English
Related papers

Related papers: From Fully Trained to Fully Random Embeddings: Imp…

200 papers

Recent work has validated the importance of subword information for word representation learning. Since subwords increase parameter sharing ability in neural models, their value should be even more pronounced in low-data regimes. In this…

Computation and Language · Computer Science 2019-09-30 Yi Zhu , Benjamin Heinzerling , Ivan Vulić , Michael Strube , Roi Reichart , Anna Korhonen

Existing neural machine translation (NMT) models generally translate sentences in isolation, missing the opportunity to take advantage of document-level information. In this work, we propose to augment NMT models with a very light-weight…

Computation and Language · Computer Science 2017-11-28 Zhaopeng Tu , Yang Liu , Shuming Shi , Tong Zhang

We present a novel online algorithm that learns the essence of each dimension in word embeddings by minimizing the within-group distance of contextualized embedding groups. Three state-of-the-art neural-based language models are used,…

Computation and Language · Computer Science 2020-05-26 Xinyi Jiang , Zhengzhe Yang , Jinho D. Choi

Token embeddings play a crucial role in language modeling but, despite this practical relevance, their theoretical understanding remains limited. Our paper addresses the gap by characterizing the structure of embeddings obtained via…

Machine Learning · Computer Science 2025-06-26 Diyuan Wu , Aleksandr Shevchenko , Samet Oymak , Marco Mondelli

Conventional word embeddings represent words with fixed vectors, which are usually trained based on co-occurrence patterns among words. In doing so, however, the power of such representations is limited, where the same word might be…

Computation and Language · Computer Science 2020-01-10 Hongming Zhang , Jiaxin Bai , Yan Song , Kun Xu , Changlong Yu , Yangqiu Song , Wilfred Ng , Dong Yu

Recently, very large pre-trained models achieve state-of-the-art results in various natural language processing (NLP) tasks, but their size makes it more challenging to apply them in resource-constrained environments. Compression techniques…

Computation and Language · Computer Science 2023-06-28 Alireza Mohammadshahi , Vassilina Nikoulina , Alexandre Berard , Caroline Brun , James Henderson , Laurent Besacier

Learning high-quality embeddings for rare words is a hard problem because of sparse context information. Mimicking (Pinter et al., 2017) has been proposed as a solution: given embeddings learned by a standard algorithm, a model is first…

Computation and Language · Computer Science 2019-04-08 Timo Schick , Hinrich Schütze

Pretraining deep neural network architectures with a language modeling objective has brought large improvements for many natural language processing tasks. Exemplified by BERT, a recently proposed such architecture, we demonstrate that…

Computation and Language · Computer Science 2019-12-05 Timo Schick , Hinrich Schütze

Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or…

Computation and Language · Computer Science 2019-06-12 Zhuosheng Zhang , Hai Zhao , Kangwei Ling , Jiangtong Li , Zuchao Li , Shexia He , Guohong Fu

In a multilingual neural machine translation model that fully shares parameters across all languages, an artificial language token is usually used to guide translation into the desired target language. However, recent studies show that…

Computation and Language · Computer Science 2022-09-07 Renren Jin , Deyi Xiong

Word embeddings are a basic building block of modern NLP pipelines. Efforts have been made to learn rich, efficient, and interpretable embeddings for large generic datasets available in the public domain. However, these embeddings have…

Computation and Language · Computer Science 2021-03-23 Rishabh Gupta , Rajesh N Rao

Word embeddings have been shown to be useful across state-of-the-art systems in many natural language processing tasks, ranging from question answering systems to dependency parsing. (Herbelot and Vecchi, 2015) explored word embeddings and…

Computation and Language · Computer Science 2016-07-12 Franck Dernoncourt

Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…

Computation and Language · Computer Science 2019-01-15 Shuo Ren , Zhirui Zhang , Shujie Liu , Ming Zhou , Shuai Ma

Network embeddings, which learn low-dimensional representations for each vertex in a large-scale network, have received considerable attention in recent years. For a wide range of applications, vertices in a network are typically…

Computation and Language · Computer Science 2018-08-30 Dinghan Shen , Xinyuan Zhang , Ricardo Henao , Lawrence Carin

In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency, which makes the Transformer-based NMT achieve…

Computation and Language · Computer Science 2020-04-09 Kehai Chen , Rui Wang , Masao Utiyama , Eiichiro Sumita

With an increase of dataset availability, the potential for learning from a variety of data sources has increased. One particular method to improve learning from multiple data sources is to embed the data source during training. This allows…

Computation and Language · Computer Science 2021-12-08 Rob van der Goot , Miryam de Lhoneux

Training efficiency is one of the main problems for Neural Machine Translation (NMT). Deep networks need for very large data as well as many training iterations to achieve state-of-the-art performance. This results in very high computation…

Computation and Language · Computer Science 2017-10-04 Dakun Zhang , Jungi Kim , Josep Crego , Jean Senellart

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

Despite being the current de-facto models in most NLP tasks, transformers are often limited to short sequences due to their quadratic attention complexity on the number of tokens. Several attempts to address this issue were studied, either…

Computation and Language · Computer Science 2023-07-19 Amine Abdaoui , Sourav Dutta

Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain…

Computation and Language · Computer Science 2024-06-07 Chi Han , Jialiang Xu , Manling Li , Yi Fung , Chenkai Sun , Nan Jiang , Tarek Abdelzaher , Heng Ji