The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?

12 October 2020

Papers citing "The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?"

43 / 93 papers shown

Title
Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation Nuno M. Guerreiro Elena Voita André F. T. Martins HILM 24 52 0 10 Aug 2022
Leveraging Explanations in Interactive Machine Learning: An Overview Stefano Teso Öznur Alkan Wolfgang Stammer Elizabeth M. Daly XAI FAtt LRM 26 62 0 29 Jul 2022
Cross-lingual AMR Aligner: Paying Attention to Cross-Attention Abelardo Carlos Martínez Lorenzo Pere-Lluís Huguet Cabot Roberto Navigli 30 4 0 15 Jun 2022
SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features Juri Opitz Anette Frank 34 33 0 14 Jun 2022
Comparison of attention models and post-hoc explanation methods for embryo stage identification: a case study T. Gomez Thomas Fréour Harold Mouchère 27 3 0 13 May 2022
A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing Michael Neely Stefan F. Schouten Maurits J. R. Bleeker Ana Lucic XAI 27 16 0 09 May 2022
GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers Ali Modarressi Mohsen Fayyaz Yadollah Yaghoobzadeh Mohammad Taher Pilehvar ViT 19 33 0 06 May 2022
Grad-SAM: Explaining Transformers via Gradient Self-Attention Maps Oren Barkan Edan Hauon Avi Caciularu Ori Katz Itzik Malkiel Omri Armstrong Noam Koenigstein 34 37 0 23 Apr 2022
A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference Kerem Zaman Yonatan Belinkov 26 8 0 11 Apr 2022
GPT-D: Inducing Dementia-related Linguistic Anomalies by Deliberate Degradation of Artificial Neural Language Models Changye Li D. Knopman Weizhe Xu T. Cohen Serguei V. S. Pakhomov 14 19 0 25 Mar 2022
A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification Dairui Liu Derek Greene Ruihai Dong 28 10 0 14 Mar 2022
Controlling the Focus of Pretrained Language Generation Models Jiabao Ji Yoon Kim James R. Glass Tianxing He 38 5 0 02 Mar 2022
Multi-Modal Knowledge Graph Construction and Application: A Survey Xiangru Zhu Zhixu Li Xiaodan Wang Xueyao Jiang Penglei Sun Xuwu Wang Yanghua Xiao N. Yuan 33 154 0 11 Feb 2022
UNIREX: A Unified Learning Framework for Language Model Rationale Extraction Aaron Chan Maziar Sanjabi Lambert Mathias L Tan Shaoliang Nie Xiaochang Peng Xiang Ren Hamed Firooz 41 41 0 16 Dec 2021
Rethinking the Authorship Verification Experimental Setups Florin Brad Andrei Manolache Elena Burceanu Antonio Bărbălău Radu Tudor Ionescu Marius Popescu 25 4 0 09 Dec 2021
CVSS-BERT: Explainable Natural Language Processing to Determine the Severity of a Computer Security Vulnerability from its Description Mustafizur R. Shahid Hervé Debar 9 42 0 16 Nov 2021
"Will You Find These Shortcuts?" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification Jasmijn Bastings Sebastian Ebert Polina Zablotskaia Anders Sandholm Katja Filippova 115 75 0 14 Nov 2021
Understanding How Encoder-Decoder Architectures Attend Kyle Aitken V. Ramasesh Yuan Cao Niru Maheswaranathan 34 17 0 28 Oct 2021
Understanding Interlocking Dynamics of Cooperative Rationalization Mo Yu Yang Zhang Shiyu Chang Tommi Jaakkola 20 41 0 26 Oct 2021
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining Andreas Madsen Nicholas Meade Vaibhav Adlakha Siva Reddy 111 35 0 15 Oct 2021
Does Commonsense help in detecting Sarcasm? Somnath Basu Roy Chowdhury Snigdha Chaturvedi 14 10 0 17 Sep 2021
Rationales for Sequential Predictions Keyon Vafa Yuntian Deng David M. Blei Alexander M. Rush 12 33 0 14 Sep 2021
Counterfactual Evaluation for Explainable AI Yingqiang Ge Shuchang Liu Zelong Li Shuyuan Xu Shijie Geng Yunqi Li Juntao Tan Fei Sun Yongfeng Zhang CML 38 14 0 05 Sep 2021
Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience G. Chrysostomou Nikolaos Aletras 32 16 0 31 Aug 2021
Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models Yiming Cui Weinan Zhang Wanxiang Che Ting Liu Zhigang Chen Shijin Wang LRM 25 9 0 26 Aug 2021
Post-hoc Interpretability for Neural NLP: A Survey Andreas Madsen Siva Reddy A. Chandar XAI 27 224 0 10 Aug 2021
The Brownian motion in the transformer model Yingshi Chen 21 1 0 12 Jul 2021
Relative Importance in Sentence Processing Nora Hollenstein Lisa Beinborn FAtt 19 29 0 07 Jun 2021
BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of Attention T. Gomez Suiyi Ling Thomas Fréour Harold Mouchère 21 5 0 04 Jun 2021
Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution Jiacheng Xu Greg Durrett 38 16 0 03 Jun 2021
Is Sparse Attention more Interpretable? Clara Meister Stefan Lazov Isabelle Augenstein Ryan Cotterell MILM 20 44 0 02 Jun 2021
ExpMRC: Explainability Evaluation for Machine Reading Comprehension Yiming Cui Ting Liu Wanxiang Che Zhigang Chen Shijin Wang ELM LRM 23 10 0 10 May 2021
SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning Aaron Chan Lyne Tchapmi Bo Long Soumya Sanyal Tanishq Gupta Xiang Ren ReLM LRM 24 11 0 18 Apr 2021
On the Sensitivity and Stability of Model Interpretations in NLP Fan Yin Zhouxing Shi Cho-Jui Hsieh Kai-Wei Chang FAtt 19 33 0 18 Apr 2021
Flexible Instance-Specific Rationalization of NLP Models G. Chrysostomou Nikolaos Aletras 31 14 0 16 Apr 2021
Evaluating Saliency Methods for Neural Language Models Shuoyang Ding Philipp Koehn FAtt XAI 23 54 0 12 Apr 2021
Multilingual Language Models Predict Human Reading Behavior Nora Hollenstein Federico Pirovano Ce Zhang Lena Jäger Lisa Beinborn VLM 47 45 0 12 Apr 2021
Exploring the Role of BERT Token Representations to Explain Sentence Probing Results Hosein Mohebbi Ali Modarressi Mohammad Taher Pilehvar MILM 27 23 0 03 Apr 2021
Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction Luoqiu Li Xiang Chen Zhen Bi Xin Xie Shumin Deng Ningyu Zhang Chuanqi Tan Mosha Chen Huajun Chen AAML 26 7 0 01 Apr 2021
Explaining the Road Not Taken Hua Shen Ting-Hao 'Kenneth' Huang FAtt XAI 27 9 0 27 Mar 2021
An Investigation of Language Model Interpretability via Sentence Editing Samuel Stevens Yu-Chuan Su LRM 15 8 0 28 Nov 2020
A Decomposable Attention Model for Natural Language Inference Ankur P. Parikh Oscar Täckström Dipanjan Das Jakob Uszkoreit 213 1,367 0 06 Jun 2016
Effective Approaches to Attention-based Neural Machine Translation Thang Luong Hieu H. Pham Christopher D. Manning 218 7,926 0 17 Aug 2015