Inserting Information Bottlenecks for Attribution in Transformers

• URL: http://arxiv.org/abs/2012.13838v1
• Date: Sun, 27 Dec 2020 00:35:43 GMT
• Title: Inserting Information Bottlenecks for Attribution in Transformers
• Authors: Zhiying Jiang, Raphael Tang, Ji Xin, Jimmy Lin
• Abstract summary: We apply information bottlenecks to analyze the attribution of each feature for prediction on a black-box model. We show the effectiveness of our method in terms of attribution and the ability to provide insight into how information flows through layers.
• Score: 46.77580577396633
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pretrained transformers achieve the state of the art across tasks in natural language processing, motivating researchers to investigate their inner mechanisms. One common direction is to understand what features are important for prediction. In this paper, we apply information bottlenecks to analyze the attribution of each feature for prediction on a black-box model. We use BERT as the example and evaluate our approach both quantitatively and qualitatively. We show the effectiveness of our method in terms of attribution and the ability to provide insight into how information flows through layers. We demonstrate that our technique outperforms two competitive methods in degradation tests on four datasets. Code is available at https://github.com/bazingagin/IBA.

Related papers

• Evaluating Prompt-based Question Answering for Object Prediction in the Open Research Knowledge Graph [0.0]
  This work reports results on adopting prompt-based training of transformers for textitscholarly knowledge graph object prediction It deviates from the other works proposing entity and relation extraction pipelines for predicting objects of a scholarly knowledge graph. We find that (i) per expectations, transformer models when tested out-of-the-box underperform on a new domain of data, (ii) prompt-based training of the models achieve performance boosts of up to 40% in a relaxed evaluation setting.
  arXiv  Detail & Related papers  (2023-05-22T10:35:18Z)
• Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs [3.662157175955389]
  We propose a novel approach for automatically constructing domain-specific knowledge graphs that contain information relevant to the identification of aspect terms. We demonstrate state-of-the-art performance on benchmark datasets for cross-domain aspect term extraction using our approach and investigate how the amount of external knowledge available to the Transformer impacts model performance.
  arXiv  Detail & Related papers  (2022-10-18T20:18:42Z)
• What does Transformer learn about source code? [26.674180481543264]
  transformer-based representation models have achieved state-of-the-art (SOTA) performance in many tasks. We propose the aggregated attention score, a method to investigate the structural information learned by the transformer. We also put forward the aggregated attention graph, a new way to extract program graphs from the pre-trained models automatically.
  arXiv  Detail & Related papers  (2022-07-18T09:33:04Z)
• Human-in-the-Loop Disinformation Detection: Stance, Sentiment, or Something Else? [93.91375268580806]
  Both politics and pandemics have recently provided ample motivation for the development of machine learning-enabled disinformation (a.k.a. fake news) detection algorithms. Existing literature has focused primarily on the fully-automated case, but the resulting techniques cannot reliably detect disinformation on the varied topics, sources, and time scales required for military applications. By leveraging an already-available analyst as a human-in-the-loop, canonical machine learning techniques of sentiment analysis, aspect-based sentiment analysis, and stance detection become plausible methods to use for a partially-automated disinformation detection system.
  arXiv  Detail & Related papers  (2021-11-09T13:30:34Z)
• Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience [9.147707153504117]
  We propose an auxiliary loss function for guiding the multi-head attention mechanism during training to be close to salient information extracted using TextRank. Experiments for explanation faithfulness across five datasets, show that models trained with SaLoss consistently provide more faithful explanations. We further show that the latter result in higher predictive performance in downstream tasks.
  arXiv  Detail & Related papers  (2021-08-31T11:21:30Z)
• Visual Transformer for Task-aware Active Learning [49.903358393660724]
  We present a novel pipeline for pool-based Active Learning. Our method exploits accessible unlabelled examples during training to estimate their co-relation with the labelled examples. Visual Transformer models non-local visual concept dependency between labelled and unlabelled examples.
  arXiv  Detail & Related papers  (2021-06-07T17:13:59Z)
• Interpretable Multi-dataset Evaluation for Named Entity Recognition [110.64368106131062]
  We present a general methodology for interpretable evaluation for the named entity recognition (NER) task. The proposed evaluation method enables us to interpret the differences in models and datasets, as well as the interplay between them. By making our analysis tool available, we make it easy for future researchers to run similar analyses and drive progress in this area.
  arXiv  Detail & Related papers  (2020-11-13T10:53:27Z)
• Self-Attention Attribution: Interpreting Information Interactions Inside Transformer [89.21584915290319]
  We propose a self-attention attribution method to interpret the information interactions inside Transformer. We show that the attribution results can be used as adversarial patterns to implement non-targeted attacks towards BERT.
  arXiv  Detail & Related papers  (2020-04-23T14:58:22Z)
• How Useful is Self-Supervised Pretraining for Visual Tasks? [133.1984299177874]
  We evaluate various self-supervised algorithms across a comprehensive array of synthetic datasets and downstream tasks. Our experiments offer insights into how the utility of self-supervision changes as the number of available labels grows.
  arXiv  Detail & Related papers  (2020-03-31T16:03:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.