中文
相关论文

相关论文: Prefix Probabilities from Stochastic Tree Adjoinin…

200 篇论文

Recently, pre-trained models with phonetic supervision have demonstrated their advantages for crosslingual speech recognition in data efficiency and information sharing across languages. However, a limitation is that a pronunciation lexicon…

音频与语音处理 · 电气工程与系统科学 2025-12-17 Saierdaer Yusuyin , Te Ma , Hao Huang , Zhijian Ou

Predictions of word-by-word conditional probabilities from Transformer-based language models are often evaluated to model the incremental processing difficulty of human readers. In this paper, we argue that there is a confound posed by the…

计算与语言 · 计算机科学 2024-10-01 Byung-Doh Oh , William Schuler

This work proposes an extension to Structured Grammatical Evolution (SGE) called Co-evolutionary Probabilistic Structured Grammatical Evolution (Co-PSGE). In Co-PSGE each individual in the population is composed by a grammar and a genotype,…

神经与进化计算 · 计算机科学 2022-04-20 Jessica Mégane , Nuno Lourenço , Penousal Machado

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word…

计算与语言 · 计算机科学 2019-02-22 Hainan Xu , Shuoyang Ding , Shinji Watanabe

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 · 计算机科学 2008-02-03 John Coleman , Janet Pierrehumbert

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…

计算与语言 · 计算机科学 2026-05-07 Yingshan Susan Wang , Linlu Qiu , Zhaofeng Wu , Roger P. Levy , Yoon Kim

The derivation trees of a tree adjoining grammar provide a first insight into the sentence semantics, and are thus prime targets for generation systems. We define a formalism, feature-based regular tree grammars, and a translation from…

计算与语言 · 计算机科学 2015-03-13 Sylvain Schmitz , Joseph Le Roux

We investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how…

计算与语言 · 计算机科学 2022-06-30 Arabella Sinclair , Jaap Jumelet , Willem Zuidema , Raquel Fernández

Usually, probabilistic automata and probabilistic grammars have crisp symbols as inputs, which can be viewed as the formal models of computing with values. In this paper, we first introduce probabilistic automata and probabilistic grammars…

人工智能 · 计算机科学 2007-05-23 Yongzhi Cao , Lirong Xia , Mingsheng Ying

An automatic word classification system has been designed which processes word unigram and bigram frequency statistics extracted from a corpus of natural language utterances. The system implements a binary top-down form of word clustering…

cmp-lg · 计算机科学 2016-08-31 John McMahon , F. J. Smith

The grammars used in grammar-based Genetic Programming (GP) methods have a significant impact on the quality of the solutions generated since they define the search space by restricting the solutions to its syntax. In this work, we propose…

神经与进化计算 · 计算机科学 2023-03-20 Jessica Mégane , Nuno Lourenço , Penousal Machado

Structured language models for speech recognition have been shown to remedy the weaknesses of n-gram models. All current structured language models are, however, limited in that they do not take into account dependencies between…

计算与语言 · 计算机科学 2007-05-23 Rens Bod

What have language models (LMs) learned about grammar? This question remains hotly debated, with major ramifications for linguistic theory. However, since probability and grammaticality are distinct notions in linguistics, it is not obvious…

计算与语言 · 计算机科学 2025-11-10 Jennifer Hu , Ethan Gotlieb Wilcox , Siyuan Song , Kyle Mahowald , Roger P. Levy

The problem of identifying a probabilistic context free grammar has two aspects: the first is determining the grammar's topology (the rules of the grammar) and the second is estimating probabilistic weights for each rule. Given the hardness…

计算机科学中的逻辑 · 计算机科学 2023-06-22 Dana Fisman , Dolav Nitay , Michal Ziv-Ukelson

Symbolic Regression (SR) allows for the discovery of scientific equations from data. To limit the large search space of possible equations, prior knowledge has been expressed in terms of formal grammars that characterize subsets of…

机器学习 · 计算机科学 2024-06-11 Tim Schneider , Amin Totounferoush , Wolfgang Nowak , Steffen Staab

Phrase-structure grammars are effective models for important syntactic and semantic aspects of natural languages, but can be computationally too demanding for use as language models in real-time speech recognition. Therefore, finite-state…

cmp-lg · 计算机科学 2008-02-03 Fernando C. N. Pereira , Rebecca N. Wright

A prefix normal word is a binary word with the property that no substring has more 1s than the prefix of the same length. This class of words is important in the context of binary jumbled pattern matching. In this paper we present an…

数据结构与算法 · 计算机科学 2014-06-23 Péter Burcsi , Gabriele Fici , Zsuzsanna Lipták , Frank Ruskey , Joe Sawada

Multiple algorithms are known for efficiently calculating the prefix probability of a string under a probabilistic context-free grammar (PCFG). Good algorithms for the problem have a runtime cubic in the length of the input string. However,…

形式语言与自动机理论 · 计算机科学 2025-05-09 Franz Nowak , Ryan Cotterell

The problem of identifying a probabilistic context free grammar has two aspects: the first is determining the grammar's topology (the rules of the grammar) and the second is estimating probabilistic weights for each rule. Given the hardness…

形式语言与自动机理论 · 计算机科学 2021-03-10 Dolav Nitay , Dana Fisman , Michal Ziv-Ukelson

Recent work has considered corpus-based or statistical approaches to the problem of prepositional phrase attachment ambiguity. Typically, ambiguous verb phrases of the form {v np1 p np2} are resolved through a model which considers values…

cmp-lg · 计算机科学 2008-02-03 Michael Collins , James Brooks