English
Related papers

Related papers: Patching Leaks in the Charformer for Efficient Cha…

200 papers

Machine translation has seen rapid progress with the advent of Transformer-based models. These models have no explicit linguistic structure built into them, yet they may still implicitly learn structured relationships by attending to…

We explore the effectiveness of character-level neural machine translation using Transformer architecture for various levels of language similarity and size of the training dataset on translation between Czech and Croatian, German,…

Computation and Language · Computer Science 2023-08-09 Josef Jon , Ondřej Bojar

A common and effective way to train translation systems between related languages is to consider sub-word level basic units. However, this increases the length of the sentences resulting in increased decoding time. The increase in length is…

Computation and Language · Computer Science 2016-11-02 Anoop Kunchukuttan , Pushpak Bhattacharyya

On-line handwritten character segmentation is often associated with handwriting recognition and even though recognition models include mechanisms to locate relevant positions during the recognition process, it is typically insufficient to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-07 Michael Jungo , Beat Wolf , Andrii Maksai , Claudiu Musat , Andreas Fischer

Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or…

Computation and Language · Computer Science 2019-06-05 Fengshun Xiao , Jiangtong Li , Hai Zhao , Rui Wang , Kehai Chen

Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging sparsity. We study…

Transformer is the state-of-the-art model in recent machine translation evaluations. Two strands of research are promising to improve models of this kind: the first uses wide networks (a.k.a. Transformer-Big) and has been the de facto…

Computation and Language · Computer Science 2019-06-06 Qiang Wang , Bei Li , Tong Xiao , Jingbo Zhu , Changliang Li , Derek F. Wong , Lidia S. Chao

Modern language models are internally -- and mathematically -- distributions over $\it{token}$ strings rather than $\it{character}$ strings, posing numerous challenges for programmers building user applications on top of them. For example,…

Computation and Language · Computer Science 2025-06-11 Tim Vieira , Ben LeBrun , Mario Giulianelli , Juan Luis Gastaldi , Brian DuSell , John Terilla , Timothy J. O'Donnell , Ryan Cotterell

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

Models that rely on subword tokenization have significant drawbacks, such as sensitivity to character-level noise like spelling errors and inconsistent compression rates across different languages and scripts. While character- or byte-level…

Computation and Language · Computer Science 2025-04-03 Julie Kallini , Shikhar Murty , Christopher D. Manning , Christopher Potts , Róbert Csordás

Recent work on Grammatical Error Correction (GEC) has highlighted the importance of language modeling in that it is certainly possible to achieve good performance by comparing the probabilities of the proposed edits. At the same time,…

Computation and Language · Computer Science 2019-06-06 Dimitrios Alikaniotis , Vipul Raheja

We combine character-level and contextual language model representations to improve performance on Discourse Representation Structure parsing. Character representations can easily be added in a sequence-to-sequence model in either one…

Computation and Language · Computer Science 2020-11-10 Rik van Noord , Antonio Toral , Johan Bos

Traditionally, character-level transduction problems have been solved with finite-state models designed to encode structural and linguistic knowledge of the underlying process, whereas recent approaches rely on the power and flexibility of…

Computation and Language · Computer Science 2021-06-25 Maria Ryskina , Eduard Hovy , Taylor Berg-Kirkpatrick , Matthew R. Gormley

Increasing the input length has been a driver of progress in language modeling with transformers. We identify conditions where shorter inputs are not harmful, and achieve perplexity and efficiency improvements through two new methods that…

Computation and Language · Computer Science 2021-06-04 Ofir Press , Noah A. Smith , Mike Lewis

Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, we propose a…

Computation and Language · Computer Science 2016-07-01 Marta R. Costa-Jussà , José A. R. Fonollosa

Most existing Neural Machine Translation models use groups of characters or whole words as their unit of input and output. We propose a model with a hierarchical char2word encoder, that takes individual characters both as input and output.…

Computation and Language · Computer Science 2016-10-21 Alexander Rosenberg Johansen , Jonas Meinertz Hansen , Elias Khazen Obeid , Casper Kaae Sønderby , Ole Winther

Multilingual Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear. Do they form shared multilingual representations with language-specific decoding, and if so, why does…

Computation and Language · Computer Science 2026-02-10 Abir Harrasse , Florent Draye , Punya Syon Pandey , Zhijing Jin , Bernhard Schölkopf

Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition of tokens. Here,…

Computation and Language · Computer Science 2022-06-07 Ayush Kaushal , Kyle Mahowald

Large language models (LLMs) can spell out tokens character by character with high accuracy, yet they struggle with more complex character-level tasks, such as identifying compositional subcomponents within tokens. In this work, we…

Computation and Language · Computer Science 2025-06-13 Tatsuya Hiraoka , Kentaro Inui

Tokenization is widely used in large language models because it significantly improves performance. However, tokenization imposes several disadvantages, such as performance biases, increased adversarial vulnerability, decreased…

Computation and Language · Computer Science 2024-10-08 Kevin Slagle