Description Based Text Classification with Reinforcement Learning

By Duo Chai, Wei Wu, Qinghong Han, Fei Wu, Jiwei Li. 2020

71 citations recorded by the source corpus.

The task of text classification is usually divided into two stages: {\it text feature extraction} and {\it classification}. In this standard formalization categories are merely represented as indexes in the label vocabulary, and the model lacks for explicit instructions on what to classify. Inspired by the current trend of formalizing NLP problems as question answering tasks, we propose a new framework for text classification, in which each category label is associated with a category description. Descriptions are generated by hand-crafted templates or using abstractive/extractive models from reinforcement learning. The concatenation of the description and the text is fed to the classifier to decide whether or not the current label should be assigned to the text. The proposed strategy forces the model to attend to the most salient texts with respect to the label, which can be regarded as a hard version of attention, leading to better performances. We observe significant performance boosts over strong baselines on a wide range of text classification tasks including single-label classification, multi-label classification and multi-aspect sentiment analysis.

Subfields: Artificial Intelligence, Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Luke S. Zettlemoyer
2. Mohit Bansal
3. Quoc V. Le
4. Percy Liang
5. Jianfeng Gao
6. Graham Neubig
7. Hannaneh Hajishirzi
8. Kyunghyun Cho

In Natural Language Processing

1. Jiwei Li
2. Mohit Bansal
3. Andrew M. Dai
4. Quoc V. Le
5. Jason Wei
6. Kyunghyun Cho
7. Kelvin Guu
8. Adams Wei Yu

In Reinforcement Learning

1. Jason Wei
2. Fei Wu
3. Kelvin Guu
4. Jiwei Li
5. Andrew M. Dai
6. Quoc V. Le
7. Adams Wei Yu
8. Qinghong Han

Citations in the corpus

• Finetuned Language Models Are Zero-Shot Learners (2021, methodology): “Moreover, our work supercedes recent work such as Chai et al. (2020) and Zhong et al. (2021) in terms of both model scale and scope of tasks.”
• BertGCN: Transductive Text Classification by Combining GNN and BERT (2021, background): “Different neural model architectures (Kim, 2014; Zhou et al., 2015; Radford et al., 2018; Chai et al., 2020) have demonstrated their effectiveness against traditional statistical feature based methods (Wallach, 2006).”