SEARCH · Searcharxiv

Results for “cmp-lg”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 577 records · Page 32Linked to original sources

arXiv1998

Character design for soccer commmentary

In this paper we present early work on an animated talking head commentary system called {\bf Byrne}\footnote{David Byrne is the lead singer of the Talking Heads.}. The goal of this project is to develop a system which can take the output from the RoboCup soccer simulator, and generate appropriate affective speech and facial expressions, based on the character's personality, emotional state, and the state of play. Here we describe a system which takes pre-analysed simulator output as input, and which generates text marked-up for use by a speech generator and a face animation system. We make heavy use of inter-system standards, so that future versions of Byrne will be able to take advantage of advances in the technologies that it incorporates.

cmp-lg↗

arXiv1998

Improving Data Driven Wordclass Tagging by System Combination

In this paper we examine how the differences in modelling between different data driven systems performing the same NLP task can be exploited to yield a higher accuracy than the best individual system. We do this by means of an experiment involving the task of morpho-syntactic wordclass tagging. Four well-known tagger generators (Hidden Markov Model, Memory-Based, Transformation Rules and Maximum Entropy) are trained on the same corpus data. After comparison, their outputs are combined using several voting strategies and second stage classifiers. All combination taggers outperform their best component, with the best combination showing a 19.1% lower error rate than the best individual tagger.

cmp-lg↗

arXiv1998

An Empirical Evaluation of Probabilistic Lexicalized Tree Insertion Grammars

We present an empirical study of the applicability of Probabilistic Lexicalized Tree Insertion Grammars (PLTIG), a lexicalized counterpart to Probabilistic Context-Free Grammars (PCFG), to problems in stochastic natural-language processing. Comparing the performance of PLTIGs with non-hierarchical N-gram models and PCFGs, we show that PLTIG combines the best aspects of both, with language modeling capability comparable to N-grams, and improved parsing performance over its non-lexicalized counterpart. Furthermore, training of PLTIGs displays faster convergence than PCFGs.

cmp-lg↗

arXiv1998

Indexing with WordNet synsets can improve Text Retrieval

The classical, vector space model for text retrieval is shown to give better results (up to 29% better in our experiments) if WordNet synsets are chosen as the indexing space, instead of word forms. This result is obtained for a manually disambiguated test collection (of queries and documents) derived from the Semcor semantic concordance. The sensitivity of retrieval performance to (automatic) disambiguation errors when indexing documents is also measured. Finally, it is observed that if queries are not disambiguated, indexing by synsets performs (at best) only as good as standard word indexing.

cmp-lg↗

arXiv1998

Parallel Strands: A Preliminary Investigation into Mining the Web for Bilingual Text

Parallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genre- and domain-specificity, licensing restrictions, and the basic difficulty of locating parallel texts in all but the most dominant of the world's languages. A parallel corpus resource not yet explored is the World Wide Web, which hosts an abundance of pages in parallel translation, offering a potential solution to some of these problems and unique opportunities of its own. This paper presents the necessary first step in that exploration: a method for automatically finding parallel translated documents on the Web. The technique is conceptually simple, fully language independent, and scalable, and preliminary evaluation results indicate that the method may be accurate enough to apply without human intervention.

cmp-lg↗

arXiv1998

Word Length Frequency and Distribution in English: Observations, Theory, and Implications for the Construction of Verse Lines

Recent observations in the theory of verse and empirical metrics have suggested that constructing a verse line involves a pattern-matching search through a source text, and that the number of found elements (complete words totaling a specified number of syllables) is given by dividing the total number of words by the mean number of syllables per word in the source text. This paper makes this latter point explicit mathematically, and in the course of this demonstration shows that the word length frequency totals in English output are distributed geometrically (previous researchers reported an adjusted Poisson distribution), and that the sequential distribution is random at the global level, with significant non-randomness in the fine structure. Data from a corpus of just under two million words, and a syllable-count lexicon of 71,000 word-forms is reported. The pattern-matching theory is shown to be internally coherent, and it is observed that some of the analytic techniques described here form a satisfactory test for regular (isometric) lineation in a text.

cmp-lg↗

arXiv1998

Combining Expression and Content in Domains for Dialog Managers

We present work in progress on abstracting dialog managers from their domain in order to implement a dialog manager development tool which takes (among other data) a domain description as input and delivers a new dialog manager for the described domain as output. Thereby we will focus on two topics; firstly, the construction of domain descriptions with description logics and secondly, the interpretation of utterances in a given domain.

cmp-lg↗

arXiv1998

Isometric Lineation in English Texts: An Empirical and Mathematical Examination of its Character and Consequences

In this paper we build on earlier observations and theory regarding word length frequency and sequential distribution to develop a mathematical characterization of some of the language features distinguishing isometrically lineated text from unlineated text, in other words the features distinguishing isometrical verse from prose. It is shown that the frequency of syllables making complete words produces a flat distribution for prose, while that for verse exhibits peaks at the line length position and subsequent multiples of that position. Data from several verse authors is presented, including a detailed mathematical analysis of the dynamics underlying peak creation, and comments are offered on the processes by which authors construct lines. We note that the word-length sequence of prose is random, whereas lineation necessitates non-random word-length sequencing, and that this has the probable consequence of introducing a degree of randomness into the otherwise highly ordered grammatical sequence. In addition we observe that this effect can be ameliorated by a reduction in the mean word length of the text (confirming earlier observations that verse tends to use shorter words) and the use of lines varying from the core isometrical set. The frequency of variant lines is shown to be coincident with the frequency of polysyllables, suggesting that the use of variant lines is motivated by polysyllabic word placement. The restrictive effects of different line lengths, the relationship between metrical restriction and poetic effect, and the general character of metrical rules are also discussed.

cmp-lg↗

arXiv1998

Some Properties of Preposition and Subordinate Conjunction Attachments

Determining the attachments of prepositions and subordinate conjunctions is a key problem in parsing natural language. This paper presents a trainable approach to making these attachments through transformation sequences and error-driven learning. Our approach is broad coverage, and accounts for roughly three times the attachment cases that have previously been handled by corpus-based techniques. In addition, our approach is based on a simplified model of syntax that is more consistent with the practice in current state-of-the-art language processing systems. This paper sketches syntactic and algorithmic details, and presents experimental results on data sets derived from the Penn Treebank. We obtain an attachment accuracy of 75.4% for the general case, the first such corpus-based result to be reported. For the restricted cases previously studied with corpus-based methods, our approach yields an accuracy comparable to current work (83.1%).

cmp-lg↗

arXiv1998

Deriving the Predicate-Argument Structure for a Free Word Order Language

In relatively free word order languages, grammatical functions are intricately related to case marking. Assuming an ordered representation of the predicate-argument structure, this work proposes a Combinatory Categorial Grammar formulation of relating surface case cues to categories and types for correctly placing the arguments in the predicate-argument structure. This is achieved by assigning case markers GF-encoding categories. Unlike other CG formulations, type shifting does not proliferate or cause spurious ambiguity. Categories of all argument-encoding grammatical functions follow from the same principle of category assignment. Normal order evaluation of the combinatory form reveals the predicate-argument structure. Application of the method to Turkish is shown.

cmp-lg↗

arXiv1998

How to define a context-free backbone for DGs: Implementing a DG in the LFG formalism

This paper presents a multidimensional Dependency Grammar (DG), which decouples the dependency tree from word order, such that surface ordering is not determined by traversing the dependency tree. We develop the notion of a \emph{word order domain structure}, which is linked but structurally dissimilar to the syntactic dependency tree. We then discuss the implementation of such a DG using constructs from a unification-based phrase-structure approach, namely Lexical-Functional Grammar (LFG). Particular attention is given to the analysis of discontinuities in DG in terms of LFG's functional uncertainty.

cmp-lg↗

arXiv1998

Letter to Sound Rules for Accented Lexicon Compression

This paper presents trainable methods for generating letter to sound rules from a given lexicon for use in pronouncing out-of-vocabulary words and as a method for lexicon compression. As the relationship between a string of letters and a string of phonemes representing its pronunciation for many languages is not trivial, we discuss two alignment procedures, one fully automatic and one hand-seeded which produce reasonable alignments of letters to phones. Top Down Induction Tree models are trained on the aligned entries. We show how combined phoneme/stress prediction is better than separate prediction processes, and still better when including in the model the last phonemes transcribed and part of speech information. For the lexicons we have tested, our models have a word accuracy (including stress) of 78% for OALD, 62% for CMU and 94% for BRULEX. The extremely high scores on the training sets allow substantial size reductions (more than 1/20). WWW site: http://tcts.fpms.ac.be/synthesis/mbrdico

cmp-lg↗

arXiv1998

Primitive Part-of-Speech Tagging using Word Length and Sentential Structure

It has been argued that, when learning a first language, babies use a series of small clues to aid recognition and comprehension, and that one of these clues is word length. In this paper we present a statistical part of speech tagger which trains itself solely on the number of letters in each word in a sentence.

cmp-lg↗

arXiv1998

Separating Surface Order and Syntactic Relations in a Dependency Grammar

This paper proposes decoupling the dependency tree from word order, such that surface ordering is not determined by traversing the dependency tree. We develop the notion of a \emph{word order domain structure}, which is linked but structurally dissimilar to the syntactic dependency tree. The proposal results in a lexicalized, declarative, and formally precise description of word order; features which lack previous proposals for dependency grammars. Contrary to other lexicalized approaches to word order, our proposal does not require lexical ambiguities for ordering alternatives.

cmp-lg↗

arXiv1998

Partial Evaluation for Efficient Access to Inheritance Lexicons

Multiple default inheritance formalisms for lexicons have attracted much interest in recent years. I propose a new efficient method to access such lexicons. After showing two basic strategies for lookup in inheritance lexicons, a compromise is developed which combines to a large degree (from a practical point of view) the advantages of both strategies and avoids their disadvantages. The method is a kind of (off-line) partial evaluation that makes a subset of inherited information explicit before using the lexicon. I identify the parts of a lexicon which should be evaluated, and show how partial evaluation works for inheritance lexicons. Finally, the theoretical results are confirmed by a complete implementation. Speedups by a factor of 10-100 are reached.

cmp-lg↗

arXiv1998

Spotting Prosodic Boundaries in Continuous Speech in French

A radio speech corpus of 9mn has been prosodically marked by a phonetician expert, and non expert listeners. this corpus is large enough to train and test an automatic boundary spotting system, namely a time delay neural network fed with F0 values, vowels and pseudo-syllable durations. Results validate both prosodic marking and automatic spotting of prosodic events.

cmp-lg↗

arXiv1998

Error-Driven Pruning of Treebank Grammars for Base Noun Phrase Identification

Finding simple, non-recursive, base noun phrases is an important subtask for many natural language processing applications. While previous empirical methods for base NP identification have been rather complex, this paper instead proposes a very simple algorithm that is tailored to the relative simplicity of the task. In particular, we present a corpus-based approach for finding base NPs by matching part-of-speech tag sequences. The training phase of the algorithm is based on two successful techniques: first the base NP grammar is read from a ``treebank'' corpus; then the grammar is improved by selecting rules with high ``benefit'' scores. Using this simple algorithm with a naive heuristic for matching rules, we achieve surprising accuracy in an evaluation on the Penn Treebank Wall Street Journal.

cmp-lg↗

arXiv1998

Segregatory Coordination and Ellipsis in Text Generation

In this paper, we provide an account of how to generate sentences with coordination constructions from clause-sized semantic representations. An algorithm is developed to generate sentences with ellipsis, gapping, right-node-raising, and non-constituent coordination constructions. Various examples from linguistic literature will be used to demonstrate that the algorithm does its job well.

cmp-lg↗