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 595 records · Page 33Linked to original sources

arXiv1997

Combining Multiple Methods for the Automatic Construction of Multilingual WordNets

This paper explores the automatic construction of a multilingual Lexical Knowledge Base from preexisting lexical resources. First, a set of automatic and complementary techniques for linking Spanish words collected from monolingual and bilingual MRDs to English WordNet synsets are described. Second, we show how resulting data provided by each method is then combined to produce a preliminary version of a Spanish WordNet with an accuracy over 85%. The application of these combinations results on an increment of the extracted connexions of a 40% without losing accuracy. Both coarse-grained (class level) and fine-grained (synset assignment level) confidence ratios are used and evaluated. Finally, the results for the whole process are presented.

cmp-lg↗

arXiv1997

Off-line Parsability and the Well-foundedness of Subsumption

Typed feature structures are used extensively for the specification of linguistic information in many formalisms. The subsumption relation orders TFSs by their information content. We prove that subsumption of acyclic TFSs is well-founded, whereas in the presence of cycles general TFS subsumption is not well-founded. We show an application of this result for parsing, where the well-foundedness of subsumption is used to guarantee termination for grammars that are off-line parsable. We define a new version of off-line parsability that is less strict than the existing one; thus termination is guaranteed for parsing with a larger set of grammars.

cmp-lg↗

arXiv1997

Using Single Layer Networks for Discrete, Sequential Data: An Example from Natural Language Processing

A natural language parser which has been successfully implemented is described. This is a hybrid system, in which neural networks operate within a rule based framework. It can be accessed via telnet for users to try on their own text. (For details, contact the author.) Tested on technical manuals, the parser finds the subject and head of the subject in over 90% of declarative sentences. The neural processing components belong to the class of Generalized Single Layer Networks (GSLN). In general, supervised, feed-forward networks need more than one layer to process data. However, in some cases data can be pre-processed with a non-linear transformation, and then presented in a linearly separable form for subsequent processing by a single layer net. Such networks offer advantages of functional transparency and operational speed. For our parser, the initial stage of processing maps linguistic data onto a higher order representation, which can then be analysed by a single layer network. This transformation is supported by information theoretic analysis.

cmp-lg↗

arXiv1997

Segmentation of Expository Texts by Hierarchical Agglomerative Clustering

We propose a method for segmentation of expository texts based on hierarchical agglomerative clustering. The method uses paragraphs as the basic segments for identifying hierarchical discourse structure in the text, applying lexical similarity between them as the proximity test. Linear segmentation can be induced from the identified structure through application of two simple rules. However the hierarchy can be used also for intelligent exploration of the text. The proposed segmentation algorithm is evaluated against an accepted linear segmentation method and shows comparable results.

cmp-lg↗

arXiv1997

Use of Weighted Finite State Transducers in Part of Speech Tagging

This paper addresses issues in part of speech disambiguation using finite-state transducers and presents two main contributions to the field. One of them is the use of finite-state machines for part of speech tagging. Linguistic and statistical information is represented in terms of weights on transitions in weighted finite-state transducers. Another contribution is the successful combination of techniques -- linguistic and statistical -- for word disambiguation, compounded with the notion of word classes.

cmp-lg↗

arXiv1997

Tagging French Without Lexical Probabilities -- Combining Linguistic Knowledge And Statistical Learning

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 the user flexibility in choosing a tagset. The problem in extracting lexical probabilities from a limited training corpus is that the statistical model may not necessarily represent the use of a particular word in a particular context. In a highly morphologically inflected language, this argument is particularly serious since a word can be tagged with a large number of parts of speech. Due to the lack of sufficient training data, we argue against estimating lexical probabilities to disambiguate parts of speech in unrestricted texts. Instead, we use the strength of contextual probabilities along with a feature we call ``genotype'', a set of tags associated with a word. Using this knowledge, we have built a part-of-speech tagger that combines linguistic and statistical approaches: contextual information is disambiguated by linguistic rules and n-gram probabilities on parts of speech only are estimated in order to disambiguate the remaining ambiguous tags.

cmp-lg↗

arXiv1997

Disambiguating with Controlled Disjunctions

In this paper, we propose a disambiguating technique called controlled disjunctions. This extension of the so-called named disjunctions relies on the relations existing between feature values (covariation, control, etc.). We show that controlled disjunctions can implement different kind of ambiguities in a consistent and homogeneous way. We describe the integration of controlled disjunctions into a HPSG feature structure representation. Finally, we present a direct implementation by means of delayed evaluation and we develop an example within the functionnal programming paradigm.

cmp-lg↗

arXiv1997

Parsing syllables: modeling OT computationally

In this paper, I propose to implement syllabification in OT as a parser. I propose several innovations that result in a finite and small candidate set. The candidate set problem is handled with several moves: i) MAX and DEP violations are not hypothesized by the parser, ii) candidates are encoded locally, and iii) EVAL is applied constraint by constraint. The parser I propose is implemented in Prolog. It has a number of desirable consequences. First, it runs and thus provides an existence proof that syllabification can be implemented in OT. There are a number of other desirable consequences as well. First, constraints are implemented as finite-state transducers. Second, the parser makes several interesting claims about the phonological properties of so-called nonrecoverable insertions and deletions. Third, the implementation suggests some particular reformulations of some of the benchmark constraints in the OT arsenal, e.g. *COMPLEX, PARSE, ONSET, and NOCODA.

cmp-lg↗

arXiv1997

Attaching Multiple Prepositional Phrases: Generalized Backed-off Estimation

There has recently been considerable interest in the use of lexically-based statistical techniques to resolve prepositional phrase attachments. To our knowledge, however, these investigations have only considered the problem of attaching the first PP, i.e., in a [V NP PP] configuration. In this paper, we consider one technique which has been successfully applied to this problem, backed-off estimation, and demonstrate how it can be extended to deal with the problem of multiple PP attachment. The multiple PP attachment introduces two related problems: sparser data (since multiple PPs are naturally rarer), and greater syntactic ambiguity (more attachment configurations which must be distinguished). We present and algorithm which solves this problem through re-use of the relatively rich data obtained from first PP training, in resolving subsequent PP attachments.

cmp-lg↗

arXiv1997

Learning Features that Predict Cue Usage

Our goal is to identify the features that predict the occurrence and placement of discourse cues in tutorial explanations in order to aid in the automatic generation of explanations. Previous attempts to devise rules for text generation were based on intuition or small numbers of constructed examples. We apply a machine learning program, C4.5, to induce decision trees for cue occurrence and placement from a corpus of data coded for a variety of features previously thought to affect cue usage. Our experiments enable us to identify the features with most predictive power, and show that machine learning can be used to induce decision trees useful for text generation.

cmp-lg↗

arXiv1997

A Corpus-Based Investigation of Definite Description Use

We present the results of a study of definite descriptions use in written texts aimed at assessing the feasibility of annotating corpora with information about definite description interpretation. We ran two experiments, in which subjects were asked to classify the uses of definite descriptions in a corpus of 33 newspaper articles, containing a total of 1412 definite descriptions. We measured the agreement among annotators about the classes assigned to definite descriptions, as well as the agreement about the antecedent assigned to those definites that the annotators classified as being related to an antecedent in the text. The most interesting result of this study from a corpus annotation perspective was the rather low agreement (K=0.63) that we obtained using versions of Hawkins' and Prince's classification schemes; better results (K=0.76) were obtained using the simplified scheme proposed by Fraurud that includes only two classes, first-mention and subsequent-mention. The agreement about antecedents was also not complete. These findings raise questions concerning the strategy of evaluating systems for definite description interpretation by comparing their results with a standardized annotation. From a linguistic point of view, the most interesting observations were the great number of discourse-new definites in our corpus (in one of our experiments, about 50% of the definites in the collection were classified as discourse-new, 30% as anaphoric, and 18% as associative/bridging) and the presence of definites which did not seem to require a complete disambiguation.

cmp-lg↗

arXiv1997

Probabilistic Event Categorization

This paper describes the automation of a new text categorization task. The categories assigned in this task are more syntactically, semantically, and contextually complex than those typically assigned by fully automatic systems that process unseen test data. Our system for assigning these categories is a probabilistic classifier, developed with a recent method for formulating a probabilistic model from a predefined set of potential features. This paper focuses on feature selection. It presents a number of fully automatic features. It identifies and evaluates various approaches to organizing collocational properties into features, and presents the results of experiments covarying type of organization and type of property. We find that one organization is not best for all kinds of properties, so this is an experimental parameter worth investigating in NLP systems. In addition, the results suggest a way to take advantage of properties that are low frequency but strongly indicative of a class. The problems of recognizing and organizing the various kinds of contextual information required to perform a linguistically complex categorization task have rarely been systematically investigated in NLP.

cmp-lg↗

arXiv1997

Probabilistic Constraint Logic Programming

This paper addresses two central problems for probabilistic processing models: parameter estimation from incomplete data and efficient retrieval of most probable analyses. These questions have been answered satisfactorily only for probabilistic regular and context-free models. We address these problems for a more expressive probabilistic constraint logic programming model. We present a log-linear probability model for probabilistic constraint logic programming. On top of this model we define an algorithm to estimate the parameters and to select the properties of log-linear models from incomplete data. This algorithm is an extension of the improved iterative scaling algorithm of Della-Pietra, Della-Pietra, and Lafferty (1995). Our algorithm applies to log-linear models in general and is accompanied with suitable approximation methods when applied to large data spaces. Furthermore, we present an approach for searching for most probable analyses of the probabilistic constraint logic programming model. This method can be applied to the ambiguity resolution problem in natural language processing applications.

cmp-lg↗

arXiv1997

Approximating Context-Free Grammars with a Finite-State Calculus

Although adequate models of human language for syntactic analysis and semantic interpretation are of at least context-free complexity, for applications such as speech processing in which speed is important finite-state models are often preferred. These requirements may be reconciled by using the more complex grammar to automatically derive a finite-state approximation which can then be used as a filter to guide speech recognition or to reject many hypotheses at an early stage of processing. A method is presented here for calculating such finite-state approximations from context-free grammars. It is essentially different from the algorithm introduced by Pereira and Wright (1991; 1996), is faster in some cases, and has the advantage of being open-ended and adaptable.

cmp-lg↗

arXiv1997

Probabilistic Parsing Using Left Corner Language Models

We introduce a novel parser based on a probabilistic version of a left-corner parser. The left-corner strategy is attractive because rule probabilities can be conditioned on both top-down goals and bottom-up derivations. We develop the underlying theory and explain how a grammar can be induced from analyzed data. We show that the left-corner approach provides an advantage over simple top-down probabilistic context-free grammars in parsing the Wall Street Journal using a grammar induced from the Penn Treebank. We also conclude that the Penn Treebank provides a fairly weak testbed due to the flatness of its bracketings and to the obvious overgeneration and undergeneration of its induced grammar.

cmp-lg↗

arXiv1997

Variation and Synthetic Speech

We describe the approach to linguistic variation taken by the Motorola speech synthesizer. A pan-dialectal pronunciation dictionary is described, which serves as the training data for a neural network based letter-to-sound converter. Subsequent to dictionary retrieval or letter-to-sound generation, pronunciations are submitted a neural network based postlexical module. The postlexical module has been trained on aligned dictionary pronunciations and hand-labeled narrow phonetic transcriptions. This architecture permits the learning of individual postlexical variation, and can be retrained for each speaker whose voice is being modeled for synthesis. Learning variation in this way can result in greater naturalness for the synthetic speech that is produced by the system.

cmp-lg↗

arXiv1997

Some apparently disjoint aims and requirements for grammar development environments: the case of natural language generation

Grammar development environments (GDE's) for analysis and for generation have not yet come together. Despite the fact that analysis-oriented GDE's (such as ALEP) may include some possibility of sentence generation, the development techniques and kinds of resources suggested are apparently not those required for practical, large-scale natural language generation work. Indeed, there is no use of `standard' (i.e., analysis-oriented) GDE's in current projects/applications targetting the generation of fluent, coherent texts. This unsatisfactory situation requires some analysis and explanation, which this paper attempts using as an example an extensive GDE for generation. The support provided for distributed large-scale grammar development, multilinguality, and resource maintenance are discussed and contrasted with analysis-oriented approaches.

cmp-lg↗

arXiv1997

Contextual Information and Specific Language Models for Spoken Language Understanding

In this paper we explain how contextual expectations are generated and used in the task-oriented spoken language understanding system Dialogos. The hard task of recognizing spontaneous speech on the telephone may greatly benefit from the use of specific language models during the recognition of callers' utterances. By 'specific language models' we mean a set of language models that are trained on contextually appropriated data, and that are used during different states of the dialogue on the basis of the information sent to the acoustic level by the dialogue management module. In this paper we describe how the specific language models are obtained on the basis of contextual information. The experimental result we report show that recognition and understanding performance are improved thanks to the use of specific language models.

cmp-lg↗