English
Related papers

Related papers: Self-Vocabularizing Training for Neural Machine Tr…

200 papers

The Byte Pair Encoding algorithm can be safely batched to merge hundreds of pairs of tokens at a time when building up a tokenizer's vocabulary. This technique combined with reducing the memory footprint of text used in vocabulary training…

Computation and Language · Computer Science 2024-08-12 Alexander P. Morgan

Natural language processing (NLP) enables the understanding and generation of meaningful human language, typically using a pre-trained complex architecture on a large dataset to learn the language and next fine-tune its weights to implement…

Computation and Language · Computer Science 2025-09-04 Yarden Tzach , Ronit D. Gross , Ella Koresh , Shalom Rosner , Or Shpringer , Tal Halevi , Ido Kanter

Byte-Pair Encoding (BPE) has become a widely adopted subword tokenization method in modern language models due to its simplicity and strong empirical performance across downstream tasks. However, applying BPE to unsegmented languages such…

Computation and Language · Computer Science 2025-06-23 Yifan Hu , Frank Liang , Dachuan Zhao , Jonathan Geuter , Varshini Reddy , Craig W. Schmidt , Chris Tanner

This work was conducted to find out how tokenization methods affect the training results of machine translation models. In this work, alphabet tokenization, morpheme tokenization, and BPE tokenization were applied to Korean as the source…

Computation and Language · Computer Science 2022-05-30 Dojun Park , Youngjin Jang , Harksoo Kim

The integration of language models for neural machine translation has been extensively studied in the past. It has been shown that an external language model, trained on additional target-side monolingual data, can help improve translation…

Computation and Language · Computer Science 2023-06-09 Christian Herold , Yingbo Gao , Mohammad Zeineldeen , Hermann Ney

Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has…

Computation and Language · Computer Science 2024-10-08 Craig W. Schmidt , Varshini Reddy , Haoran Zhang , Alec Alameddine , Omri Uzan , Yuval Pinter , Chris Tanner

Applying Reinforcement learning (RL) following maximum likelihood estimation (MLE) pre-training is a versatile method for enhancing neural machine translation (NMT) performance. However, recent work has argued that the gains produced by RL…

Computation and Language · Computer Science 2022-10-07 Asaf Yehudai , Leshem Choshen , Lior Fox , Omri Abend

We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. Classifiers are known to perform better with balanced class…

Computation and Language · Computer Science 2021-04-06 Thamme Gowda , Jonathan May

Language models typically need to be trained or finetuned in order to acquire new knowledge, which involves updating their weights. We instead envision language models that can simply read and memorize new data at inference time, thus…

Machine Learning · Computer Science 2022-03-18 Yuhuai Wu , Markus N. Rabe , DeLesley Hutchins , Christian Szegedy

Pre-trained word embeddings improve the performance of a neural model at the cost of increasing the model size. We propose to benefit from this resource without paying the cost by operating strictly at the sub-lexical level. Our approach is…

Computation and Language · Computer Science 2017-07-24 Karl Stratos

In this paper, we propose the use of in-training matrix factorization to reduce the model size for neural machine translation. Using in-training matrix factorization, parameter matrices may be decomposed into the products of smaller…

Computation and Language · Computer Science 2020-03-25 Zachary Kaden , Teven Le Scao , Raphael Olivier

We revisit self-training in the context of end-to-end speech recognition. We demonstrate that training with pseudo-labels can substantially improve the accuracy of a baseline model. Key to our approach are a strong baseline acoustic and…

Computation and Language · Computer Science 2020-05-08 Jacob Kahn , Ann Lee , Awni Hannun

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

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…

Computation and Language · Computer Science 2016-05-23 Dzmitry Bahdanau , Kyunghyun Cho , Yoshua Bengio

Meta-learning has recently become a research hotspot in speaker verification (SV). We introduce two methods to improve the meta-learning training for SV in this paper. For the first method, a backbone embedding network is first jointly…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-04 Yafeng Chen , Wu Guo , Bin Gu

The necessity of using a fixed-size word vocabulary in order to control the model complexity in state-of-the-art neural machine translation (NMT) systems is an important bottleneck on performance, especially for morphologically rich…

Computation and Language · Computer Science 2017-08-01 Duygu Ataman , Matteo Negri , Marco Turchi , Marcello Federico

While most neural machine translation (NMT) systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can substantially improve…

Computation and Language · Computer Science 2019-09-17 John Wieting , Taylor Berg-Kirkpatrick , Kevin Gimpel , Graham Neubig

Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient…

Computation and Language · Computer Science 2025-11-14 Benjamin L. Badger , Matthew Neligeorge

Generative language models are usually pretrained on large text corpus via predicting the next token (i.e., sub-word/word/phrase) given the previous ones. Recent works have demonstrated the impressive performance of large generative…

Computation and Language · Computer Science 2026-01-16 Zhenpeng Su , Xing Wu , Xue Bai , Zijia Lin , Hui Chen , Guiguang Ding , Wei Zhou , Songlin Hu

In learning-based functionality stealing, the attacker is trying to build a local model based on the victim's outputs. The attacker has to make choices regarding the local model's architecture, optimization method and, specifically for NLP…

Computation and Language · Computer Science 2024-01-30 Vilém Zouhar