Multi-Head Attention with Disagreement Regularization (D18-1)

Copied to clipboard

Challenge: Existing methods to encourage diversity among multi-head attention are limited.
Approach: They propose a disagreement regularization term to encourage diversity among attention heads . they validated their approach on EnglishGerman and ChineseEnglish translation tasks .
Outcome: The proposed approach improves translation performance across language pairs on English-German and Chinese-English translation tasks.

Similar Papers

Information Aggregation for Multi-Head Attention with Routing-by-Agreement (N19-1)

Copied to clipboard

Challenge: Existing studies focus on extracting informative or distinct partial-representations from different subspaces, while few studies have paid attention to the aggregation of the extracted partial-Representations.
Approach: They propose to use a routing-by-agreement algorithm to improve multi-head attention by iteratively updating the proportion of how much a part should be assigned to a whole based on agreement between parts and wholes.
Outcome: The proposed algorithm improves the information aggregation for multi-head attention over the standard linear transformation on linguistic probing and machine translation tasks.
Mixed Multi-Head Self-Attention for Neural Machine Translation (D19-56)

Copied to clipboard

Challenge: Recent advances in neural machine translation have been made in the field of multi-head self-attention and there is no explicit mechanism to ensure that different attention heads capture different features.
Approach: They propose a novel multi-head self-attention model which models not only global and local attention but also forward and backward attention in different attention heads.
Outcome: The proposed model improves on WAT17 English-Japanese and IWSLT14 German-English translation tasks without increasing the number of parameters.
Finding the Pillars of Strength for Multi-Head Attention (2023.acl-long)

Copied to clipboard

Challenge: Recent studies have revealed some issues of Multi-Head Attention (MHA) e.g., redundancy and over-parameterization.
Approach: They propose to train attention heads with a self-supervised group constraint to focus on an essential but distinctive feature subset.
Outcome: The proposed method achieves significant performance gains on three well-established tasks while significantly compressing parameters.
Multi-Head Attention with Diversity for Learning Grounded Multilingual Multimodal Representations (D19-1)

Copied to clipboard

Challenge: Recent studies have advanced learning VSE under the monolingual setup.
Approach: They propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations by leveraging visual object detection.
Outcome: The proposed model performs well in German-Image and English-Image matching tasks and in the Semantic Textual Similarity task with English descriptions of visual content.
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads? (2021.findings-acl)

Copied to clipboard

Challenge: Recent studies on multilingual representations focus on whether there is an emergence of language-independent representations or whether multilingual models partition their weights among different languages.
Approach: They analyze encoder self-attention and encoder-decoder attention heads in a multilingual neural translation model.
Outcome: The proposed model is based on a multilingual neural translation model with a language-independent representation.
Hybrid Neural Attention for Agreement/Disagreement Inference in Online Debates (D18-1)

Copied to clipboard

Challenge: Existing models for agreement/disagreement in debates lack the ability to model these two factors together.
Approach: They propose a hybrid attention model which combines self and cross attention mechanism to locate salient part from textual context and interaction between users.
Outcome: The proposed model outperforms the state-of-the-art models on three (dis)agreement inference datasets.
Multi-Level Attention Aggregation for Language-Agnostic Speaker Replication (2024.eacl-short)

Copied to clipboard

Challenge: Recent advances in speech synthesis research have enabled the generation of natural-sounding speech, which has prompted a notable shift in TTS research towards the synthesis of speech in the voices of both seen and unseen speakers.
Approach: They propose a multi-level attention aggregation approach that probes and amplifies various speaker-specific attributes in a hierarchical manner.
Outcome: The proposed model achieves substantial speaker similarity and generalizes to out-of-domain (OOD) cases.
Alleviating the Inequality of Attention Heads for Neural Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Recent studies show that the attention heads in Transformer are not equal.
Approach: They propose a masking method to mask attention heads in Transformer . they empirically validate the inequality and propose 'head mask' method to avoid bottleneck .
Outcome: The proposed masking method improves translation performance on multiple languages . it can be used to remove a small subset of heads without affecting performance .
Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing pre-trained language models have produced performance gains in various tasks but come with large computational requirements.
Approach: They propose an alternative module that uses only a single shared projection matrix and multiple head embeddings (MHE) they demonstrate that MHE attention is substantially more memory efficient compared to alternative attention mechanisms.
Outcome: The proposed model is more memory efficient compared to the current model while achieving high retention ratio on several downstream tasks.
CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis (D19-1)

Copied to clipboard

Challenge: Existing methods for aspect-specific sentiment classification are noisy and downgraded performance.
Approach: They propose a constrained attention network to regularize attention for multi-aspect sentiment analysis by orthogonal regularization on multiple aspects and sparse regularization for each single aspect.
Outcome: The proposed approach outperforms state-of-the-art methods on two public datasets and extends to multi-task settings.

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