English
Related papers

Related papers: Modeling the Unigram Distribution

200 papers

Though there are some works on improving distributed word representations using lexicons, the improper overfitting of the words that have multiple meanings is a remaining issue deteriorating the learning when lexicons are used, which needs…

Computation and Language · Computer Science 2017-03-10 Yuanzhi Ke , Masafumi Hagiwara

Understanding what constitutes high-quality pre-training data remains a central question in language model training. In this work, we investigate whether benchmark performance is primarily driven by the degree of statistical pattern overlap…

Computation and Language · Computer Science 2026-02-12 Woojin Chung , Jeonghoon Kim

We introduce conditional unigram tokenization, a novel approach that extends unigram tokenization by conditioning target token probabilities on source-language tokens from parallel data. Given a fixed source tokenizer, our method learns a…

Computation and Language · Computer Science 2025-07-11 Gianluca Vico , Jindřinch Libovický

This paper (cmp-lg/yymmnnn) has been accepted for publication in the student session of EACL-95. It outlines ongoing work using statistical and unsupervised neural network methods for clustering words in untagged corpora. Such approaches…

cmp-lg · Computer Science 2008-02-03 Christopher C. Huckle

Grammaticality and likelihood are distinct notions in human language. Pretrained language models (LMs), which are probabilistic models of language fitted to maximize corpus likelihood, generate grammatically well-formed text and…

Computation and Language · Computer Science 2026-05-07 Yingshan Susan Wang , Linlu Qiu , Zhaofeng Wu , Roger P. Levy , Yoon Kim

Language modeling, a central task in natural language processing, involves estimating a probability distribution over strings. In most cases, the estimated distribution sums to 1 over all finite strings. However, in some pathological cases,…

Computation and Language · Computer Science 2023-08-23 Li Du , Lucas Torroba Hennigen , Tiago Pimentel , Clara Meister , Jason Eisner , Ryan Cotterell

A fundamental characteristic of natural language is the high rate at which speakers produce novel expressions. Because of this novelty, a heavy-tail of rare events accounts for a significant amount of the total probability mass of…

Computation and Language · Computer Science 2022-03-25 Benjamin LeBrun , Alessandro Sordoni , Timothy J. O'Donnell

The rate of occurrence of words is not uniform but varies from document to document. Despite this observation, parameters for conventional n-gram language models are usually derived using the assumption of a constant word rate. In this…

Computation and Language · Computer Science 2007-05-23 Yoshihiko Gotoh , Steve Renals

Chinese input recommendation plays an important role in alleviating human cost in typing Chinese words, especially in the scenario of mobile applications. The fundamental problem is to predict the conditional probability of the next word…

Computation and Language · Computer Science 2019-07-12 Hainan Zhang , Yanyan Lan , Jiafeng Guo , Jun Xu , Xueqi Cheng

A statistical model for segmentation and word discovery in continuous speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described. Results of empirical tests showing that the…

Computation and Language · Computer Science 2007-05-23 Anand Venkataraman

In the present paper we show that distributional information is particularly important when considering concept availability under implicit language learning conditions. Based on results from different behavioural experiments we argue that…

Computation and Language · Computer Science 2016-06-30 Dimitrios Alikaniotis , John N. Williams

Pre-trained word vectors are ubiquitous in Natural Language Processing applications. In this paper, we show how training word embeddings jointly with bigram and even trigram embeddings, results in improved unigram embeddings. We claim that…

Computation and Language · Computer Science 2019-04-11 Prakhar Gupta , Matteo Pagliardini , Martin Jaggi

In this paper, we investigate the problem of reasoning over natural language statements. Prior neural based approaches do not explicitly consider the inter-dependency among answers and their proofs. In this paper, we propose PRobr, a novel…

Computation and Language · Computer Science 2021-07-07 Changzhi Sun , Xinbo Zhang , Jiangjie Chen , Chun Gan , Yuanbin Wu , Jiaze Chen , Hao Zhou , Lei Li

Words can have multiple senses. Compositional distributional models of meaning have been argued to deal well with finer shades of meaning variation known as polysemy, but are not so well equipped to handle word senses that are…

Computation and Language · Computer Science 2020-10-13 Francois Meyer , Martha Lewis

This paper presents a number of experiments to model changes in a historical Portuguese corpus composed of literary texts for the purpose of temporal text classification. Algorithms were trained to classify texts with respect to their…

Computation and Language · Computer Science 2016-10-04 Marcos Zampieri , Shervin Malmasi , Mark Dras

When deriving contextualized word representations from language models, a decision needs to be made on how to obtain one for out-of-vocabulary (OOV) words that are segmented into subwords. What is the best way to represent these words with…

Computation and Language · Computer Science 2024-02-23 Aina Garí Soler , Matthieu Labeau , Chloé Clavel

Neural language models learn, to varying degrees of accuracy, the grammatical properties of natural languages. In this work, we investigate whether there are systematic sources of variation in the language models' accuracy. Focusing on…

Computation and Language · Computer Science 2020-10-28 Charles Yu , Ryan Sie , Nico Tedeschi , Leon Bergen

Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation (NMT). While sentences are usually converted into unique subword sequences, subword segmentation is potentially ambiguous and…

Computation and Language · Computer Science 2018-05-01 Taku Kudo

Recent work has found that contemporary language models such as transformers can become so good at next-word prediction that the probabilities they calculate become worse for predicting reading time. In this paper, we propose that this can…

Computation and Language · Computer Science 2026-03-11 James A. Michaelov , Roger P. Levy

Word embeddings predict a word from its neighbours by learning small, dense embedding vectors. In practice, this prediction corresponds to a semantic score given to the predicted word (or term weight). We present a novel model that, given a…

Information Retrieval · Computer Science 2019-06-04 Casper Hansen , Christian Hansen , Stephen Alstrup , Jakob Grue Simonsen , Christina Lioma