Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences

Eleftheria Briakou, Navita Goyal, Marine Carpuat


Abstract
Explainable NLP techniques primarily explain by answering “Which tokens in the input are responsible for this prediction?”. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by answering “What differences between the two inputs explain this prediction?”. We introduce a technique to generate contrastive phrasal highlights that explain the predictions of a semantic divergence model via phrase alignment guided erasure. We show that the resulting highlights match human rationales of cross-lingual semantic differences better than popular post-hoc saliency techniques and that they successfully help people detect fine-grained meaning differences in human translations and critical machine translation errors.
Anthology ID:
2023.emnlp-main.690
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11220–11237
Language:
URL:
https://aclanthology.org/2023.emnlp-main.690
DOI:
10.18653/v1/2023.emnlp-main.690
Bibkey:
Cite (ACL):
Eleftheria Briakou, Navita Goyal, and Marine Carpuat. 2023. Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11220–11237, Singapore. Association for Computational Linguistics.
Cite (Informal):
Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences (Briakou et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.690.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.690.mp4