Searcharxiv⌕ Search

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 739 records · Page 41Linked to original sources
arXiv1998

Automating Coreference: The Role of Annotated Training Data

We report here on a study of interannotator agreement in the coreference task as defined by the Message Understanding Conference (MUC-6 and MUC-7). Based on feedback from annotators, we clarified and simplified the annotation specification. We then performed an analysis of disagreement among several annotators, concluding that only 16% of the disagreements represented genuine disagreement about coreference; the remainder of the cases were mostly typographical errors or omissions, easily reconciled. Initially, we measured interannotator agreement in the low 80s for precision and recall. To try to improve upon this, we ran several experiments. In our final experiment, we separated the tagging of candidate noun phrases from the linking of actual coreferring expressions. This method shows promise - interannotator agreement climbed to the low 90s - but it needs more extensive validation. These results position the research community to broaden the coreference task to multiple languages, and possibly to different kinds of coreference.

cmp-lg↗
arXiv1998

Time, Tense and Aspect in Natural Language Database Interfaces

Most existing natural language database interfaces (NLDBs) were designed to be used with database systems that provide very limited facilities for manipulating time-dependent data, and they do not support adequately temporal linguistic mechanisms (verb tenses, temporal adverbials, temporal subordinate clauses, etc.). The database community is becoming increasingly interested in temporal database systems, that are intended to store and manipulate in a principled manner information not only about the present, but also about the past and future. When interfacing to temporal databases, supporting temporal linguistic mechanisms becomes crucial. We present a framework for constructing natural language interfaces for temporal databases (NLTDBs), that draws on research in tense and aspect theories, temporal logics, and temporal databases. The framework consists of a temporal intermediate representation language, called TOP, an HPSG grammar that maps a wide range of questions involving temporal mechanisms to appropriate TOP expressions, and a provably correct method for translating from TOP to TSQL2, TSQL2 being a recently proposed temporal extension of the SQL database language. This framework was employed to implement a prototype NLTDB using ALE and Prolog.

cmp-lg↗
arXiv1998

Nymble: a High-Performance Learning Name-finder

This paper presents a statistical, learned approach to finding names and other non-recursive entities in text (as per the MUC-6 definition of the NE task), using a variant of the standard hidden Markov model. We present our justification for the problem and our approach, a detailed discussion of the model itself and finally the successful results of this new approach.

cmp-lg↗
arXiv1998

Graph Interpolation Grammars: a Rule-based Approach to the Incremental Parsing of Natural Languages

Graph Interpolation Grammars are a declarative formalism with an operational semantics. Their goal is to emulate salient features of the human parser, and notably incrementality. The parsing process defined by GIGs incrementally builds a syntactic representation of a sentence as each successive lexeme is read. A GIG rule specifies a set of parse configurations that trigger its application and an operation to perform on a matching configuration. Rules are partly context-sensitive; furthermore, they are reversible, meaning that their operations can be undone, which allows the parsing process to be nondeterministic. These two factors confer enough expressive power to the formalism for parsing natural languages.

cmp-lg↗
arXiv1998

The Proper Treatment of Optimality in Computational Phonology

This paper presents a novel formalization of optimality theory. Unlike previous treatments of optimality in computational linguistics, starting with Ellison (1994), the new approach does not require any explicit marking and counting of constraint violations. It is based on the notion of "lenient composition," defined as the combination of ordinary composition and priority union. If an underlying form has outputs that can meet a given constraint, lenient composition enforces the constraint; if none of the output candidates meet the constraint, lenient composition allows all of them. For the sake of greater efficiency, we may "leniently compose" the GEN relation and all the constraints into a single finite-state transducer that maps each underlying form directly into its optimal surface realizations, and vice versa, without ever producing any failing candidates. Seen from this perspective, optimality theory is surprisingly similar to the two older strains of finite-state phonology: classical rewrite systems and two-level models. In particular, the ranking of optimality constraints corresponds to the ordering of rewrite rules.

cmp-lg↗
arXiv1998

Treatment of Epsilon-Moves in Subset Construction

The paper discusses the problem of determinising finite-state automata containing large numbers of epsilon-moves. Experiments with finite-state approximations of natural language grammars often give rise to very large automata with a very large number of epsilon-moves. The paper identifies three subset construction algorithms which treat epsilon-moves. A number of experiments has been performed which indicate that the algorithms differ considerably in practice. Furthermore, the experiments suggest that the average number of epsilon-moves per state can be used to predict which algorithm is likely to perform best for a given input automaton.

cmp-lg↗
arXiv1998

Corpus-Based Word Sense Disambiguation

Resolution of lexical ambiguity, commonly termed ``word sense disambiguation'', is expected to improve the analytical accuracy for tasks which are sensitive to lexical semantics. Such tasks include machine translation, information retrieval, parsing, natural language understanding and lexicography. Reflecting the growth in utilization of machine readable texts, word sense disambiguation techniques have been explored variously in the context of corpus-based approaches. Within one corpus-based framework, that is the similarity-based method, systems use a database, in which example sentences are manually annotated with correct word senses. Given an input, systems search the database for the most similar example to the input. The lexical ambiguity of a word contained in the input is resolved by selecting the sense annotation of the retrieved example. In this research, we apply this method of resolution of verbal polysemy, in which the similarity between two examples is computed as the weighted average of the similarity between complements governed by a target polysemous verb. We explore similarity-based verb sense disambiguation focusing on the following three methods. First, we propose a weighting schema for each verb complement in the similarity computation. Second, in similarity-based techniques, the overhead for manual supervision and searching the large-sized database can be prohibitive. To resolve this problem, we propose a method to select a small number of effective examples, for system usage. Finally, the efficiency of our system is highly dependent on the similarity computation used. To maximize efficiency, we propose a method which integrates the advantages of previous methods for similarity computation.

cmp-lg↗
arXiv1998

Valence Induction with a Head-Lexicalized PCFG

This paper presents an experiment in learning valences (subcategorization frames) from a 50 million word text corpus, based on a lexicalized probabilistic context free grammar. Distributions are estimated using a modified EM algorithm. We evaluate the acquired lexicon both by comparison with a dictionary and by entropy measures. Results show that our model produces highly accurate frame distributions.

cmp-lg↗
arXiv1998

Group Theory and Grammatical Description

This paper presents a model for linguistic description based on group theory. A grammar in this model, or "G-grammar", is a collection of lexical expressions which are products of logical forms, phonological forms, and their inverses. Phrasal descriptions are obtained by forming products of lexical expressions and by cancelling contiguous elements which are inverses of each other. We show applications of this model to parsing and generation, long-distance movement, and quantifier scoping. We believe that by moving from the free monoid over a vocabulary V --- standard in formal language studies --- to the free group over V, deep affinities between linguistic phenomena and classical algebra come to the surface, and that the consequences of tapping the mathematical connections thus established could be considerable.

cmp-lg↗
arXiv1998

Models of Co-occurrence

A model of co-occurrence in bitext is a boolean predicate that indicates whether a given pair of word tokens co-occur in corresponding regions of the bitext space. Co-occurrence is a precondition for the possibility that two tokens might be mutual translations. Models of co-occurrence are the glue that binds methods for mapping bitext correspondence with methods for estimating translation models into an integrated system for exploiting parallel texts. Different models of co-occurrence are possible, depending on the kind of bitext map that is available, the language-specific information that is available, and the assumptions made about the nature of translational equivalence. Although most statistical translation models are based on models of co-occurrence, modeling co-occurrence correctly is more difficult than it may at first appear.

cmp-lg↗
arXiv1998

Annotation Style Guide for the Blinker Project

This annotation style guide was created by and for the Blinker project at the University of Pennsylvania. The Blinker project was so named after the ``bilingual linker'' GUI, which was created to enable bilingual annotators to ``link'' word tokens that are mutual translations in parallel texts. The parallel text chosen for this project was the Bible, because it is probably the easiest text to obtain in electronic form in multiple languages. The languages involved were English and French, because, of the languages with which the project co-ordinator was familiar, these were the two for which a sufficient number of annotators was likely to be found.

cmp-lg↗
arXiv1998

Manual Annotation of Translational Equivalence: The Blinker Project

Bilingual annotators were paid to link roughly sixteen thousand corresponding words between on-line versions of the Bible in modern French and modern English. These annotations are freely available to the research community from http://www.cis.upenn.edu/~melamed . The annotations can be used for several purposes. First, they can be used as a standard data set for developing and testing translation lexicons and statistical translation models. Second, researchers in lexical semantics will be able to mine the annotations for insights about cross-linguistic lexicalization patterns. Third, the annotations can be used in research into certain recently proposed methods for monolingual word-sense disambiguation. This paper describes the annotated texts, the specially-designed annotation tool, and the strategies employed to increase the consistency of the annotations. The annotation process was repeated five times by different annotators. Inter-annotator agreement rates indicate that the annotations are reasonably reliable and that the method is easy to replicate.

cmp-lg↗
arXiv1998

Word-to-Word Models of Translational Equivalence

Parallel texts (bitexts) have properties that distinguish them from other kinds of parallel data. First, most words translate to only one other word. Second, bitext correspondence is noisy. This article presents methods for biasing statistical translation models to reflect these properties. Analysis of the expected behavior of these biases in the presence of sparse data predicts that they will result in more accurate models. The prediction is confirmed by evaluation with respect to a gold standard -- translation models that are biased in this fashion are significantly more accurate than a baseline knowledge-poor model. This article also shows how a statistical translation model can take advantage of various kinds of pre-existing knowledge that might be available about particular language pairs. Even the simplest kinds of language-specific knowledge, such as the distinction between content words and function words, is shown to reliably boost translation model performance on some tasks. Statistical models that are informed by pre-existing knowledge about the model domain combine the best of both the rationalist and empiricist traditions.

cmp-lg↗
arXiv1998

Parsing Inside-Out

The inside-outside probabilities are typically used for reestimating Probabilistic Context Free Grammars (PCFGs), just as the forward-backward probabilities are typically used for reestimating HMMs. I show several novel uses, including improving parser accuracy by matching parsing algorithms to evaluation criteria; speeding up DOP parsing by 500 times; and 30 times faster PCFG thresholding at a given accuracy level. I also give an elegant, state-of-the-art grammar formalism, which can be used to compute inside-outside probabilities; and a parser description formalism, which makes it easy to derive inside-outside formulas and many others.

cmp-lg↗
arXiv1998

A Descriptive Characterization of Tree-Adjoining Languages (Full Version)

Since the early Sixties and Seventies it has been known that the regular and context-free languages are characterized by definability in the monadic second-order theory of certain structures. More recently, these descriptive characterizations have been used to obtain complexity results for constraint- and principle-based theories of syntax and to provide a uniform model-theoretic framework for exploring the relationship between theories expressed in disparate formal terms. These results have been limited, to an extent, by the lack of descriptive characterizations of language classes beyond the context-free. Recently, we have shown that tree-adjoining languages (in a mildly generalized form) can be characterized by recognition by automata operating on three-dimensional tree manifolds, a three-dimensional analog of trees. In this paper, we exploit these automata-theoretic results to obtain a characterization of the tree-adjoining languages by definability in the monadic second-order theory of these three-dimensional tree manifolds. This not only opens the way to extending the tools of model-theoretic syntax to the level of TALs, but provides a highly flexible mechanism for defining TAGs in terms of logical constraints. This is the full version of a paper to appear in the proceedings of COLING-ACL'98 as a project note.

cmp-lg↗
arXiv1998

Discovery of Linguistic Relations Using Lexical Attraction

This work has been motivated by two long term goals: to understand how humans learn language and to build programs that can understand language. Using a representation that makes the relevant features explicit is a prerequisite for successful learning and understanding. Therefore, I chose to represent relations between individual words explicitly in my model. Lexical attraction is defined as the likelihood of such relations. I introduce a new class of probabilistic language models named lexical attraction models which can represent long distance relations between words and I formalize this new class of models using information theory. Within the framework of lexical attraction, I developed an unsupervised language acquisition program that learns to identify linguistic relations in a given sentence. The only explicitly represented linguistic knowledge in the program is lexical attraction. There is no initial grammar or lexicon built in and the only input is raw text. Learning and processing are interdigitated. The processor uses the regularities detected by the learner to impose structure on the input. This structure enables the learner to detect higher level regularities. Using this bootstrapping procedure, the program was trained on 100 million words of Associated Press material and was able to achieve 60% precision and 50% recall in finding relations between content-words. Using knowledge of lexical attraction, the program can identify the correct relations in syntactically ambiguous sentences such as ``I saw the Statue of Liberty flying over New York.''

cmp-lg↗
arXiv1998

Integrating Text Plans for Conciseness and Coherence

Our experience with a critiquing system shows that when the system detects problems with the user's performance, multiple critiques are often produced. Analysis of a corpus of actual critiques revealed that even though each individual critique is concise and coherent, the set of critiques as a whole may exhibit several problems that detract from conciseness and coherence, and consequently assimilation. Thus a text planner was needed that could integrate the text plans for individual communicative goals to produce an overall text plan representing a concise, coherent message. This paper presents our general rule-based system for accomplishing this task. The system takes as input a \emph{set} of individual text plans represented as RST-style trees, and produces a smaller set of more complex trees representing integrated messages that still achieve the multiple communicative goals of the individual text plans. Domain-independent rules are used to capture strategies across domains, while the facility for addition of domain-dependent rules enables the system to be tuned to the requirements of a particular domain. The system has been tested on a corpus of critiques in the domain of trauma care.

cmp-lg↗