English
Related papers

Related papers: Estimating Lexical Priors for Low-Frequency Syncre…

200 papers

Morphological analysis involves predicting the syntactic traits of a word (e.g. {POS: Noun, Case: Acc, Gender: Fem}). Previous work in morphological tagging improves performance for low-resource languages (LRLs) through cross-lingual…

Computation and Language · Computer Science 2018-07-12 Chaitanya Malaviya , Matthew R. Gormley , Graham Neubig

This article introduces a framework for evaluating statistical decisions under both prior ambiguity and likelihood misspecification. We begin with an ambiguity set - a frequentist model that pairs a possibly misspecified likelihood with…

Econometrics · Economics 2026-05-14 Karun Adusumilli

The unigram distribution is the non-contextual probability of finding a specific word form in a corpus. While of central importance to the study of language, it is commonly approximated by each word's sample frequency in the corpus. This…

Computation and Language · Computer Science 2021-06-07 Irene Nikkarinen , Tiago Pimentel , Damián E. Blasi , Ryan Cotterell

Most recent research in trainable part of speech taggers has explored stochastic tagging. While these taggers obtain high accuracy, linguistic information is captured indirectly, typically in tens of thousands of lexical and contextual…

cmp-lg · Computer Science 2008-02-03 Eric Brill

Spoken word recognition involves at least two basic computations. First is matching acoustic input to phonological categories (e.g. /b/, /p/, /d/). Second is activating words consistent with those phonological categories. Here we test the…

Computation and Language · Computer Science 2017-11-21 Laura Gwilliams , David Poeppel , Alec Marantz , Tal Linzen

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

In part of speech tagging by Hidden Markov Model, a statistical model is used to assign grammatical categories to words in a text. Early work in the field relied on a corpus which had been tagged by a human annotator to train the model.…

cmp-lg · Computer Science 2008-02-03 David Elworthy

We present a technique which complements Hidden Markov Models by incorporating some lexicalized states representing syntactically uncommon words. Our approach examines the distribution of transitions, selects the uncommon words, and makes…

Computation and Language · Computer Science 2007-05-23 Jin-Dong Kim , Sang-Zoo Lee , Hae-Chang Rim

Syntactic annotation of corpora in the form of part-of-speech (POS) tags is a key requirement for both linguistic research and subsequent automated natural language processing (NLP) tasks. This problem is commonly tackled using machine…

Computation and Language · Computer Science 2024-10-30 Stefan Heid , Marcel Wever , Eyke Hüllermeier

In foundational works of generative phonology it is claimed that subjects can reliably discriminate between possible but non-occurring words and words that could not be English. In this paper we examine the use of a probabilistic…

cmp-lg · Computer Science 2008-02-03 John Coleman , Janet Pierrehumbert

Complex classifiers may exhibit "embarassing" failures in cases where humans can easily provide a justified classification. Avoiding such failures is obviously of key importance. In this work, we focus on one such setting, where a label is…

Machine Learning · Computer Science 2019-06-14 Deborah Cohen , Amit Daniely , Amir Globerson , Gal Elidan

Language models trained on observed sequences are often described as learning the conditional distribution of the next token given previous tokens. This description is only conditionally correct. A model trained on realized token…

Computation and Language · Computer Science 2026-05-25 Francesco Corielli

Language models (LMs) estimate a probability distribution over strings in a natural language; these distributions are crucial for computing perplexity and surprisal in linguistics research. While we are usually concerned with measuring…

Computation and Language · Computer Science 2024-10-15 Tiago Pimentel , Clara Meister

We perform extensive Monte Carlo simulations to systematically compare the frequentist and Bayesian treatments of the Lomb--Scargle periodogram. The goal is to investigate whether the Bayesian period search is advantageous over the…

Instrumentation and Methods for Astrophysics · Physics 2025-01-22 Roman V. Baluev

This thesis presents a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The parser builds fully connected derivations incrementally, in a single pass from…

Computation and Language · Computer Science 2007-05-23 Brian Roark

Recently, there has been considerable progress on designing algorithms with provable guarantees -- typically using linear algebraic methods -- for parameter learning in latent variable models. But designing provable algorithms for inference…

Machine Learning · Computer Science 2016-05-30 Sanjeev Arora , Rong Ge , Frederic Koehler , Tengyu Ma , Ankur Moitra

The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that these pre-trained representations do encode some level of…

Computation and Language · Computer Science 2025-08-08 Karolina Stańczak , Lucas Torroba Hennigen , Adina Williams , Ryan Cotterell , Isabelle Augenstein

Modern language models predict the next token in the sequence by considering the past text through a powerful function such as attention. However, language models have no explicit mechanism that allows them to spend computation time for…

Computation and Language · Computer Science 2024-09-04 Florian Mai , Nathan Cornille , Marie-Francine Moens

We argue that some of the computational complexity associated with estimation of stochastic attribute-value grammars can be reduced by training upon an informative subset of the full training set. Results using the parsed Wall Street…

Computation and Language · Computer Science 2007-05-23 Miles Osborne

Inflection is an essential part of every human language's morphology, yet little effort has been made to unify linguistic theory and computational methods in recent years. Methods of string manipulation are used to infer inflectional…

Computation and Language · Computer Science 2020-09-07 Eleni Metheniti , Guenter Neumann , Josef van Genabith