Papers with self-attention layers

12 papers
Efficient Content-Based Sparse Attention with Routing Transformers (2021.tacl-1)

Copied to clipboard

Challenge: Self-attention suffers from quadratic computation and memory requirements with respect to sequence length . despite its effectiveness, self-attention models suffer from quadratic computation and a limited set of locations .
Approach: They propose to learn dynamic sparse attention patterns that avoid allocating computation and memory to attend to content unrelated to the query of interest.
Outcome: The proposed model outperforms similar sparse attention models on language modeling and image generation on Wikitext-103 .
A Non-Linear Structural Probe (2021.naacl-main)

Copied to clipboard

Challenge: Probing is a method of investigating the encoding of knowledge in contextual representations.
Approach: They propose to kernelize a metric and develop a non-linear variant with an identical number of parameters by using a kernel-based probe.
Outcome: The proposed probe learns only linear transformations and achieves statistically significant performance improvement over baseline in all languages.
Towards efficient self-supervised representation learning in speech processing (2024.findings-eacl)

Copied to clipboard

Challenge: Existing models require several GPUs for days to pretrain, generating environmental concerns because of their high energy consumption.
Approach: They propose an efficient self-supervised model that uses a single GPU during 24 to 48 hours of pretraining to address high computational costs.
Outcome: The proposed model represents two orders of magnitude better than existing models.
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.
Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models (2021.naacl-main)

Copied to clipboard

Challenge: Pre-trained language models process text as a sequence of characters, ignoring more coarse granularity, e.g., words.
Approach: They propose a new pre-training paradigm for Chinese that incorporates word representations along with characters and can model a sentence in a multi-granular manner.
Outcome: The proposed model can bring an average increase of 1.5% under the 12-layer setting, which achieves new state-of-the-art among base-size models on the CLUE benchmarks.
Double Path Networks for Sequence to Sequence Learning (C18-1)

Copied to clipboard

Challenge: Existing approaches for Sequence to Sequence learning have been developed . convolutional neural networks and self-attention networks are the most popular .
Approach: They propose to integrate convolutional and self-attention layers into a double path network for sequence to sequence learning.
Outcome: The proposed method significantly improves performance over state-of-the-art systems.
Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization (2023.acl-long)

Copied to clipboard

Challenge: Z-Code++ is a pre-trained language model optimized for abstractive text summarization.
Approach: They propose a pre-trained language model optimized for abstractive text summarization that uses a two-phase pre-training technique to improve model's performance.
Outcome: The proposed model outperforms the competing models on low-resource summarization tasks in zero-shot and few-shot settings.
Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models (2021.acl-long)

Copied to clipboard

Challenge: Recent work has shown that convolutions have been successful in natural language learning.
Approach: They propose a convolutional approach to construct relative position embeddings in self-attention layers and propose 'compact attention' they propose multiple ways to integrate convolutions into Transformer self- attention.
Outcome: The proposed composite attention improves performance on multiple downstream tasks, replacing absolute position embeddings, and is more expressive than convolutions in NLP.
Variational Language Concepts for Interpreting Foundation Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Foundation Language Models (FLMs) have achieved remarkable success in natural language processing.
Approach: They propose a variational Bayesian framework to provide word-level interpretations for FLMs . they propose valc to find optimal language concepts to interpret FLM predictions .
Outcome: Empirical results show that the proposed framework can provide conceptual interpretations for foundation language models.
Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks (2024.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained large language models can be fine-tuned with instruction tuning to align the model responses with human intentions.
Approach: They investigate the effectiveness of parameter efficient fine-tuning (PEFT) of the Q-Former with visual reasoning benchmarks ScienceQA and IconQA.
Outcome: The proposed model achieves comparable performance to full fine-tuning using under 2% of the trainable parameters.
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference (2024.findings-emnlp)

Copied to clipboard

Challenge: XC-Llama uses pre-trained decoder-only models to condition generation on reference text without the prompt.
Approach: They propose a model that uses cross-attention to condition generation on reference text without the prompt.
Outcome: The proposed models outperform prompt-based inference methods and reduce space footprint relative to standard KV caching by two orders of magnitude.
Training-free Deep Concept Injection Enables Language Models for Video Question Answering (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to train pretrained language models for zero-shot crossmodal tasks require crossmodal pretraining.
Approach: They propose to inject visual concepts into the input text embedding space of a pretrained language model and build adaptation layers based on the intermediate representation of concepts.
Outcome: The proposed model performs zero-shot crossmodal tasks without crossmodal pretraining . it is based on the injection of visual concepts as input tokens and augmentation in intermediate features . the proposed model achieves competitive or even better results in zero- shot and fine-tuning 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