653/v1/2020.coling-main.485
- Cite (ACL):
- Chen Lyu, Weijie Liu, and Ping Wang. 2020. Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5547–5552, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network (Lyu et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.485.pdf