English
Related papers

Related papers: Confounding Factors in Relating Model Performance …

200 papers

Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they…

Computation and Language · Computer Science 2017-04-28 Clara Vania , Adam Lopez

Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the…

Computation and Language · Computer Science 2023-10-19 Avijit Thawani , Saurabh Ghanekar , Xiaoyuan Zhu , Jay Pujara

Scaling existing applications and solutions to multiple human languages has traditionally proven to be difficult, mainly due to the language-dependent nature of preprocessing and feature engineering techniques employed in traditional…

Computation and Language · Computer Science 2020-01-01 Xiaotong Liu , Yingbei Tong , Anbang Xu , Rama Akkiraju

While multilingual large language models (LLMs) perform well on high-level tasks like translation and question answering, their ability to handle grammatical gender and morphological agreement remains underexplored. In morphologically rich…

Computation and Language · Computer Science 2026-04-22 Mehul Agarwal , Aditya Aggarwal , Arnav Goel , Medha Hira , Anubha Gupta

Subword tokenization has become the de-facto standard for tokenization, although comparative evaluations of subword vocabulary quality across languages are scarce. Existing evaluation studies focus on the effect of a tokenization algorithm…

Computation and Language · Computer Science 2023-10-23 Lisa Beinborn , Yuval Pinter

Across languages, numeral systems vary widely in how they construct and combine numbers. While humans consistently learn to navigate this diversity, large language models (LLMs) struggle with linguistic-mathematical puzzles involving…

Computation and Language · Computer Science 2025-10-16 Antara Raaghavi Bhattacharya , Isabel Papadimitriou , Kathryn Davidson , David Alvarez-Melis

Cross-lingual transfer in language models is difficult to study in natural corpora because lexical overlap, morphology, data imbalance, and tokenization are entangled. We introduce an in-vitro framework with two procedurally generated…

Computation and Language · Computer Science 2026-05-27 Adrian Cosma

Languages vary widely in how meanings map to word forms. These mappings have been found to support efficient communication; however, this theory does not account for systematic relations within word forms. We examine how a restricted set of…

Computation and Language · Computer Science 2026-01-27 Doreen Osmelak , Yang Xu , Michael Hahn , Kate McCurdy

Language Confusion is a phenomenon where Large Language Models (LLMs) generate text that is neither in the desired language, nor in a contextually appropriate language. This phenomenon presents a critical challenge in text generation by…

Computation and Language · Computer Science 2025-02-11 Yiyi Chen , Qiongxiu Li , Russa Biswas , Johannes Bjerva

Large language models (LLMs) have demonstrated significant progress in various natural language generation and understanding tasks. However, their linguistic generalization capabilities remain questionable, raising doubts about whether…

Non-native speakers show difficulties with spoken word processing. Many studies attribute these difficulties to imprecise phonological encoding of words in the lexical memory. We test an alternative hypothesis: that some of these…

Computation and Language · Computer Science 2021-03-12 Yevgen Matusevych , Herman Kamper , Thomas Schatz , Naomi H. Feldman , Sharon Goldwater

Morphological tasks use large multi-lingual datasets that organize words into inflection tables, which then serve as training and evaluation data for various tasks. However, a closer inspection of these data reveals profound…

Computation and Language · Computer Science 2022-10-20 Omer Goldman , Reut Tsarfaty

Language models learn and represent language differently than humans; they learn the form and not the meaning. Thus, to assess the success of language model explainability, we need to consider the impact of its divergence from a user's…

Computation and Language · Computer Science 2022-07-15 Rita Sevastjanova , Mennatallah El-Assady

Questions related to the evolution of language have recently known an impressive increase of interest (Briscoe, 2002). This short paper aims at questioning the scientific status of these models and their relations to attested data. We show…

Artificial Intelligence · Computer Science 2007-05-23 Thierry Poibeau

Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that…

Computation and Language · Computer Science 2017-06-02 Ivan Vulić , Nikola Mrkšić , Roi Reichart , Diarmuid Ó Séaghdha , Steve Young , Anna Korhonen

Tokenization is an important text preprocessing step to prepare input tokens for deep language models. WordPiece and BPE are de facto methods employed by important models, such as BERT and GPT. However, the impact of tokenization can be…

Computation and Language · Computer Science 2023-03-28 Cagri Toraman , Eyup Halit Yilmaz , Furkan Şahinuç , Oguzhan Ozcelik

Despite major advances in multilingual modeling, large quality disparities persist across languages. Besides the obvious impact of uneven training resources, typological properties have also been proposed to determine the intrinsic…

Computation and Language · Computer Science 2026-02-04 Vitalii Hirak , Jaap Jumelet , Arianna Bisazza

Are the predictions of humans and language models affected by similar things? Research suggests that while comprehending language, humans make predictions about upcoming words, with more predictable words being processed more easily.…

Computation and Language · Computer Science 2022-11-11 James A. Michaelov , Benjamin K. Bergen

Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of common sense reasoning ability. We show, however, with a new diagnostic…

Computation and Language · Computer Science 2020-05-08 Mostafa Abdou , Vinit Ravishankar , Maria Barrett , Yonatan Belinkov , Desmond Elliott , Anders Søgaard

Token representations influence the efficiency and adaptability of language models, yet conventional tokenization strategies impose rigid segmentation boundaries that do not adjust dynamically to evolving contextual relationships. The…

Computation and Language · Computer Science 2025-08-11 Alistair Dombrowski , Beatrix Engelhardt , Dimitri Fairbrother , Henry Evidail