English
Related papers

Related papers: Neural Machine Translation without Embeddings

200 papers

Traditional neural machine translation is limited to the topmost encoder layer's context representation and cannot directly perceive the lower encoder layers. Existing solutions usually rely on the adjustment of network architecture, making…

Computation and Language · Computer Science 2020-11-04 Qiang Wang , Changliang Li , Yue Zhang , Tong Xiao , Jingbo Zhu

Large language models route every input through a learned embedding table of shape |V| x d_model, consuming hundreds of millions to billions of trainable parameters at frontier scale. We introduce Kronecker Embeddings, a deterministic…

Computation and Language · Computer Science 2026-05-29 Rohan Shravan

The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. In this paper we present a faster and simpler architecture based on a succession of convolutional layers. This allows to…

Computation and Language · Computer Science 2017-07-26 Jonas Gehring , Michael Auli , David Grangier , Yann N. Dauphin

Deep Learning methods employ multiple processing layers to learn hierarchial representations of data. They have already been deployed in a humongous number of applications and have produced state-of-the-art results. Recently with the growth…

Computation and Language · Computer Science 2018-08-15 Sarvesh Patil

In this paper, we propose a new universal machine translation approach focusing on languages with a limited amount of parallel data. Our proposed approach utilizes a transfer-learning approach to share lexical and sentence level…

Computation and Language · Computer Science 2018-04-18 Jiatao Gu , Hany Hassan , Jacob Devlin , Victor O. K. Li

This work combines algorithms based on word embeddings, dimensionality reduction, and clustering. The objective is to obtain topics from a set of unclassified texts. The algorithm to obtain the word embeddings is the BERT model, a neural…

Computation and Language · Computer Science 2023-12-08 Diego Saldaña Ulloa

Recent work has shown that deeper character-based neural machine translation (NMT) models can outperform subword-based models. However, it is still unclear what makes deeper character-based models successful. In this paper, we conduct an…

Computation and Language · Computer Science 2020-11-09 Gongbo Tang , Rico Sennrich , Joakim Nivre

We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair…

Machine Learning · Statistics 2017-07-06 Bart van Merriënboer , Amartya Sanyal , Hugo Larochelle , Yoshua Bengio

Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why deep models help NMT is an open question. In this paper, we…

Computation and Language · Computer Science 2020-10-09 Bei Li , Ziyang Wang , Hui Liu , Yufan Jiang , Quan Du , Tong Xiao , Huizhen Wang , Jingbo Zhu

Language models (LMs) are bound to their tokenizer, which maps raw text to a sequence of vocabulary items (tokens). This restricts their flexibility: for example, LMs trained primarily on English may still perform well in other natural and…

Computation and Language · Computer Science 2025-10-29 Benjamin Minixhofer , Edoardo Maria Ponti , Ivan Vulić

Bytes form the basis of the digital world and thus are a promising building block for multimodal foundation models. Recently, Byte Language Models (BLMs) have emerged to overcome tokenization, yet the excessive length of bytestreams…

Computation and Language · Computer Science 2025-02-21 Eric Egli , Matteo Manica , Jannis Born

Dealing with the complex word forms in morphologically rich languages is an open problem in language processing, and is particularly important in translation. In contrast to most modern neural systems of translation, which discard the…

Neural and Evolutionary Computing · Computer Science 2016-06-15 Ekaterina Vylomova , Trevor Cohn , Xuanli He , Gholamreza Haffari

Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP models to mobile devices requires compressing the word…

Computation and Language · Computer Science 2017-11-20 Raphael Shu , Hideki Nakayama

In this paper, we propose a new method for calculating the output layer in neural machine translation systems. The method is based on predicting a binary code for each word and can reduce computation time/memory requirements of the output…

Computation and Language · Computer Science 2017-04-25 Yusuke Oda , Philip Arthur , Graham Neubig , Koichiro Yoshino , Satoshi Nakamura

Sequential word order is important when processing text. Currently, neural networks (NNs) address this by modeling word position using position embeddings. The problem is that position embeddings capture the position of individual words,…

Computation and Language · Computer Science 2020-06-30 Benyou Wang , Donghao Zhao , Christina Lioma , Qiuchi Li , Peng Zhang , Jakob Grue Simonsen

Neural machine translation with millions of parameters is vulnerable to unfamiliar inputs. We propose Token Drop to improve generalization and avoid overfitting for the NMT model. Similar to word dropout, whereas we replace dropped token…

Computation and Language · Computer Science 2020-10-22 Huaao Zhang , Shigui Qiu , Xiangyu Duan , Min Zhang

We present UTF8Tokenizer, a minimalist byte-level tokenizer that maps text exactly to IDs corresponding to the bytes underlying the text's UTF-8 encoding (e.g., byte x09 is token ID 9). Unlike prior byte-level approaches (Xue et al., 2021;…

Computation and Language · Computer Science 2025-10-21 Amit Moryossef , Clara Meister , Pavel Stepachev , Desmond Elliott

We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model…

We propose a new technique for computational language representation called elementwise embedding, in which a material (semantic unit) is abstracted into a horizontal concatenation of lower-dimensional element (character) embeddings. While…

Computation and Language · Computer Science 2023-02-28 Dunam Kim , Jeeeun Kim

Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks adaptation to individual domains. To overcome this…

Computation and Language · Computer Science 2021-02-15 Haoming Jiang , Chen Liang , Chong Wang , Tuo Zhao