English
Related papers

Related papers: A Cognitive Regularizer for Language Modeling

200 papers

The uniform information density (UID) hypothesis posits a preference among language users for utterances structured such that information is distributed uniformly across a signal. While its implications on language production have been well…

Computation and Language · Computer Science 2021-09-27 Clara Meister , Tiago Pimentel , Patrick Haller , Lena Jäger , Ryan Cotterell , Roger Levy

The Uniform Information Density (UID) hypothesis posits that speakers tend to distribute information evenly across linguistic units to achieve efficient communication. Of course, information rate in texts and discourses is not perfectly…

Computation and Language · Computer Science 2024-10-22 Eleftheria Tsipidi , Franz Nowak , Ryan Cotterell , Ethan Wilcox , Mario Giulianelli , Alex Warstadt

The Uniform Information Density (UID) hypothesis posits that speakers are subject to a communicative pressure to distribute information evenly within utterances, minimising surprisal variance. While this hypothesis has been tested…

Computation and Language · Computer Science 2026-02-17 Matteo Gay , Coleman Haley , Mario Giulianelli , Edoardo Ponti

The Uniform Information Density (UID) hypothesis proposes that effective communication is achieved by maintaining a stable flow of information. In this work, we revisit this principle in the context of Large Language Model (LLM) reasoning,…

Artificial Intelligence · Computer Science 2026-04-20 Minju Gwak , Guijin Son , Jaehyung Kim

While natural languages differ widely in both canonical word order and word order flexibility, their word orders still follow shared cross-linguistic statistical patterns, often attributed to functional pressures. In the effort to identify…

Computation and Language · Computer Science 2023-07-11 Thomas Hikaru Clark , Clara Meister , Tiago Pimentel , Michael Hahn , Ryan Cotterell , Richard Futrell , Roger Levy

Large language models (LLMs) often solve problems using step-by-step Chain-of-Thought (CoT) reasoning, yet these intermediate steps are frequently unfaithful or hard to interpret. Inspired by the Uniform Information Density (UID) hypothesis…

Computation and Language · Computer Science 2025-10-21 Minju Gwak , Guijin Son , Jaehyung Kim

The uniform information density (UID) hypothesis proposes that speakers aim to distribute information evenly throughout a text, balancing production effort and listener comprehension difficulty. However, language typically does not maintain…

Computation and Language · Computer Science 2025-06-05 Eleftheria Tsipidi , Samuel Kiegeland , Franz Nowak , Tianyang Xu , Ethan Wilcox , Alex Warstadt , Ryan Cotterell , Mario Giulianelli

Speakers often have multiple ways to express the same meaning. The Uniform Information Density (UID) hypothesis suggests that speakers exploit this variability to maintain a consistent rate of information transmission during language…

Computation and Language · Computer Science 2025-10-27 Hailin Hao , Elsi Kaiser

Masked language modeling is a widely used method for learning language representations, where the model predicts a randomly masked word in each input. However, this approach typically considers only a single correct answer during training,…

Computation and Language · Computer Science 2025-04-10 Seunghyun Ji , Soowon Lee

Humans tend to follow the Uniform Information Density (UID) principle by distributing information evenly in utterances. We study if decoding algorithms implicitly follow this UID principle, and under what conditions adherence to UID might…

Computation and Language · Computer Science 2023-03-31 Saranya Venkatraman , He He , David Reitter

Deep learning has introduced significant improvements in many software analysis tasks. Although the Large Language Models (LLMs) based neural code models demonstrate commendable performance when trained and tested within the intra-project…

Artificial Intelligence · Computer Science 2024-03-12 Zhiming Li , Yanzhou Li , Tianlin Li , Mengnan Du , Bozhi Wu , Yushi Cao , Junzhe Jiang , Yang Liu

The Uniform Information Density (UID) hypothesis posits that speakers optimize the communicative properties of their utterances by avoiding spikes in information, thereby maintaining a relatively uniform information profile over time. This…

Computation and Language · Computer Science 2024-06-03 Ella Rabinovich

Large language models (LLMs) exhibit pronounced social biases. Output-level or data-optimization--based debiasing methods cannot fully resolve these biases, and many prior works have shown that biases are embedded in internal…

Computation and Language · Computer Science 2026-03-20 Zikang Ding , Junchi Yao , Junhao Li , Yi Zhang , Wenbo Jiang , Hongbo Liu , Lijie Hu

Regularization occurs when the output a learner produces is less variable than the linguistic data they observed. In an artificial language learning experiment, we show that there exist at least two independent sources of regularization…

Computation and Language · Computer Science 2018-10-22 Vanessa Ferdinand , Simon Kirby , Kenny Smith

Universal Dependencies (UD), while widely regarded as the most successful linguistic framework for cross-lingual syntactic representation, remains underexplored in terms of its effectiveness. This paper addresses this gap by integrating UD…

Computation and Language · Computer Science 2025-06-06 Wenxi Li

Data augmentation is used in machine learning to make the classifier invariant to label-preserving transformations. Usually this invariance is only encouraged implicitly by including a single augmented input during training. However,…

Machine Learning · Computer Science 2022-03-08 Aleksander Botev , Matthias Bauer , Soham De

Although prior work in computer vision has shown strong correlations between in-distribution (ID) and out-of-distribution (OOD) accuracies, such relationships remain underexplored in audio-based models. In this study, we investigate how…

Machine Learning · Computer Science 2025-08-01 Anaïs Baranger , Lucas Maison

After just a few hundred training updates, a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, making it difficult to estimate the probability distribution…

Computation and Language · Computer Science 2023-06-26 Clara Meister , Wojciech Stokowiec , Tiago Pimentel , Lei Yu , Laura Rimell , Adhiguna Kuncoro

Recurrent neural networks (RNNs) are powerful models of sequential data. They have been successfully used in domains such as text and speech. However, RNNs are susceptible to overfitting; regularization is important. In this paper we…

Machine Learning · Statistics 2018-07-16 Adji B. Dieng , Rajesh Ranganath , Jaan Altosaar , David M. Blei

Spoken language identification (LID) technologies have improved in recent years from discriminating largely distinct languages to discriminating highly similar languages or even dialects of the same language. One aspect that has been mostly…

Audio and Speech Processing · Electrical Eng. & Systems 2020-01-30 Andrew Titus , Jan Silovsky , Nanxin Chen , Roger Hsiao , Mary Young , Arnab Ghoshal
‹ Prev 1 2 3 10 Next ›