Multi-Granular Text Encoding for Self-Explaining Categorization

Zhiguo Wang, Yue Zhang, Mo Yu, Wei Zhang, Lin Pan, Linfeng Song, Kun Xu, Yousef El-Kurdi


Abstract
Self-explaining text categorization requires a classifier to make a prediction along with supporting evidence. A popular type of evidence is sub-sequences extracted from the input text which are sufficient for the classifier to make the prediction. In this work, we define multi-granular ngrams as basic units for explanation, and organize all ngrams into a hierarchical structure, so that shorter ngrams can be reused while computing longer ngrams. We leverage the tree-structured LSTM to learn a context-independent representation for each unit via parameter sharing. Experiments on medical disease classification show that our model is more accurate, efficient and compact than the BiLSTM and CNN baselines. More importantly, our model can extract intuitive multi-granular evidence to support its predictions.
Anthology ID:
W19-4805
Volume:
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Tal Linzen, Grzegorz Chrupała, Yonatan Belinkov, Dieuwke Hupkes
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
41–45
Language:
URL:
https://aclanthology.org/W19-4805
DOI:
10.18653/v1/W19-4805
Bibkey:
Cite (ACL):
Zhiguo Wang, Yue Zhang, Mo Yu, Wei Zhang, Lin Pan, Linfeng Song, Kun Xu, and Yousef El-Kurdi. 2019. Multi-Granular Text Encoding for Self-Explaining Categorization. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 41–45, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Multi-Granular Text Encoding for Self-Explaining Categorization (Wang et al., BlackboxNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4805.pdf