English
Related papers

Related papers: How Well Does First-Token Entropy Approximate Word…

200 papers

We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the…

Computation and Language · Computer Science 2018-06-11 Ben Athiwaratkun , Andrew Gordon Wilson , Anima Anandkumar

Language models (LMs) are statistical models trained to assign probability to human-generated text. As such, it is reasonable to question whether they approximate linguistic variability exhibited by humans well. This form of statistical…

Computation and Language · Computer Science 2024-03-19 Evgenia Ilia , Wilker Aziz

An increase in the novelty of news predicts negative stock market returns and negative macroeconomic outcomes over the next year. We quantify news novelty - changes in the distribution of news text - through an entropy measure, calculated…

General Finance · Quantitative Finance 2023-09-12 Paul Glasserman , Harry Mamaysky , Jimmy Qin

In signal analysis and synthesis, linear approximation theory considers a linear decomposition of any given signal in a set of atoms, collected into a so-called dictionary. Relevant sparse representations are obtained by relaxing the…

Information Theory · Computer Science 2014-11-04 Paul Honeine

Estimating the p-th frequency moment of data stream is a very heavily studied problem. The problem is actually trivial when p = 1, assuming the strict Turnstile model. The sample complexity of our proposed algorithm is essentially O(1) near…

Data Structures and Algorithms · Computer Science 2015-03-14 Ping Li

Recent research demonstrates the effectiveness of using pretrained language models (PLM) to improve dense retrieval and multilingual dense retrieval. In this work, we present a simple but effective monolingual pretraining task called…

Information Retrieval · Computer Science 2022-06-08 Ning Wu , Yaobo Liang , Houxing Ren , Linjun Shou , Nan Duan , Ming Gong , Daxin Jiang

The principle of maximum entropy provides a useful method for inferring statistical mechanics models from observations in correlated systems, and is widely used in a variety of fields where accurate data are available. While the assumptions…

Neurons and Cognition · Quantitative Biology 2017-06-02 Ulisse Ferrari , Tomoyuki Obuchi , Thierry Mora

Audio captioning quality metrics which are typically borrowed from the machine translation and image captioning areas measure the degree of overlap between predicted tokens and gold reference tokens. In this work, we consider a metric…

Multimedia · Computer Science 2023-03-06 Rehana Mahfuz , Yinyi Guo , Erik Visser

A fundamental result in psycholinguistics is that less predictable words take a longer time to process. One theoretical explanation for this finding is Surprisal Theory (Hale, 2001; Levy, 2008), which quantifies a word's predictability as…

Computation and Language · Computer Science 2025-04-15 Ethan Gotlieb Wilcox , Tiago Pimentel , Clara Meister , Ryan Cotterell , Roger P. Levy

There are different ways of measuring diversity in complex systems. In particular, in language, lexical diversity is characterized in terms of the type-token ratio and the word entropy. We here investigate both diversity metrics in six…

Computation and Language · Computer Science 2025-07-16 Pablo Rosillo-Rodes , Maxi San Miguel , David Sanchez

Compression of documents, images, audios and videos have been traditionally practiced to increase the efficiency of data storage and transfer. However, in order to process or carry out any analytical computations, decompression has become…

Computer Vision and Pattern Recognition · Computer Science 2014-04-09 P. Nagabhushan , Mohammed Javed , B. B. Chaudhuri

Understanding the importance of the inputs on the output is useful across many tasks. This work provides an information-theoretic framework to analyse the influence of inputs for text classification tasks. Natural language processing (NLP)…

Computation and Language · Computer Science 2024-02-05 Luran Wang , Mark Gales , Vatsal Raina

This paper explores the information-theoretic measure entropy to detect metaphoric change, transferring ideas from hypernym detection to research on language change. We also build the first diachronic test set for German as a standard for…

Computation and Language · Computer Science 2017-06-16 Dominik Schlechtweg , Stefanie Eckmann , Enrico Santus , Sabine Schulte im Walde , Daniel Hole

Similarity-sensitive entropy measures the uncertainty of a probability law relative to a similarity kernel that encodes the distinguishability between states. We develop a measure-theoretic treatment covering both finite similarity matrices…

Probability · Mathematics 2026-05-29 Joseph Samuel Miller

The widely-used automatic evaluation metrics cannot adequately reflect the fluency of the translations. The n-gram-based metrics, like BLEU, limit the maximum length of matched fragments to n and cannot catch the matched fragments longer…

Computation and Language · Computer Science 2016-11-07 Hui Yu , Xiaofeng Wu , Wenbin Jiang , Qun Liu , Shouxun Lin

We identify the similarity between two words in English by casting the task as machine translation performance prediction (MTPP) between the words given the context and the distance between their similarities. We use referential translation…

Computation and Language · Computer Science 2024-07-10 Ergun Biçici

The occurrence of unknown words in texts significantly hinders reading comprehension. To improve accessibility for specific target populations, computational modelling has been applied to identify complex words in texts and substitute them…

Computation and Language · Computer Science 2023-03-10 Kai North , Marcos Zampieri , Matthew Shardlow

Perplexity (per word) is the most widely used metric for evaluating language models. Despite this, there has been no dearth of criticism for this metric. Most of these criticisms center around lack of correlation with extrinsic metrics like…

Computation and Language · Computer Science 2016-04-01 Kushal Arora , Anand Rangarajan

Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-13 Rogier C. van Dalen , Shucong Zhang , Titouan Parcollet , Sourav Bhattacharya

Predicting context-dependent and non-literal utterances like sarcastic and ironic expressions still remains a challenging task in NLP, as it goes beyond linguistic patterns, encompassing common sense and shared knowledge as crucial…

Computation and Language · Computer Science 2018-09-27 Suzana Ilić , Edison Marrese-Taylor , Jorge A. Balazs , Yutaka Matsuo
‹ Prev 1 8 9 10 Next ›