English
Related papers

Related papers: Embedding Recycling for Language Models

200 papers

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Computation and Language · Computer Science 2025-02-21 Lukas Stankevičius , Mantas Lukoševičius

We build a dual-way neural dictionary to retrieve words given definitions, and produce definitions for queried words. The model learns the two tasks simultaneously and handles unknown words via embeddings. It casts a word or a definition to…

Computation and Language · Computer Science 2022-10-12 Pinzhen Chen , Zheng Zhao

In this paper, we show that high-performing embedding models organize their embedding spaces in a consistent way. We evaluate 25 contemporary embedding models on five MTEB tasks spanning four diverse task categories (retrieval, bitext…

Computation and Language · Computer Science 2026-05-22 Amanda Myntti , Jenna Kanerva , Veronika Laippala , Filip Ginter

Training large-scale image recognition models is computationally expensive. This raises the question of whether there might be simple ways to improve the test performance of an already trained model without having to re-train or fine-tune…

Computer Vision and Pattern Recognition · Computer Science 2018-11-27 A. Emin Orhan

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

Computation and Language · Computer Science 2025-01-28 Ziwei Liu , Qi Zhang , Lifu Gao

Cross-lingual word embeddings (CLEs) enable multilingual modeling of meaning and facilitate cross-lingual transfer of NLP models. Despite their ubiquitous usage in downstream tasks, recent increasingly popular projection-based CLE models…

Computation and Language · Computer Science 2019-06-07 Goran Glavas , Robert Litschko , Sebastian Ruder , Ivan Vulic

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Computation and Language · Computer Science 2020-02-24 Herman Kamper , Yevgen Matusevych , Sharon Goldwater

Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks. Contextual embeddings assign each word a…

Computation and Language · Computer Science 2020-04-14 Qi Liu , Matt J. Kusner , Phil Blunsom

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In…

Computation and Language · Computer Science 2021-02-08 Herman Kamper , Yevgen Matusevych , Sharon Goldwater

Traditional neural word embeddings are usually dependent on a richer diversity of vocabulary. However, the language models recline to cover major vocabularies via the word embedding parameters, in particular, for multilingual language…

Computation and Language · Computer Science 2023-08-21 Amit Kumar Jaiswal , Haiming Liu

Modern recommendation systems rely on real-valued embeddings of categorical features. Increasing the dimension of embedding vectors improves model accuracy but comes at a high cost to model size. We introduce a multi-layer embedding…

Machine Learning · Computer Science 2020-06-11 Benjamin Ghaemmaghami , Zihao Deng , Benjamin Cho , Leo Orshansky , Ashish Kumar Singh , Mattan Erez , Michael Orshansky

Pretrained foundation models learn embeddings that can be used for a wide range of downstream tasks. These embeddings optimise general performance, and if insufficiently accurate at a specific task the model can be fine-tuned to improve…

Machine Learning · Computer Science 2025-02-20 Matthew P. Wilson , Edward O. Pyzer-Knapp , Nicolas Galichet , Luke Dicks

We investigate the extent to which verb alternation classes, as described by Levin (1993), are encoded in the embeddings of Large Pre-trained Language Models (PLMs) such as BERT, RoBERTa, ELECTRA, and DeBERTa using selectively constructed…

Computation and Language · Computer Science 2022-09-13 David K. Yi , James V. Bruno , Jiayu Han , Peter Zukerman , Shane Steinert-Threlkeld

Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities. Its theoretical basis shows its universal approximation…

Machine Learning · Computer Science 2024-06-27 Ergun Biçici

When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…

Computation and Language · Computer Science 2024-06-18 Belinda Z. Li , Emmy Liu , Alexis Ross , Abbas Zeitoun , Graham Neubig , Jacob Andreas

Parameter-efficient finetuning (PEFT) has become ubiquitous to adapt foundation models to downstream task requirements while retaining their generalization ability. However, the amount of additionally introduced parameters and compute for…

Machine Learning · Computer Science 2024-10-14 Massimo Bini , Karsten Roth , Zeynep Akata , Anna Khoreva

Neural word representations have proven useful in Natural Language Processing (NLP) tasks due to their ability to efficiently model complex semantic and syntactic word relationships. However, most techniques model only one representation…

Computation and Language · Computer Science 2015-11-23 Andrew Trask , Phil Michalak , John Liu

Sentence-level representations are necessary for various NLP tasks. Recurrent neural networks have proven to be very effective in learning distributed representations and can be trained efficiently on natural language inference tasks. We…

Computation and Language · Computer Science 2019-08-15 Aarne Talman , Anssi Yli-Jyrä , Jörg Tiedemann

We present models for encoding sentences into embedding vectors that specifically target transfer learning to other NLP tasks. The models are efficient and result in accurate performance on diverse transfer tasks. Two variants of the…

Since its introduction, Word2Vec and its variants are widely used to learn semantics-preserving representations of words or entities in an embedding space, which can be used to produce state-of-art results for various Natural Language…

Computation and Language · Computer Science 2016-06-28 Jeroen B. P. Vuurens , Carsten Eickhoff , Arjen P. de Vries
‹ Prev 1 4 5 6 7 8 10 Next ›