English
Related papers

Related papers: Language Design as Information Renormalization

200 papers

In this work, we propose a new language modeling paradigm that has the ability to perform both prediction and moderation of information flow at multiple granularities: neural lattice language models. These models construct a lattice of…

Computation and Language · Computer Science 2018-03-15 Jacob Buckman , Graham Neubig

Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…

Computation and Language · Computer Science 2019-04-05 Inigo Jauregi Unanue , Ehsan Zare Borzeshi , Nazanin Esmaili , Massimo Piccardi

We describe a framework for inducing probabilistic grammars from corpora of positive samples. First, samples are {\em incorporated} by adding ad-hoc rules to a working grammar; subsequently, elements of the model (such as states or…

cmp-lg · Computer Science 2022-02-28 Andreas Stolcke , Stephen M. Omohundro

Decoding language from neural signals holds considerable theoretical and practical importance. Previous research has indicated the feasibility of decoding text or speech from invasive neural signals. However, when using non-invasive neural…

Human-Computer Interaction · Computer Science 2023-09-15 Bo Wang , Xiran Xu , Longxiang Zhang , Boda Xiao , Xihong Wu , Jing Chen

Many complex generative systems use languages to create structured objects. We consider a model of random languages, defined by weighted context-free grammars. As the distribution of grammar weights broadens, a transition is found from a…

Disordered Systems and Neural Networks · Physics 2019-04-03 E. DeGiuli

Process model extraction (PME) is a recently emerged interdiscipline between natural language processing (NLP) and business process management (BPM), which aims to extract process models from textual descriptions. Previous process…

Computation and Language · Computer Science 2020-03-23 Chen Qian , Lijie Wen , Akhil Kumar , Leilei Lin , Li Lin , Zan Zong , Shuang Li , Jianmin Wang

Pretrained language model (PLM) hidden states are frequently employed as contextual word embeddings (CWE): high-dimensional representations that encode semantic information given linguistic context. Across many areas of computational…

Computation and Language · Computer Science 2024-08-09 Jacob A. Matthews , John R. Starr , Marten van Schijndel

Word embeddings are ubiquitous in NLP and information retrieval, but it is unclear what they represent when the word is polysemous. Here it is shown that multiple word senses reside in linear superposition within the word embedding and…

Computation and Language · Computer Science 2018-12-10 Sanjeev Arora , Yuanzhi Li , Yingyu Liang , Tengyu Ma , Andrej Risteski

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

Computation and Language · Computer Science 2025-03-03 Rachel Wicks , Kartik Ravisankar , Xinchen Yang , Philipp Koehn , Matt Post

With distributed machine learning being a prominent technique for large-scale machine learning tasks, communication complexity has become a major bottleneck for speeding up training and scaling up machine numbers. In this paper, we propose…

Machine Learning · Computer Science 2023-09-26 Pengyun Yue , Hanzhen Zhao , Cong Fang , Di He , Liwei Wang , Zhouchen Lin , Song-chun Zhu

We introduce Telegraph English (TE), a prompt-compression protocol that rewrites natural language into a symbol-rich, formally-structured dialect. Where token-deletion methods such as LLMLingua-2 train a classifier to delete low-importance…

Computation and Language · Computer Science 2026-05-07 Mikhail L. Arbuzov , Sisong Bei , Ziwei Dong , Dmitri Kalaev , Alexey A. Shvets

Despite it being the cornerstone of BPE, the most common tokenization algorithm, the importance of compression in the tokenization process is still unclear. In this paper, we argue for the theoretical importance of compression, that can be…

Computation and Language · Computer Science 2024-06-25 Omer Goldman , Avi Caciularu , Matan Eyal , Kris Cao , Idan Szpektor , Reut Tsarfaty

Large language models (LLMs) are widely recognized for their exceptional capacity to capture semantics meaning. Yet, there remains no established metric to quantify this capability. In this work, we introduce a quantitative metric,…

Computation and Language · Computer Science 2024-12-19 Hang Chen , Xinyu Yang , Jiaying Zhu , Wenya Wang

To ensure large language models (LLMs) are used safely, one must reduce their propensity to hallucinate or to generate unacceptable answers. A simple and often used strategy is to first let the LLM generate multiple hypotheses and then…

Computation and Language · Computer Science 2025-02-12 António Farinhas , Haau-Sing Li , André F. T. Martins

In the literature, tensors have been effectively used for capturing the context information in language models. However, the existing methods usually adopt relatively-low order tensors, which have limited expressive power in modeling…

Computation and Language · Computer Science 2019-02-01 Lipeng Zhang , Peng Zhang , Xindian Ma , Shuqin Gu , Zhan Su , Dawei Song

Data noising is an effective technique for regularizing neural network models. While noising is widely adopted in application domains such as vision and speech, commonly used noising primitives have not been developed for discrete…

Machine Learning · Computer Science 2017-03-09 Ziang Xie , Sida I. Wang , Jiwei Li , Daniel Lévy , Aiming Nie , Dan Jurafsky , Andrew Y. Ng

By positing a relationship between naturalistic reading times and information-theoretic surprisal, surprisal theory (Hale, 2001; Levy, 2008) provides a natural interface between language models and psycholinguistic models. This paper…

Computation and Language · Computer Science 2021-06-25 Yiding Hao , Simon Mendelsohn , Rachel Sterneck , Randi Martinez , Robert Frank

Representing molecular structures effectively in chemistry remains a challenging task. Language models and graph-based models are extensively utilized within this domain, consistently achieving state-of-the-art results across an array of…

Machine Learning · Computer Science 2025-05-27 Nikolai Rekut , Alexey Orlov , Klea Ziu , Elizaveta Starykh , Martin Takac , Aleksandr Beznosikov

To extract essential information from complex data, computer scientists have been developing machine learning models that learn low-dimensional representation mode. From such advances in machine learning research, not only computer…

Artificial Intelligence · Computer Science 2024-06-18 Akira Matsui , Emilio Ferrara

We present a cross-linguistic study that aims to quantify vowel harmony using data-driven computational modeling. Concretely, we define an information-theoretic measure of harmonicity based on the predictability of vowels in a natural…

Computation and Language · Computer Science 2023-08-10 Julius Steuer , Badr Abdullah , Johann-Mattis List , Dietrich Klakow