English
Related papers

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

200 papers

The rapid adaptation ability of auto-regressive foundation models is often attributed to the diversity of their pre-training data. This is because, from a Bayesian standpoint, minimizing prediction error in such settings requires…

Machine Learning · Computer Science 2025-06-23 Leo Gagnon , Eric Elmoznino , Sarthak Mittal , Tom Marty , Tejas Kasetty , Dhanya Sridhar , Guillaume Lajoie

This paper explores morpho-syntactic ambiguities for French to develop a strategy for part-of-speech disambiguation that a) reflects the complexity of French as an inflected language, b) optimizes the estimation of probabilities, c) allows…

cmp-lg · Computer Science 2007-05-23 Evelyne Tzoukermann , Dragomir R. Radev , William A. Gale

Lexical ambiguities naturally arise in languages. We present Lamb, a lexical analyzer that produces a lexical analysis graph describing all the possible sequences of tokens that can be found within the input string. Parsers can process such…

Computation and Language · Computer Science 2012-03-01 Luis Quesada , Fernando Berzal , Francisco J. Cortijo

Research into the automatic acquisition of lexical information from corpora is starting to produce large-scale computational lexicons containing data on the relative frequencies of subcategorisation alternatives for individual verbal…

cmp-lg · Computer Science 2007-05-23 John Carroll , Guido Minnen , Ted Briscoe

Word embeddings allow natural language processing systems to share statistical information across related words. These embeddings are typically based on distributional statistics, making it difficult for them to generalize to rare or unseen…

Computation and Language · Computer Science 2016-09-27 Parminder Bhatia , Robert Guthrie , Jacob Eisenstein

Lexical ambiguity makes it difficult to compute various useful statistics of a corpus. A given word form might represent any of several morphological feature bundles. One can, however, use unsupervised learning (as in EM) to fit a model…

Computation and Language · Computer Science 2020-02-26 Ryan Cotterell , Christo Kirov , Sabrina J. Mielke , Jason Eisner

In this paper I propose a new way of measuring linguistic productivity that objectively assesses the ability of an affix to be used to coin new complex words and, unlike other popular measures, is not directly dependent upon token…

Computation and Language · Computer Science 2023-08-25 Sergei Monakhov

In natural language processing (NLP), the likelihood ratios (LRs) of N-grams are often estimated from the frequency information. However, a corpus contains only a fraction of the possible N-grams, and most of them occur infrequently. Hence,…

Computation and Language · Computer Science 2022-04-15 Masato Kikuchi , Mitsuo Yoshida , Kyoji Umemura , Tadachika Ozono

Suffix prediction of business processes forecasts the remaining sequence of events until process completion. Current approaches focus on predicting the most likely suffix, representing a single scenario. However, when the future course of a…

Machine Learning · Computer Science 2025-06-09 Henryk Mustroph , Michel Kunkler , Stefanie Rinderle-Ma

How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).When used as predictors of processing effort, LM probabilities outperform probabilities…

Computation and Language · Computer Science 2026-05-27 Sathvik Nair , Byung-Doh Oh

Log-linear models provide a statistically sound framework for Stochastic ``Unification-Based'' Grammars (SUBGs) and stochastic versions of other kinds of grammars. We describe two computationally-tractable ways of estimating the parameters…

Computation and Language · Computer Science 2007-05-23 Mark Johnson , Stuart Geman , Stephen Canon , Zhiyi Chi , Stefan Riezler

This paper describes the results of some experiments exploring statistical methods to infer syntactic behavior of words and morphemes from a raw corpus in an unsupervised fashion. It shares certain points in common with Brown et al (1992)…

Computation and Language · Computer Science 2007-05-23 Mikhail Belkin , John Goldsmith

We propose a new model for multi-token prediction in transformers, aiming to enhance sampling efficiency without compromising accuracy. Motivated by recent work that predicts the probabilities of subsequent tokens using multiple heads, we…

Machine Learning · Computer Science 2025-02-11 Artem Basharin , Andrei Chertkov , Ivan Oseledets

Functional Distributional Semantics provides a computationally tractable framework for learning truth-conditional semantics from a corpus. Previous work in this framework has provided a probabilistic version of first-order logic, recasting…

Computation and Language · Computer Science 2020-06-05 Guy Emerson

We show that the imperceptibility of several existing linguistic steganographic systems (Fang et al., 2017; Yang et al., 2018) relies on implicit assumptions on statistical behaviors of fluent text. We formally analyze them and empirically…

Computation and Language · Computer Science 2019-07-31 Falcon Z. Dai , Zheng Cai

Temporary syntactic ambiguities arise when the beginning of a sentence is compatible with multiple syntactic analyses. We inspect to which extent neural language models (LMs) exhibit uncertainty over such analyses when processing…

Computation and Language · Computer Science 2021-09-17 Laura Aina , Tal Linzen

Many segmentation tasks, such as medical image segmentation or future state prediction, are inherently ambiguous, meaning that multiple predictions are equally correct. Current methods typically rely on generative models to capture this…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Sebastian Gerard , Josephine Sullivan

In many applications of natural language processing (NLP) it is necessary to determine the likelihood of a given word combination. For example, a speech recognizer may need to determine which of the two word combinations ``eat a peach'' and…

Computation and Language · Computer Science 2007-05-23 Ido Dagan , Lillian Lee , Fernando C. N. Pereira

We describe an extension of Earley's parser for stochastic context-free grammars that computes the following quantities given a stochastic context-free grammar and an input string: a) probabilities of successive prefixes being generated by…

cmp-lg · Computer Science 2008-02-03 Andreas Stolcke

The described tagger is based on a hidden Markov model and uses tags composed of features such as part-of-speech, gender, etc. The contextual probability of a tag (state transition probability) is deduced from the contextual probabilities…

cmp-lg · Computer Science 2008-02-03 Andre Kempe
‹ Prev 1 2 3 10 Next ›