English
Related papers

Related papers: Zipfian Whitening

200 papers

Words in natural language follow a Zipfian distribution whereby some words are frequent but most are rare. Learning representations for words in the "long tail" of this distribution requires enormous amounts of data. Representations of rare…

Machine Learning · Computer Science 2018-03-08 Dzmitry Bahdanau , Tom Bosc , Stanisław Jastrzębski , Edward Grefenstette , Pascal Vincent , Yoshua Bengio

Tokenization is a fundamental step in natural language processing (NLP) and other sequence modeling domains, where the choice of vocabulary size significantly impacts model performance. Despite its importance, selecting an optimal…

Machine Learning · Computer Science 2025-07-31 Yanjin He , Qingkai Zeng , Meng Jiang

Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of words do not usually appear frequently or at all in the…

Computation and Language · Computer Science 2018-11-14 Victor Prokhorov , Mohammad Taher Pilehvar , Dimitri Kartsaklis , Pietro Lio , Nigel Collier

Natural languages are full of rules and exceptions. One of the most famous quantitative rules is Zipf's law which states that the frequency of occurrence of a word is approximately inversely proportional to its rank. Though this `law' of…

Computation and Language · Computer Science 2015-05-27 Jake Ryland Williams , James P. Bagrow , Christopher M. Danforth , Peter Sheridan Dodds

Zipf's law predicts a power-law relationship between word rank and frequency in language communication systems and has been widely reported in a variety of natural language processing applications. However, the emergence of natural language…

Computation and Language · Computer Science 2018-12-05 Bohdan Khomtchouk , Shyam Sudhakaran

The prevailing maximum likelihood estimators for inferring power law models from rank-frequency data are biased. The source of this bias is an inappropriate likelihood function. The correct likelihood function is derived and shown to be…

Applications · Statistics 2021-07-27 Charlie Pilgrim , Thomas T Hills

The formation of sentences is a highly structured and history-dependent process. The probability of using a specific word in a sentence strongly depends on the 'history' of word-usage earlier in that sentence. We study a simple…

Physics and Society · Physics 2015-05-28 Stefan Thurner , Rudolf Hanel , Bo Liu , Bernat Corominas-Murtra

Recent studies have investigated siamese network architectures for learning invariant speech representations using same-different side information at the word level. Here we investigate systematically an often ignored component of siamese…

Computation and Language · Computer Science 2018-08-24 Rachid Riad , Corentin Dancette , Julien Karadayi , Neil Zeghidour , Thomas Schatz , Emmanuel Dupoux

We checked that the distribution of words in text should uniform, which gives Heaps' law as natural result, that is, the number of types of words can be expressed as a power law of the number of tokens within text. We developed a…

Physics and Society · Physics 2025-04-16 Kim Chol-jun

Word embeddings learnt from large corpora have been adopted in various applications in natural language processing and served as the general input representations to learning systems. Recently, a series of post-processing methods have been…

Machine Learning · Computer Science 2019-10-25 Shuai Tang , Mahta Mousavi , Virginia R. de Sa

The frequencies at which individual words occur across languages follow power law distributions, a pattern of findings known as Zipf's law. A vast literature argues over whether this serves to optimize the efficiency of human communication,…

Computation and Language · Computer Science 2020-01-16 Michael Ramscar

According to Zipf's meaning-frequency law, words that are more frequent tend to have more meanings. Here it is shown that a linear dependency between the frequency of a form and its number of meanings is found in a family of models of…

Computation and Language · Computer Science 2016-10-14 Ramon Ferrer-i-Cancho

Despite the recent successes of deep learning in natural language processing (NLP), there remains widespread usage of and demand for techniques that do not rely on machine learning. The advantage of these techniques is their…

Computation and Language · Computer Science 2020-12-04 Adam Hare , Yu Chen , Yinan Liu , Zhenming Liu , Christopher G. Brinton

Pre-trained language models such as BERT have become a more common choice of natural language processing (NLP) tasks. Research in word representation shows that isotropic embeddings can significantly improve performance on downstream tasks.…

Computation and Language · Computer Science 2021-08-30 Yuxin Liang , Rui Cao , Jie Zheng , Jie Ren , Ling Gao

Zipf's law is found when the vocabulary of long written texts is ranked according to the frequency of word occurrences, establishing a power-law decay for the frequency vs rank relation. This law is a robust statistical property observed…

Physics and Society · Physics 2020-02-17 Juan Ignacio Perotti , Orlando Vito Billoni

Zipf's law has been found in many human-related fields, including language, where the frequency of a word is persistently found as a power law function of its frequency rank, known as Zipf's law. However, there is much dispute whether it is…

Computation and Language · Computer Science 2018-07-06 Shuiyuan Yu , Chunshan Xu , Haitao Liu

Word embeddings resulting from neural language models have been shown to be successful for a large variety of NLP tasks. However, such architecture might be difficult to train and time-consuming. Instead, we propose to drastically simplify…

Computation and Language · Computer Science 2017-01-05 Rémi Lebret , Ronan Collobert

Low isotropy in an embedding space impairs performance on tasks involving semantic inference. Our study investigates the impact of isotropy on semantic code search performance and explores post-processing techniques to mitigate this issue.…

Computation and Language · Computer Science 2024-11-28 Andor Diera , Lukas Galke , Ansgar Scherp

In this study, we investigate whether speech symbols, learned through deep learning, follow Zipf's law, akin to natural language symbols. Zipf's law is an empirical law that delineates the frequency distribution of words, forming…

Computation and Language · Computer Science 2023-09-19 Shinnosuke Takamichi , Hiroki Maeda , Joonyong Park , Daisuke Saito , Hiroshi Saruwatari

The article introduces corrections to Zipf's and Heaps' laws based on systematic models of the proportion of hapaxes, i.e., words that occur once. The derivation rests on two assumptions: The first one is the standard urn model which…

Computation and Language · Computer Science 2025-05-27 Łukasz Dębowski
‹ Prev 1 2 3 10 Next ›