Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions

13 September 2021

Papers citing "Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions"

8 / 8 papers shown

Title
Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers Tobias Leemann Alina Fastowski Felix Pfeiffer Gjergji Kasneci 62 4 0 10 Jan 2025
Non-Fluent Synthetic Target-Language Data Improve Neural Machine Translation Víctor M. Sánchez-Cartagena Miquel Espla-Gomis J. A. Pérez-Ortiz F. Sánchez-Martínez 35 4 0 29 Jan 2024
Predicting Human Translation Difficulty with Neural Machine Translation Zheng Wei Lim Ekaterina Vylomova Charles Kemp Trevor Cohn 32 0 0 19 Dec 2023
Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation Nuno M. Guerreiro Pierre Colombo Pablo Piantanida André F.T. Martins 30 10 0 19 Dec 2022
Word Alignment in the Era of Deep Learning: A Tutorial Bryan Li 31 5 0 30 Nov 2022
Towards Faithful Model Explanation in NLP: A Survey Qing Lyu Marianna Apidianaki Chris Callison-Burch XAI 114 107 0 22 Sep 2022
SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features Juri Opitz Anette Frank 34 33 0 14 Jun 2022
Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer Javier Ferrando Gerard I. Gállego Belen Alastruey Carlos Escolano Marta R. Costa-jussá 30 44 0 23 May 2022