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 757 records · Page 42Linked to original sources

arXiv1998

Automatic summarising: factors and directions

This position paper suggests that progress with automatic summarising demands a better research methodology and a carefully focussed research strategy. In order to develop effective procedures it is necessary to identify and respond to the context factors, i.e. input, purpose, and output factors, that bear on summarising and its evaluation. The paper analyses and illustrates these factors and their implications for evaluation. It then argues that this analysis, together with the state of the art and the intrinsic difficulty of summarising, imply a nearer-term strategy concentrating on shallow, but not surface, text analysis and on indicative summarising. This is illustrated with current work, from which a potentially productive research programme can be developed.

cmp-lg↗

arXiv1998

Recognizing Syntactic Errors in the Writing of Second Language Learners

This paper reports on the recognition component of an intelligent tutoring system that is designed to help foreign language speakers learn standard English. The system models the grammar of the learner, with this instantiation of the system tailored to signers of American Sign Language (ASL). We discuss the theoretical motivations for the system, various difficulties that have been encountered in the implementation, as well as the methods we have used to overcome these problems. Our method of capturing ungrammaticalities involves using mal-rules (also called 'error productions'). However, the straightforward addition of some mal-rules causes significant performance problems with the parser. For instance, the ASL population has a strong tendency to drop pronouns and the auxiliary verb `to be'. Being able to account for these as sentences results in an explosion in the number of possible parses for each sentence. This explosion, left unchecked, greatly hampers the performance of the system. We discuss how this is handled by taking into account expectations from the specific population (some of which are captured in our unique user model). The different representations of lexical items at various points in the acquisition process are modeled by using mal-rules, which obviates the need for multiple lexicons. The grammar is evaluated on its ability to correctly diagnose agreement problems in actual sentences produced by ASL native speakers.

cmp-lg↗

arXiv1998

Learning Correlations between Linguistic Indicators and Semantic Constraints: Reuse of Context-Dependent Descriptions of Entities

This paper presents the results of a study on the semantic constraints imposed on lexical choice by certain contextual indicators. We show how such indicators are computed and how correlations between them and the choice of a noun phrase description of a named entity can be automatically established using supervised learning. Based on this correlation, we have developed a technique for automatic lexical choice of descriptions of entities in text generation. We discuss the underlying relationship between the pragmatics of choosing an appropriate description that serves a specific purpose in the automatically generated text and the semantics of the description itself. We present our work in the framework of the more general concept of reuse of linguistic structures that are automatically extracted from large corpora. We present a formal evaluation of our approach and we conclude with some thoughts on potential applications of our method.

cmp-lg↗

arXiv1998

Computing Dialogue Acts from Features with Transformation-Based Learning

To interpret natural language at the discourse level, it is very useful to accurately recognize dialogue acts, such as SUGGEST, in identifying speaker intentions. Our research explores the utility of a machine learning method called Transformation-Based Learning (TBL) in computing dialogue acts, because TBL has a number of advantages over alternative approaches for this application. We have identified some extensions to TBL that are necessary in order to address the limitations of the original algorithm and the particular demands of discourse processing. We use a Monte Carlo strategy to increase the applicability of the TBL method, and we select features of utterances that can be used as input to improve the performance of TBL. Our system is currently being tested on the VerbMobil corpora of spoken dialogues, producing promising preliminary results.

cmp-lg↗

arXiv1998

Lazy Transformation-Based Learning

We introduce a significant improvement for a relatively new machine learning method called Transformation-Based Learning. By applying a Monte Carlo strategy to randomly sample from the space of rules, rather than exhaustively analyzing all possible rules, we drastically reduce the memory and time costs of the algorithm, without compromising accuracy on unseen data. This enables Transformation- Based Learning to apply to a wider range of domains, as it can effectively consider a larger number of different features and feature interactions in the data. In addition, the Monte Carlo improvement decreases the labor demands on the human developer, who no longer needs to develop a minimal set of rule templates to maintain tractability.

cmp-lg↗

arXiv1998

Rationality, Cooperation and Conversational Implicature

Conversational implicatures are usually described as being licensed by the disobeying or flouting of a Principle of Cooperation. However, the specification of this principle has proved computationally elusive. In this paper we suggest that a more useful concept is rationality. Such a concept can be specified explicitely in planning terms and we argue that speakers perform utterances as part of the optimal plan for their particular communicative goals. Such an assumption can be used by the hearer to infer conversational implicatures implicit in the speaker's utterance.

cmp-lg↗

arXiv1998

Eliminating deceptions and mistaken belief to infer conversational implicature

Conversational implicatures are usually described as being licensed by the disobeying or flouting of some principle by the speaker in cooperative dialogue. However, such work has failed to distinguish cases of the speaker flouting such a principle from cases where the speaker is either deceptive or holds a mistaken belief. In this paper, we demonstrate how the three different cases can be distinguished in terms of the beliefs ascribed to the speaker of the utterance. We argue that in the act of distinguishing the speaker's intention and ascribing such beliefs, the intended inference can be made by the hearer. This theory is implemented in ViewGen, a pre-existing belief modelling system used in a medical counselling domain.

cmp-lg↗

arXiv1998

Dialogue Act Tagging with Transformation-Based Learning

For the task of recognizing dialogue acts, we are applying the Transformation-Based Learning (TBL) machine learning algorithm. To circumvent a sparse data problem, we extract values of well-motivated features of utterances, such as speaker direction, punctuation marks, and a new feature, called dialogue act cues, which we find to be more effective than cue phrases and word n-grams in practice. We present strategies for constructing a set of dialogue act cues automatically by minimizing the entropy of the distribution of dialogue acts in a training corpus, filtering out irrelevant dialogue act cues, and clustering semantically-related words. In addition, to address limitations of TBL, we introduce a Monte Carlo strategy for training efficiently and a committee method for computing confidence measures. These ideas are combined in our working implementation, which labels held-out data as accurately as any other reported system for the dialogue act tagging task.

cmp-lg↗

arXiv1998

An Investigation of Transformation-Based Learning in Discourse

This paper presents results from the first attempt to apply Transformation-Based Learning to a discourse-level Natural Language Processing task. To address two limitations of the standard algorithm, we developed a Monte Carlo version of Transformation-Based Learning to make the method tractable for a wider range of problems without degradation in accuracy, and we devised a committee method for assigning confidence measures to tags produced by Transformation-Based Learning. The paper describes these advances, presents experimental evidence that Transformation-Based Learning is as effective as alternative approaches (such as Decision Trees and N-Grams) for a discourse task called Dialogue Act Tagging, and argues that Transformation-Based Learning has desirable features that make it particularly appealing for the Dialogue Act Tagging task.

cmp-lg↗

arXiv1998

Unlimited Vocabulary Grapheme to Phoneme Conversion for Korean TTS

This paper describes a grapheme-to-phoneme conversion method using phoneme connectivity and CCV conversion rules. The method consists of mainly four modules including morpheme normalization, phrase-break detection, morpheme to phoneme conversion and phoneme connectivity check. The morpheme normalization is to replace non-Korean symbols into standard Korean graphemes. The phrase-break detector assigns phrase breaks using part-of-speech (POS) information. In the morpheme-to-phoneme conversion module, each morpheme in the phrase is converted into phonetic patterns by looking up the morpheme phonetic pattern dictionary which contains candidate phonological changes in boundaries of the morphemes. Graphemes within a morpheme are grouped into CCV patterns and converted into phonemes by the CCV conversion rules. The phoneme connectivity table supports grammaticality checking of the adjacent two phonetic morphemes. In the experiments with a corpus of 4,973 sentences, we achieved 99.9% of the grapheme-to-phoneme conversion performance and 97.5% of the sentence conversion performance. The full Korean TTS system is now being implemented using this conversion method.

cmp-lg↗

arXiv1998

Methods and Tools for Building the Catalan WordNet

In this paper we introduce the methodology used and the basic phases we followed to develop the Catalan WordNet, and shich lexical resources have been employed in its building. This methodology, as well as the tools we made use of, have been thought in a general way so that they could be applied to any other language.

cmp-lg↗

arXiv1998

Towards a single proposal is spelling correction

The study presented here relies on the integrated use of different kinds of knowledge in order to improve first-guess accuracy in non-word context-sensitive correction for general unrestricted texts. State of the art spelling correction systems, e.g. ispell, apart from detecting spelling errors, also assist the user by offering a set of candidate corrections that are close to the misspelled word. Based on the correction proposals of ispell, we built several guessers, which were combined in different ways. Firstly, we evaluated all possibilities and selected the best ones in a corpus with artificially generated typing errors. Secondly, the best combinations were tested on texts with genuine spelling errors. The results for the latter suggest that we can expect automatic non-word correction for all the errors in a free running text with 80% precision and a single proposal 98% of the times (1.02 proposals on average).

cmp-lg↗

arXiv1999

A Memory-Based Approach to Learning Shallow Natural Language Patterns

Recognizing shallow linguistic patterns, such as basic syntactic relationships between words, is a common task in applied natural language and text processing. The common practice for approaching this task is by tedious manual definition of possible pattern structures, often in the form of regular expressions or finite automata. This paper presents a novel memory-based learning method that recognizes shallow patterns in new text based on a bracketed training corpus. The training data are stored as-is, in efficient suffix-tree data structures. Generalization is performed on-line at recognition time by comparing subsequences of the new text to positive and negative evidence in the corpus. This way, no information in the training is lost, as can happen in other learning systems that construct a single generalized model at the time of training. The paper presents experimental results for recognizing noun phrase, subject-verb and verb-object patterns in English. Since the learning approach enables easy porting to new domains, we plan to apply it to syntactic patterns in other languages and to sub-language patterns for information extraction.

cmp-lg↗

arXiv1998

Bayesian Stratified Sampling to Assess Corpus Utility

This paper describes a method for asking statistical questions about a large text corpus. We exemplify the method by addressing the question, "What percentage of Federal Register documents are real documents, of possible interest to a text researcher or analyst?" We estimate an answer to this question by evaluating 200 documents selected from a corpus of 45,820 Federal Register documents. Stratified sampling is used to reduce the sampling uncertainty of the estimate from over 3100 documents to fewer than 1000. The stratification is based on observed characteristics of real documents, while the sampling procedure incorporates a Bayesian version of Neyman allocation. A possible application of the method is to establish baseline statistics used to estimate recall rates for information retrieval systems.

cmp-lg↗

arXiv1998

Can Subcategorisation Probabilities Help a Statistical Parser?

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 predicates. However, the empirical question of whether this type of frequency information can in practice improve the accuracy of a statistical parser has not yet been answered. In this paper we describe an experiment with a wide-coverage statistical grammar and parser for English and subcategorisation frequencies acquired from ten million words of text which shows that this information can significantly improve parse accuracy.

cmp-lg↗

arXiv1998

Word Sense Disambiguation using Optimised Combinations of Knowledge Sources

Word sense disambiguation algorithms, with few exceptions, have made use of only one lexical knowledge source. We describe a system which performs unrestricted word sense disambiguation (on all content words in free text) by combining different knowledge sources: semantic preferences, dictionary definitions and subject/domain codes along with part-of-speech tags. The usefulness of these sources is optimised by means of a learning algorithm. We also describe the creation of a new sense tagged corpus by combining existing resources. Tested accuracy of our approach on this corpus exceeds 92%, demonstrating the viability of all-word disambiguation rather than restricting oneself to a small sample.

cmp-lg↗

arXiv1998

Building Accurate Semantic Taxonomies from Monolingual MRDs

This paper presents a method that combines a set of unsupervised algorithms in order to accurately build large taxonomies from any machine-readable dictionary (MRD). Our aim is to profit from conventional MRDs, with no explicit semantic coding. We propose a system that 1) performs fully automatic exraction of taxonomic links from MRD entries and 2) ranks the extracted relations in a way that selective manual refinement is allowed. Tested accuracy can reach around 100% depending on the degree of coverage selected, showing that taxonomy building is not limited to structured dictionaries such as LDOCE.

cmp-lg↗

arXiv1998

Using WordNet for Building WordNets

This paper summarises a set of methodologies and techniques for the fast construction of multilingual WordNets. The English WordNet is used in this approach as a backbone for Catalan and Spanish WordNets and as a lexical knowledge resource for several subtasks.

cmp-lg↗