English
Related papers

Related papers: MYTE: Morphology-Driven Byte Encoding for Better a…

200 papers

Tables are ubiquitous across various domains for concisely representing structured information. Empowering large language models (LLMs) to reason over tabular data represents an actively explored direction. However, since typical LLMs only…

Computation and Language · Computer Science 2024-10-21 Jia-Nan Li , Jian Guan , Wei Wu , Zhengtao Yu , Rui Yan

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

Computation and Language · Computer Science 2025-06-24 Kang Chen , Mengdi Zhang , Yixin Cao

How should text dataset sizes be compared across languages? Even for content-matched (parallel) corpora, UTF-8 encoded text can require a dramatically different number of bytes for different languages. In our work, we define the byte…

Computation and Language · Computer Science 2024-03-04 Catherine Arnett , Tyler A. Chang , Benjamin K. Bergen

Effectively modeling time information and incorporating it into applications or models involving chronologically occurring events is crucial. Real-world scenarios often involve diverse and complex time patterns, which pose significant…

Machine Learning · Computer Science 2025-05-15 Xi Chen , Yateng Tang , Jiarong Xu , Jiawei Zhang , Siwei Zhang , Sijia Peng , Xuehao Zheng , Yun Xiong

As a cornerstone in language modeling, tokenization involves segmenting text inputs into pre-defined atomic units. Conventional statistical tokenizers often disrupt constituent boundaries within words, thereby corrupting semantic…

Computation and Language · Computer Science 2025-07-11 Qingyang Zhu , Xiang Hu , Pengyu Ji , Wei Wu , Kewei Tu

This thesis investigates how the sub-structure of words can be accounted for in probabilistic models of language. Such models play an important role in natural language processing tasks such as translation or speech recognition, but often…

Computation and Language · Computer Science 2015-08-19 Jan A. Botha

Multilingual language models (LMs) promise broader NLP access, yet current systems deliver uneven performance across the world's languages. This survey examines why these gaps persist and whether they reflect intrinsic linguistic difficulty…

Computation and Language · Computer Science 2026-04-13 Chen Shani , Yuval Reif , Nathan Roll , Dan Jurafsky , Ekaterina Shutova

Tokenization significantly influences language models(LMs)' performance. This paper traces the evolution of tokenizers from word-level to subword-level, analyzing how they balance tokens and types to enhance model adaptability while…

Computation and Language · Computer Science 2024-03-04 Jinbiao Yang

To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is currently only possible through the use of external tools or…

Machine Learning · Computer Science 2026-05-21 Linus Kreitner , Paul Hager , Jonathan Mengedoht , Georgios Kaissis , Daniel Rueckert , Martin J. Menten

The diversity of human language, shaped by social, cultural, and regional influences, presents significant challenges for natural language processing (NLP) systems. Existing benchmarks often overlook intra-language variations, leaving…

Computation and Language · Computer Science 2025-04-11 Abhay Gupta , Jacob Cheung , Philip Meng , Shayan Sayyed , Austen Liao , Kevin Zhu , Sean O'Brien

Chemical language models (CLMs) are prominent for their effectiveness in exploring chemical space and enabling molecular engineering. However, while exploring chemical-linguistic space, CLMs suffer from the gap between natural language and…

Computational Engineering, Finance, and Science · Computer Science 2025-01-07 Liuzhenghao Lv , Hao Li , Yu Wang , Zhiyuan Yan , Zijun Chen , Zongying Lin , Li Yuan , Yonghong Tian

Traditionally, many text-mining tasks treat individual word-tokens as the finest meaningful semantic granularity. However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword…

Computation and Language · Computer Science 2019-11-15 Ahmed El-Kishky , Frank Xu , Aston Zhang , Jiawei Han

Byte Pair Encoding (BPE) tokenizers, widely used in Large Language Models, face challenges in multilingual settings, including penalization of non-Western scripts and the creation of tokens with partial UTF-8 sequences. Pretokenization,…

Computation and Language · Computer Science 2025-06-02 Sander Land , Catherine Arnett

Prior studies in multilingual language modeling (e.g., Cotterell et al., 2018; Mielke et al., 2019) disagree on whether or not inflectional morphology makes languages harder to model. We attempt to resolve the disagreement and extend those…

Computation and Language · Computer Science 2021-03-29 Hyunji Hayley Park , Katherine J. Zhang , Coleman Haley , Kenneth Steimel , Han Liu , Lane Schwartz

The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by better modelling the…

Computation and Language · Computer Science 2023-05-23 Amit Kumar , Shantipriya Parida , Ajay Pratap , Anil Kumar Singh

Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines. Standard algorithms for learning tokenizers rely on frequency-based objectives, which favor languages dominant in the training data and consequently…

Computation and Language · Computer Science 2025-08-25 Negar Foroutan , Clara Meister , Debjit Paul , Joel Niklaus , Sina Ahmadi , Antoine Bosselut , Rico Sennrich

Scaling multilingual representation learning beyond the hundred most frequent languages is challenging, in particular to cover the long tail of low-resource languages. A promising approach has been to train one-for-all multilingual models…

Computation and Language · Computer Science 2022-05-26 Kevin Heffernan , Onur Çelebi , Holger Schwenk

Many proofs in discrete mathematics and theoretical computer science are based on the probabilistic method. To prove the existence of a good object, we pick a random object and show that it is bad with low probability. This method is…

Information Theory · Computer Science 2017-08-01 Pat Morin , Wolfgang Mulzer , Tommy Reddad

Molecules are graphs, but large language models~(LLMs) are usually asked to reason about them through linear strings. The most popular molecular representation, SMILES, compresses atoms, bonds, branches and rings into a compact sequence in…

Biomolecules · Quantitative Biology 2026-05-19 Zhiyuan Yan , Chen Liu , Boxuan Zhao , Kaiqing Lin , Jixiang Zhao , Yimi Wang , Liuzhenghao Lv , Hao Li , Shanzhuo Zhang , Li Yuan , Fanyang Mo

Morphologically rich languages often lack the annotated linguistic resources required to develop accurate natural language processing tools. We propose models suitable for training morphological taggers with rich tagsets for low-resource…

Computation and Language · Computer Science 2016-06-15 Jan Buys , Jan A. Botha