Enhancing Interpretable Clauses Semantically using Pretrained Word Representation
Rohan Kumar Yadav, Lei Jiao, Ole-Christoffer Granmo, Morten Goodwin
Abstract
Tsetlin Machine (TM) is an interpretable pattern recognition algorithm based on propositional logic, which has demonstrated competitive performance in many Natural Language Processing (NLP) tasks, including sentiment analysis, text classification, and Word Sense Disambiguation. To obtain human-level interpretability, legacy TM employs Boolean input features such as bag-of-words (BOW). However, the BOW representation makes it difficult to use any pre-trained information, for instance, word2vec and GloVe word representations. This restriction has constrained the performance of TM compared to deep neural networks (DNNs) in NLP. To reduce the performance gap, in this paper, we propose a novel way of using pre-trained word representations for TM. The approach significantly enhances the performance and interpretability of TM. We achieve this by extracting semantically related words from pre-trained word representations as input features to the TM. Our experiments show that the accuracy of the proposed approach is significantly higher than the previous BOW-based TM, reaching the level of DNN-based models.- Anthology ID:
- 2021.blackboxnlp-1.19
- Volume:
- Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Jasmijn Bastings, Yonatan Belinkov, Emmanuel Dupoux, Mario Giulianelli, Dieuwke Hupkes, Yuval Pinter, Hassan Sajjad
- Venue:
- BlackboxNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 265–274
- Language:
- URL:
- https://aclanthology.org/2021.blackboxnlp-1.19
- DOI:
- 10.18653/v1/2021.blackboxnlp-1.19
- Cite (ACL):
- Rohan Kumar Yadav, Lei Jiao, Ole-Christoffer Granmo, and Morten Goodwin. 2021. Enhancing Interpretable Clauses Semantically using Pretrained Word Representation. In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 265–274, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Enhancing Interpretable Clauses Semantically using Pretrained Word Representation (Yadav et al., BlackboxNLP 2021)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2021.blackboxnlp-1.19.pdf
- Code
- additional community code
- Data
- MR, Reuters-21578