Abstract
Recently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods are crucial to understand their decisions. Occlusion is a well established method that provides explanations on discrete language data, e.g. by removing a language unit from an input and measuring the impact on a model’s decision. We argue that current occlusion-based methods often produce invalid or syntactically incorrect language data, neglecting the improved abilities of recent NLP models. Furthermore, gradient-based explanation methods disregard the discrete distribution of data in NLP. Thus, we propose OLM: a novel explanation method that combines occlusion and language models to sample valid and syntactically correct replacements with high likelihood, given the context of the original input. We lay out a theoretical foundation that alleviates these weaknesses of other explanation methods in NLP and provide results that underline the importance of considering data likelihood in occlusion-based explanation.- Anthology ID:
- 2020.acl-srw.16
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 111–117
- Language:
- URL:
- https://aclanthology.org/2020.acl-srw.16
- DOI:
- 10.18653/v1/2020.acl-srw.16
- Cite (ACL):
- David Harbecke and Christoph Alt. 2020. Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 111–117, Online. Association for Computational Linguistics.
- Cite (Informal):
- Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling (Harbecke & Alt, ACL 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.acl-srw.16.pdf
- Code
- DFKI-NLP/OLM
- Data
- CoLA, MultiNLI, SST