conftrace_

attention weight

68 papers

Explore in graph

Co-occurring keywords

attention mechanism (4001) neural network (6616) model interpretability (519) text classification (6793) large language model (13587) transformer model (1996) language model (4599) graph neural network (3962) retrieval-augmented generation (1592) feature attribution (280)

Papers

Zero-shot Sequence Labeling for Transformer-based Sentence Classifiers IJCNLP 2021
Does Chinese BERT Encode Word Structure? COLING 2020
Quantifying Attention Flow in Transformers ACL 2020
Structured Self-Attention Weights Encode Semantics in Sentiment Analysis EMNLP 2020
The elephant in the interpretability room: Why use attention as explanation when we have saliency methods? EMNLP 2020
Understanding Attention for Text Classification ACL 2020
Accurate Word Alignment Induction from Neural Machine Translation EMNLP 2020
On Model Stability as a Function of Random Seed CONLL 2019
Keeping Consistency of Sentence Generation and Document Classification with Multi-Task Learning EMNLP 2019
On the Importance of Delexicalization for Fact Verification IJCNLP 2019
Attention is not Explanation NAACL 2019
Fill the GAP: Exploiting BERT for Pronoun Resolution ACL 2019
On the Importance of Delexicalization for Fact Verification EMNLP 2019
Is Attention Interpretable? ACL 2019
Code Generation as a Dual Task of Code Summarization NIPS 2019
On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation EMNLP 2018
A Deep Network with Visual Text Composition Behavior ACL 2017
Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition NIPS 2016