Sparse Sequence-to-Sequence Models (P19-1)

Copied to clipboard

Challenge: Sequence-to-sequence models are dense and assigning nonzero probability to implausible outputs.
Approach: They propose a new family of -entmax transformations that includes softmax and sparsemax as particular cases and is sparser for any > 1 . they provide fast algorithms to evaluate these transformations and their gradients, which scale well for large vocabulary sizes.
Outcome: The proposed models are able to produce sparse alignments and assign nonzero probability to short list of plausible outputs, sometimes rendering beam search exact.

Similar Papers

Smoothing and Shrinking the Sparse Seq2Seq Search Space (2021.naacl-main)

Copied to clipboard

Challenge: entmax-based sparse sequence-to-sequence models give high scores to short hypotheses . ent max models can shrink the search space by assigning zero probability to bad hypothese .
Approach: They propose entmax-based sparse sequence-to-sequence models that minimize cross-entropy and use softmax to compute local normalized probabilities over target sequences.
Outcome: The proposed models remove a major source of model error for word-level tasks . the proposed models improve cross-lingual morphological inflection and machine translation .
Speeding Up Entmax (2022.findings-naacl)

Copied to clipboard

Challenge: Recent studies suggest that sparsity is a problem when the trained model is used for inference.
Approach: They propose an alternative to softmax that produces a dense probability distribution but is slower than softmax.
Outcome: The proposed method keeps its virtuous characteristics but is slower than softmax and achieves on par or better performance in machine translation task.
Surprisingly Easy Hard-Attention for Sequence to Sequence Learning (D18-1)

Copied to clipboard

Challenge: Existing attention mechanisms are hard and hard, but they are more accurate when trained.
Approach: They propose to use a beam approximation of the joint distribution between attention and output to train sequence to sequence learning.
Outcome: The proposed method is compared to existing attention mechanisms on five translation tasks and shows consistent gains on the same tasks.
SEQˆ3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression (N19-1)

Copied to clipboard

Challenge: Neural sequence-to-sequence models are currently the dominant approach in natural language processing tasks, but require massive parallel corpora.
Approach: They propose a sequence-to-sequence-tosequnce autoencoder with words as latent variables . they apply the model to unsupervised abstractive sentence compression .
Outcome: The proposed model achieves promising results in unsupervised sentence compression on benchmark datasets.
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs (2025.acl-short)

Copied to clipboard

Challenge: Recent advances in Video Large Language Models (Video-LLMs) have achieved exceptional performance on tasks like video question answering and captioning.
Approach: They propose a decoding strategy that leverages sparse top-K attention and dense full attention to accelerate Video-LLMs without loss.
Outcome: The proposed approach achieves a 1.94 walltime speedup in video processing.
Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation? (2022.findings-acl)

Copied to clipboard

Challenge: Pre-trained multilingual sequence-to-sequence models like mBART and mT5 can be used to translate low-resource languages, but their practical application is unclear.
Approach: They conduct an empirical experiment in 10 languages to determine what can pre-trained multilingual sequence-to-sequence models like mBART do to translate low-resource languages?
Outcome: The proposed models are robust to domain differences, but translations for unseen and typologically distant languages remain below 3.0 BLEU.
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models (2021.findings-acl)

Copied to clipboard

Challenge: Using sequence-to-sequence models, encoder outputs are usually transferred to the decoder for generation, but in this study, encoded outputs can be compressed to shorten the sequence for decoding.
Approach: They propose to use a stochastic gate-based algorithm to mask encoder outputs to shorten the sequence delivered for decoding.
Outcome: The proposed model can be used to shorten encoder outputs to short a sequence . the proposed model yields a speedup of up to 1.65 on document summarization and 1.20 on character-based machine translation tasks.
A Detailed Evaluation of Neural Sequence-to-Sequence Models for In-domain and Cross-domain Text Simplification (L18-1)

Copied to clipboard

Challenge: Xu et al., 2016) show that a simple neural architecture can be efficiently used for in-domain and cross-domain text simplification.
Approach: They evaluate neural sequence-to-sequence models for text simplification on Wikipedia and Newsela datasets.
Outcome: The proposed model can generalize across corpora and overcome challenges when tested on Wikipedia and Newsela datasets.
Sparse Text Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Current text generators require sampling from a modified softmax to avoid degenerate text . entmax sampling creates a mismatch between training and testing conditions .
Approach: They propose to use entmax transformation to train and sample from a sparse language model to avoid degenerate text.
Outcome: The proposed model improves fluency and consistency, fewer repetitions, and n-gram diversity closer to human text.
Efficient Out-of-Domain Detection for Sequence to Sequence Models (2023.findings-acl)

Copied to clipboard

Challenge: Sequence-to-sequence (seq2sequ) models are a ubiquitous tool for text generation but they are not suitable for many other tasks.
Approach: They propose to use UE techniques to identify out-of-domain (OOD) inputs where the model is susceptible to errors.
Outcome: The proposed methods outperform heavyweight ensembles on the task of OOD detection.

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