English
Related papers

Related papers: Grammar Specialization through Entropy Thresholds

200 papers

An attractive mechanism to specify global constraints in rostering and other domains is via formal languages. For instance, the Regular and Grammar constraints specify constraints in terms of the languages accepted by an automaton and a…

Artificial Intelligence · Computer Science 2009-03-04 George Katsirelos , Nina Narodytska , Toby Walsh

This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture…

Computation and Language · Computer Science 2014-01-23 Trevor Anthony Cohn , Mirella Lapata

For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given sentences. By substituting complex words with simple…

Computation and Language · Computer Science 2021-01-01 Rongzhou Bao , Jiayi Wang , Zhuosheng Zhang , Hai Zhao

Learning word embeddings has received a significant amount of attention recently. Often, word embeddings are learned in an unsupervised manner from a large collection of text. The genre of the text typically plays an important role in the…

Computation and Language · Computer Science 2019-02-04 Wei Yang , Wei Lu , Vincent W. Zheng

In this letter we present a very general method to extract information from a generic string of characters, e.g. a text, a DNA sequence or a time series. Based on data-compression techniques, its key point is the computation of a suitable…

Statistical Mechanics · Physics 2009-11-07 Dario Benedetto , Emanuele Caglioti , Vittorio Loreto

A criterion for pruning parameters from N-gram backoff language models is developed, based on the relative entropy between the original and the pruned model. It is shown that the relative entropy resulting from pruning a single N-gram can…

Computation and Language · Computer Science 2007-05-23 A. Stolcke

Descriptive grammars are highly valuable, but writing them is time-consuming and difficult. Furthermore, while linguists typically use corpora to create them, grammar descriptions often lack quantitative data. As for formal grammars, they…

Computation and Language · Computer Science 2024-03-27 Santiago Herrera , Caio Corro , Sylvain Kahane

Modern natural language understanding models depend on pretrained subword embeddings, but applications may need to reason about words that were never or rarely seen during pretraining. We show that examples that depend critically on a rarer…

Computation and Language · Computer Science 2021-03-08 Christopher Malon

This paper presents a method for the automatic extraction of subgrammars to control and speeding-up natural language generation NLG. The method is based on explanation-based learning (EBL). The main advantage for the proposed new method for…

cmp-lg · Computer Science 2007-05-23 Guenter Neumann

We study the problem of entropy calibration, which asks whether a language model's entropy over generations matches its log loss on human text. Past work found that models are miscalibrated, with entropy per step increasing as generations…

Computation and Language · Computer Science 2026-01-14 Steven Cao , Gregory Valiant , Percy Liang

A series of recent papers has used a parsing algorithm due to Shen et al. (2018) to recover phrase-structure trees based on proxies for "syntactic depth." These proxy depths are obtained from the representations learned by recurrent…

Computation and Language · Computer Science 2019-09-23 Chris Dyer , Gábor Melis , Phil Blunsom

Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training. By extending previous work on compositional generalization in semantic parsing, we…

Computation and Language · Computer Science 2024-06-10 Sondre Wold , Étienne Simon , Lucas Georges Gabriel Charpentier , Egor V. Kostylev , Erik Velldal , Lilja Øvrelid

Text classification is one of the most widely studied tasks in natural language processing. Motivated by the principle of compositionality, large multilayer neural network models have been employed for this task in an attempt to effectively…

Computation and Language · Computer Science 2018-08-07 Devendra Singh Sachan , Manzil Zaheer , Ruslan Salakhutdinov

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

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…

Computation and Language · Computer Science 2015-03-13 Sylvain Schmitz , Joseph Le Roux

A common meadow is an enrichment of a field with a partial division operation that is made total by assuming that division by zero takes the a default value, a special element $\bot$ adjoined to the field. To a common meadow of real numbers…

Information Theory · Computer Science 2025-02-12 Jan A Bergstra , John V Tucker

We present a trainable model for identifying sentence boundaries in raw text. Given a corpus annotated with sentence boundaries, our model learns to classify each occurrence of ., ?, and ! as either a valid or invalid sentence boundary. The…

cmp-lg · Computer Science 2008-02-03 Jeffrey C. Reynar , Adwait Ratnaparkhi

The grammars of natural languages may be learned by using genetic algorithms that reproduce and mutate grammatical rules and part-of-speech tags, improving the quality of later generations of grammatical components. Syntactic rules are…

cmp-lg · Computer Science 2008-02-03 Robert M. Losee

This paper presents a new view of Explanation-Based Learning (EBL) of natural language parsing. Rather than employing EBL for specializing parsers by inferring new ones, this paper suggests employing EBL for learning how to reduce ambiguity…

cmp-lg · Computer Science 2008-02-03 Khalil Sima'an

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Shihao Zhang , Linlin Yang , Michael Bi Mi , Xiaoxu Zheng , Angela Yao