Papers with attention layer

12 papers
Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection (2024.eacl-srw)

Copied to clipboard

Challenge: Existing approaches to multimodal hateful content detection focus on detecting hate speech from text-based content, but they fail to address modality-specific features.
Approach: They propose a context-aware attention framework for multimodal hateful content detection that integrates an attention layer to meaningfully align the visual and textual features.
Outcome: The proposed framework achieves F1-scores of 69.7% and 70.3% on two hateful meme datasets and shows 2.5% and 3.2% performance improvement over the state-of-the-art systems.
On Sentence Representations for Propaganda Detection: From Handcrafted Features to Word Embeddings (D19-50)

Copied to clipboard

Challenge: The rise of fake and hyperpartisan news on social media and online news outlets calls for improved automatic detection of propaganda in texts.
Approach: They propose to use handcrafted features and learn dense semantic representations to detect propaganda in sentence-level and with random undersampling of the majority class (non-propaganda)
Outcome: The proposed system achieves a ranking of 10 among 25 participants, with 59.5 F1-score.
How does Attention Affect the Model? (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies on the effectiveness of attention in NLP do not consider changes in semantic capability of different components.
Approach: They propose a framework that exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic.
Outcome: The proposed framework exploits a convex hull representation of sequence semantics in an n-dimensional Semantic Euclidean Space and defines indicators to capture the impact of attention on sequence semantic.
Adversarial Attention Modeling for Multi-dimensional Emotion Regression (P19-1)

Copied to clipboard

Challenge: Empirical evaluation on EMOBANK corpus shows that our approach achieves notable improvements in r-values over the state-of-the-art baselines.
Approach: They propose a neural network-based approach to multi-dimensional emotion regression which automatically rates multiple emotion dimension scores for an input text.
Outcome: The proposed approach achieves notable improvements in r-values on both EMOBANK Reader’s and Writer’s multi-dimensional emotion regression tasks over the state-of-the-art baselines.
Multi-turn Response Selection using Dialogue Dependency Relations (2020.emnlp-main)

Copied to clipboard

Challenge: Existing models for multi-turn response selection ignore the dependencies between the turns.
Approach: They propose a dialogue extraction algorithm to transform a dialog history into threads based on their dependency relations.
Outcome: The proposed model outperforms the state-of-the-art models on DSTC7 and DSTF8* with competitive results on UbuntuV2 .
Aspect Based Sentiment Analysis with Gated Convolutional Networks (P18-1)

Copied to clipboard

Challenge: Aspect-based sentiment analysis can provide more detailed information than general sentiment analysis.
Approach: They propose a model based on convolutional neural networks and gating mechanisms which can selectively output the sentiment features according to the given aspect or entity.
Outcome: The proposed model can selectively output sentiment features according to the given aspect or entity.
Structured Minimally Supervised Learning for Neural Relation Extraction (N19-1)

Copied to clipboard

Challenge: Recent work shows that distant supervision can cause significant label noise when learning from large quantities of unlabeled text.
Approach: They propose a method that combines the benefits of learning representations and structured learning to predict sentence-level relation mentions given only proposition-level supervision from a KB.
Outcome: The proposed approach outperforms a number of baseline approaches while minimizing label noise.
APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Existing prompt tuning methods only introduce prompts at the input layer, limiting performance and leaving large room for improvement.
Approach: They propose a method that involves tuning a small set of soft prompts for pre-trained language models.
Outcome: The proposed method outperforms state-of-the-art methods with pre-trained models on the SuperGLUE benchmark.
Finding Educationally Supportive Contexts for Vocabulary Learning with Attention-Based Models (2024.lrec-main)

Copied to clipboard

Challenge: Identifying educationally supportive contexts for vocabulary learning is an important problem to solve for designing effective curricula for contextual word learning.
Approach: They evaluate attention-based approaches to find supportive contexts for vocabulary learning scenarios using an existing benchmark dataset.
Outcome: The proposed model outperforms a generic model and a custom model on a major dataset for educational context support prediction.
Multi-Task Stance Detection with Sentiment and Stance Lexicons (D19-1)

Copied to clipboard

Challenge: Recent studies show improvements in stance detection by using attention mechanism or sentiment information.
Approach: They propose a multi-task framework that incorporates attention mechanism and takes sentiment classification as an auxiliary task.
Outcome: The proposed model outperforms state-of-the-art deep learning methods on the SemEval-2016 dataset.
Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies have found that low-rank pre-training often compromises effectiveness.
Approach: They propose to apply low-dimensional module only to the attention layer to improve both effectiveness and efficiency.
Outcome: The proposed model saves 12.4% time while improving test perplexity and on downstream tasks compared with vanilla Transformer.
On the Expressivity Role of LayerNorm in Transformers’ Attention (2023.findings-acl)

Copied to clipboard

Challenge: Layer Normalization (LayerNorm) is an inherent component in all Transformer-based models.
Approach: They propose to use LayerNorm to normalize the activations during the forward pass and their gradients during the backward pass.
Outcome: The proposed model is able to express the multi-head attention layer that follows it in a d-1 space and scales to the same norm of d.

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