English
Related papers

Related papers: Self-Normalization Properties of Language Modeling

200 papers

It's been said that "Language Models are Unsupervised Multitask Learners." Indeed, self-supervised language models trained on "positive" examples of English text generalize in desirable ways to many natural language tasks. But if such…

Computation and Language · Computer Science 2020-10-23 Michael L. Wick , Kate Silverstein , Jean-Baptiste Tristan , Adam Pocock , Mark Johnson

One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer,…

Artificial Intelligence · Computer Science 2025-11-20 Alessio Pellegrino , Jacopo Mauro

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

Computation and Language · Computer Science 2021-04-15 Nikunj Saunshi , Sadhika Malladi , Sanjeev Arora

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

Training large vocabulary Neural Network Language Models (NNLMs) is a difficult task due to the explicit requirement of the output layer normalization, which typically involves the evaluation of the full softmax function over the complete…

Computation and Language · Computer Science 2017-08-23 Youssef Oualil , Dietrich Klakow

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

Capitalization normalization (truecasing) is the task of restoring the correct case (uppercase or lowercase) of noisy text. We propose a fast, accurate and compact two-level hierarchical word-and-character-based recurrent neural network…

Computation and Language · Computer Science 2022-02-17 Hao Zhang , You-Chi Cheng , Shankar Kumar , W. Ronny Huang , Mingqing Chen , Rajiv Mathews

Neural language models typically tokenise input text into sub-word units to achieve an open vocabulary. The standard approach is to use a single canonical tokenisation at both train and test time. We suggest that this approach is…

Computation and Language · Computer Science 2021-09-22 Kris Cao , Laura Rimell

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring…

Computation and Language · Computer Science 2021-09-10 Michael Mendelson , Yonatan Belinkov

Neural networks have been shown to improve performance across a range of natural-language tasks. However, designing and training them can be complicated. Frequently, researchers resort to repeated experimentation to pick optimal settings.…

Computation and Language · Computer Science 2015-08-21 Kenton Murray , David Chiang

Native speakers can judge whether a sentence is an acceptable instance of their language. Acceptability provides a means of evaluating whether computational language models are processing language in a human-like manner. We test the ability…

Computation and Language · Computer Science 2019-10-11 Wang Jing , M. A. Kelly , David Reitter

In recent years, neural machine translation (NMT) has become the dominant approach in automated translation. However, like many other deep learning approaches, NMT suffers from overfitting when the amount of training data is limited. This…

Computation and Language · Computer Science 2019-10-01 Inigo Jauregi Unanue , Ehsan Zare Borzeshi , Massimo Piccardi

Noise-contrastive estimation (NCE) is a statistically consistent method for learning unnormalized probabilistic models. It has been empirically observed that the choice of the noise distribution is crucial for NCE's performance. However,…

Machine Learning · Computer Science 2021-10-22 Bingbin Liu , Elan Rosenfeld , Pradeep Ravikumar , Andrej Risteski

Speech evaluation measures a learners oral proficiency using automatic models. Corpora for training such models often pose sparsity challenges given that there often is limited scored data from teachers, in addition to the score…

Artificial Intelligence · Computer Science 2024-09-24 Huayun Zhang , Jeremy H. M. Wong , Geyu Lin , Nancy F. Chen

The detection and normalization of temporal expressions is an important task and preprocessing step for many applications. However, prior work on normalization is rule-based, which severely limits the applicability in real-world…

Computation and Language · Computer Science 2023-02-13 Lukas Lange , Jannik Strötgen , Heike Adel , Dietrich Klakow

We theoretically investigate the phenomena of generalization and memorization in diffusion models. Empirical studies suggest that these phenomena are influenced by model complexity and the size of the training dataset. In our experiments,…

Machine Learning · Computer Science 2025-10-09 Anand Jerry George , Rodrigo Veiga , Nicolas Macris

With the prevalence of large-scale pretrained vision-language models (VLMs), such as CLIP, soft-prompt tuning has become a popular method for adapting these models to various downstream tasks. However, few works delve into the inherent…

Computer Vision and Pattern Recognition · Computer Science 2024-08-28 Shuai Fu , Xiequn Wang , Qiushi Huang , Yu Zhang

A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By…

Machine Learning · Computer Science 2020-06-16 Daniel Chiu , Franklyn Wang , Scott Duke Kominers

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for simple, surface-level textual relations over full semantic complexity of the problem. This proposal investigates a…

Computation and Language · Computer Science 2022-06-20 Michal Štefánik

Readability assessment aims to automatically classify text by the level appropriate for learning readers. Traditional approaches to this task utilize a variety of linguistically motivated features paired with simple machine learning models.…

Computation and Language · Computer Science 2020-08-04 Tovly Deutsch , Masoud Jasbi , Stuart Shieber