Abstract
Recent advancements in natural language processing (NLP) have reshaped the industry, with powerful language models such as GPT-3 achieving superhuman performance on various tasks. However, the increasing complexity of such models turns them into “black boxes”, creating uncertainty about their internal operation and decision-making. Tsetlin Machine (TM) employs human-interpretable conjunctive clauses in propositional logic to solve complex pattern recognition problems and has demonstrated competitive performance in various NLP tasks. In this paper, we propose ConvTextTM, a novel convolutional TM architecture for text classification. While legacy TM solutions treat the whole text as a corpus-specific set-of-words (SOW), ConvTextTM breaks down the text into a sequence of text fragments. The convolution over the text fragments opens up for local position-aware analysis. Further, ConvTextTM eliminates the dependency on a corpus-specific vocabulary. Instead, it employs a generic SOW formed by the tokenization scheme of the Bidirectional Encoder Representations from Transformers (BERT). The convolution binds together the tokens, allowing ConvTextTM to address the out-of-vocabulary problem as well as spelling errors. We investigate the local explainability of our proposed method using clause-based features. Extensive experiments are conducted on seven datasets, to demonstrate that the accuracy of ConvTextTM is either superior or comparable to state-of-the-art baselines.- Anthology ID:
- 2022.lrec-1.401
- Volume:
- Proceedings of the Thirteenth Language Resources and Evaluation Conference
- Month:
- June
- Year:
- 2022
- Address:
- Marseille, France
- Editors:
- Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association
- Note:
- Pages:
- 3761–3770
- Language:
- URL:
- https://aclanthology.org/2022.lrec-1.401
- DOI:
- Cite (ACL):
- Bimal Bhattarai, Ole-Christoffer Granmo, and Lei Jiao. 2022. ConvTextTM: An Explainable Convolutional Tsetlin Machine Framework for Text Classification. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 3761–3770, Marseille, France. European Language Resources Association.
- Cite (Informal):
- ConvTextTM: An Explainable Convolutional Tsetlin Machine Framework for Text Classification (Bhattarai et al., LREC 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2022.lrec-1.401.pdf
- Data
- PolitiFact, WOS