Challenge: Word-embeddings are vital components of natural language processing (NLP) but they consume a lot of memory which poses a challenge for edge deployment.
Approach: They propose an embedding compression method based on matrix decomposition and knowledge distillation that initializes weights of pre-trained word-embeddings and fine-tunes end-to-end.
Outcome: The proposed method has higher BLEU score on translation and lower perplexity on language modeling compared to complex, difficult to tune methods.

Similar Papers

Block-wise Word Embedding Compression Revisited: Better Weighting and Structuring (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for word embedding compression are limited . word embeds have a considerable size and need to be compressed to deploy on edge devices .
Approach: They propose a block-wise low-rank approximation method for word embedding called GroupReduce . they propose 'frequency-inverse document frequency method' and a differentiable method for weighting .
Outcome: The proposed algorithm more effectively finds word weights than competitors in most cases.
Tensorized Embedding Layers (2020.findings-emnlp)

Copied to clipboard

Challenge: Using the Tensor Train decomposition, embeddings layers occupy large portion of model weights, preventing their deployment in limited resource settings.
Approach: They propose a method for parameterizing embedding layers based on the Tensor Train decomposition, which allows compressing the model significantly at the cost of a negligible drop or even a slight gain in performance.
Outcome: The proposed method can be plugged into any model and trained end-to-end.
EmByte: Decomposition and Compression Learning for Small yet Private NLP (2025.findings-emnlp)

Copied to clipboard

Challenge: EMBYTE is a byte-level tokenization model that reduces embedding parameters by up to 94% . it is also resilient to privacy threats such as gradient inversion attacks .
Approach: EMBYTE is a byte-level tokenization model that decomposes subwords into fine-grained byte embeddings and then compresses them via neural projection.
Outcome: EMBYTE achieves substantial embedding compression while preserving accuracy and enhancing privacy.
Distilling Relation Embeddings from Pretrained Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models capture a surprisingly rich amount of lexical knowledge, but it is unclear to what extent relation embeddings can be used to encode relational knowledge.
Approach: They found that word vector differences capture lexical relations . relationship embeddings can be used to encode relational knowledge .
Outcome: The results are highly competitive on analogy (unsupervised) and relation classification (supervised) benchmarks, even without any task-specific fine-tuning.
Obtaining Better Static Word Embeddings Using Contextual Embedding Models (2021.acl-long)

Copied to clipboard

Challenge: Recent contextual word embeddings have prohibitively high computational cost in many use-cases and are hard to interpret.
Approach: They propose a distillation method which is an extension of CBOW-based training and improves computational efficiency of NLP applications.
Outcome: The proposed method outperforms existing models and existing models in terms of quality and performance.
Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation (2022.findings-acl)

Copied to clipboard

Challenge: Existing pre-trained language models produce large sentence embeddings, resulting in performance gap between large and small models.
Approach: They propose a method that augments a small Transformer encoder model with learnable projection layers to produce compact sentences while mimicking a large pre-trained language model to retain the sentence representation quality.
Outcome: The proposed method achieves 2.7-4.5 points performance gain on STS and SR tasks while maintaining the quality of the pre-trained language models.
Better Word Embeddings by Disentangling Contextual n-Gram Information (N19-1)

Copied to clipboard

Challenge: Pre-trained word vectors are ubiquitous in Natural Language Processing applications.
Approach: They show that word embeddings with bigram and trigram embedds improve unigram embeds . they claim this removes contextual information from unigrammes, resulting in better unigraph embedders .
Outcome: The proposed model outperforms competing models on a wide variety of tasks.
Natural Language Generation for Effective Knowledge Distillation (D19-61)

Copied to clipboard

Challenge: Knowledge distillation can transfer knowledge from deep language representation models to shallow word embedding-based neural networks.
Approach: They propose to build an unlabeled transfer dataset to enable effective knowledge transfer . they hypothesize that this principled, general approach outperforms rule-based techniques .
Outcome: The proposed method outperforms OpenAI GPT on four datasets in sentiment classification, sentence similarity, and linguistic acceptability.
Textual Dataset Distillation via Language Model Embedding (2024.findings-emnlp)

Copied to clipboard

Challenge: prevailing methods for dataset distillation generate distilled data as embedding vectors, which are not human-readable.
Approach: They propose a model-agnostic, data-efficient method that leverages Language Model embeddings . their method offers enhanced flexibility and improved transferability .
Outcome: The proposed method achieves comparable performance with faster processing times compared to other methods . it offers enhanced flexibility and improved transferability, expanding the range of potential applications .
Multi-Sense Embeddings for Language Models and Knowledge Distillation (2025.findings-acl)

Copied to clipboard

Challenge: Transformer-based large language models generate different representations for the same token depending on context . however, words and tokens typically have only a limited number of senses . a knowledge distillation method can be used to learn a smaller student model .
Approach: They propose a multi-sense embedding method that uses a clustering algorithm to generate a sense embeddable dictionary.
Outcome: The proposed method offers significant space and inference time savings while maintaining competitive performance.

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