Papers with Attention mechanisms

13 papers
Attention is not not Explanation (D19-1)

Copied to clipboard

Challenge: Attention mechanisms play a central role in NLP systems, especially within recurrent neural network (RNN) models.
Approach: They propose to use a simple uniform-weights baseline, a variance calibration and a diagnostic framework to determine when/whether attention can be used as explanation in RNN models.
Outcome: The proposed tests show that even reliable adversarial distributions don't perform well on the simple diagnostic, indicating that prior work does not disprove the usefulness of attention mechanisms for explainability.
Bidirectional Masked Self-attention and N-gram Span Attention for Constituency Parsing (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing attention mechanisms for constituency parsing lack directional information needed to form sentence spans.
Approach: They propose a bidirectional masked and N-gram span Attention model which captures the explicit dependencies between each word and enhances the representation of the output span vectors.
Outcome: The proposed model achieves state-of-the-art performance on the Penn Treebank and Chinese Penn TreeBank datasets with F1 scores of 96.47 and 94.15 respectively.
Rethinking Self-Attention: Towards Interpretability in Neural Parsing (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent work shows that attention mechanisms provide arguably explainable attention distributions that can help to interpret predictions.
Approach: They propose a new self-attention layer where attention heads represent labels.
Outcome: The proposed model obtains state-of-the-art results on the Penn Treebank and Chinese Treebank.
A Lexicon-Based Supervised Attention Model for Neural Sentiment Analysis (C18-1)

Copied to clipboard

Challenge: Existing attention models do not take full advantage of sentiment lexicons, which provide rich sentiment information and play a critical role in sentiment analysis.
Approach: They propose a lexicon-based supervised attention model which allows a neural network to focus on the sentiment content, thus generating sentiment-informative representations.
Outcome: The proposed model outperforms existing models on three large-scale sentiment classification datasets.
Answering Legal Questions by Learning Neural Attentive Text Representation (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for retrieval-based question answering are limited by legal documents and long and complicated documents.
Approach: They propose a retrieval-based model for answering legal questions at the article level by learning neural attentive text representation.
Outcome: The proposed model outperforms state-of-the-art retrieval-based methods on an annotated corpus of 5,922 Vietnamese legal questions in terms of recall and NDCG.
Attention Calibration for Transformer in Neural Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: Attention mechanisms have been ubiquitous in neural machine translation (NMT) however, many studies doubt whether highlyattended inputs have a large impact on the model outputs.
Approach: They propose to introduce a mask perturbation model that automatically evaluates each input’s contribution to the model outputs.
Outcome: The proposed model is more uniform at lower layers while more concentrated on the specific inputs at higher layers.
Using a Penalty-based Loss Re-estimation Method to Improve Implicit Discourse Relation Classification (2020.coling-main)

Copied to clipboard

Challenge: inessential words are unintentionally misjudged as attention-worthy words and assigned heavier attention weights than should be.
Approach: They propose a penalty-based method to regulate the attention learning process by integrating penalty coefficients into the computation of loss by means of overstability of attention weight distributions.
Outcome: The proposed method improves on the Penn Discourse TreeBank corpus and is competitive compared to the state-of-the-art methods.
Adaptively Sparse Transformers (D19-1)

Copied to clipboard

Challenge: Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention.
Approach: They propose an adaptively sparse Transformer where attention heads have flexible, context-dependent sparsity patterns.
Outcome: The proposed model improves interpretability and head diversity when compared to softmax-based models on machine translation datasets.
Is Attention Interpretable? (P19-1)

Copied to clipboard

Challenge: Attention mechanisms have recently boosted performance on a range of NLP tasks.
Approach: They propose to manipulate attention weights in text classification models and analyze the resulting differences in their predictions.
Outcome: The proposed approach improves models' predictions by using gradient-based rankings of attention weights.
Multi-grained Attention with Object-level Grounding for Visual Question Answering (P19-1)

Copied to clipboard

Challenge: Current approaches to visual question answering train attention models from coarse-grained associations between sentences and images, which fail on small objects or uncommon concepts.
Approach: They propose a multi-grained attention method that learns explicit word-object correspondence by word-level attention complementary to the sentence-image association.
Outcome: The proposed method achieves competitive performance with state-of-the-art models on the VQA benchmark.
Attention is not Explanation (N19-1)

Copied to clipboard

Challenge: Attention mechanisms have seen wide adoption in neural NLP models.
Approach: They perform extensive experiments to assess the degree to which attention weights provide meaningful "explanations" they find that attention weighted inputs are often uncorrelated with gradient-based measures of feature importance .
Outcome: The proposed model is based on a distribution over attended-to input units . the findings show that attention weights are often uncorrelated with features .
Data-Informed Global Sparseness in Attention Mechanisms for Deep Neural Networks (2024.lrec-main)

Copied to clipboard

Challenge: Attention pruning techniques have been developed to identify and exploit sparseness . previous work has taken pioneering steps to discover and explain the sparsity in attention patterns .
Approach: They propose a framework that observes attention patterns in a fixed dataset and generates a global sparseness mask.
Outcome: The proposed approach saves 90% of computations and maintains quality of results.
Learning to Deceive with Attention-Based Explanations (2020.acl-main)

Copied to clipboard

Challenge: Attention mechanisms are ubiquitous components in neural network architectures and are often claimed to confer interpretability.
Approach: They propose a method for training models to produce deceptive attention masks by combining weights assigned to designated impermissible tokens with a weighted sum.
Outcome: The proposed method reduces the weight assigned to designated impermissible tokens while still using them across multiple models and tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations