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 451 records · Page 25Linked to original sources

arXiv1997

Concept Clustering and Knowledge Integration from a Children's Dictionary

Knowledge structures called Concept Clustering Knowledge Graphs (CCKGs) are introduced along with a process for their construction from a machine readable dictionary. CCKGs contain multiple concepts interrelated through multiple semantic relations together forming a semantic cluster represented by a conceptual graph. The knowledge acquisition is performed on a children's first dictionary. A collection of conceptual clusters together can form the basis of a lexical knowledge base, where each CCKG contains a limited number of highly connected words giving useful information about a particular domain or situation.

cmp-lg↗

arXiv1997

Machine Transliteration

It is challenging to translate names and technical terms across languages with different alphabets and sound inventories. These items are commonly transliterated, i.e., replaced with approximate phonetic equivalents. For example, "computer" in English comes out as "konpyuutaa" in Japanese. Translating such items from Japanese back to English is even more challenging, and of practical interest, as transliterated items make up the bulk of text phrases not found in bilingual dictionaries. We describe and evaluate a method for performing backwards transliterations by machine. This method uses a generative model, incorporating several distinct stages in the transliteration process.

cmp-lg↗

arXiv1997

PARADISE: A Framework for Evaluating Spoken Dialogue Agents

This paper presents PARADISE (PARAdigm for DIalogue System Evaluation), a general framework for evaluating spoken dialogue agents. The framework decouples task requirements from an agent's dialogue behaviors, supports comparisons among dialogue strategies, enables the calculation of performance over subdialogues and whole dialogues, specifies the relative contribution of various factors to performance, and makes it possible to compare agents performing different tasks by normalizing for task complexity.

cmp-lg↗

arXiv1997

Representing Constraints with Automata

In this paper we describe an approach to constraint-based syntactic theories in terms of finite tree automata. The solutions to constraints expressed in weak monadic second order (MSO) logic are represented by tree automata recognizing the assignments which make the formulas true. We show that this allows an efficient representation of knowledge about the content of constraints which can be used as a practical tool for grammatical theory verification. We achieve this by using the intertranslatability of formulas of MSO logic and tree automata and the embedding of MSO logic into a constraint logic programming scheme. The usefulness of the approach is discussed with examples from the realm of Principles-and-Parameters based parsing.

cmp-lg↗

arXiv1997

Combining Unsupervised Lexical Knowledge Methods for Word Sense Disambiguation

This paper presents a method to combine a set of unsupervised algorithms that can accurately disambiguate word senses in a large, completely untagged corpus. Although most of the techniques for word sense resolution have been presented as stand-alone, it is our belief that full-fledged lexical ambiguity resolution should combine several information sources and techniques. The set of techniques have been applied in a combined way to disambiguate the genus terms of two machine-readable dictionaries (MRD), enabling us to construct complete taxonomies for Spanish and French. Tested accuracy is above 80% overall and 95% for two-way ambiguous genus terms, showing that taxonomy building is not limited to structured dictionaries such as LDOCE.

cmp-lg↗

arXiv1997

Developing a hybrid NP parser

We describe the use of energy function optimization in very shallow syntactic parsing. The approach can use linguistic rules and corpus-based statistics, so the strengths of both linguistic and statistical approaches to NLP can be combined in a single framework. The rules are contextual constraints for resolving syntactic ambiguities expressed as alternative tags, and the statistical language model consists of corpus-based n-grams of syntactic tags. The success of the hybrid syntactic disambiguator is evaluated against a held-out benchmark corpus. Also the contributions of the linguistic and statistical language models to the hybrid model are estimated.

cmp-lg↗

arXiv1997

Morphological Disambiguation by Voting Constraints

We present a constraint-based morphological disambiguation system in which individual constraints vote on matching morphological parses, and disambiguation of all the tokens in a sentence is performed at the end by selecting parses that receive the highest votes. This constraint application paradigm makes the outcome of the disambiguation independent of the rule sequence, and hence relieves the rule developer from worrying about potentially conflicting rule sequencing. Our results for disambiguating Turkish indicate that using about 500 constraint rules and some additional simple statistics, we can attain a recall of 95-96% and a precision of 94-95% with about 1.01 parses per token. Our system is implemented in Prolog and we are currently investigating an efficient implementation based on finite state transducers.

cmp-lg↗

arXiv1997

Quantitative Constraint Logic Programming for Weighted Grammar Applications

Constraint logic grammars provide a powerful formalism for expressing complex logical descriptions of natural language phenomena in exact terms. Describing some of these phenomena may, however, require some form of graded distinctions which are not provided by such grammars. Recent approaches to weighted constraint logic grammars attempt to address this issue by adding numerical calculation schemata to the deduction scheme of the underlying CLP framework. Currently, these extralogical extensions are not related to the model-theoretic counterpart of the operational semantics of CLP, i.e., they do not come with a formal semantics at all. The aim of this paper is to present a clear formal semantics for weighted constraint logic grammars, which abstracts away from specific interpretations of weights, but nevertheless gives insights into the parsing problem for such weighted grammars. Building on the formalization of constraint logic grammars in the CLP scheme of Hoehfeld and Smolka 1988, this formal semantics will be given by a quantitative version of CLP. Such a quantitative CLP scheme can also be valuable for CLP tasks independent of grammars.

cmp-lg↗

arXiv1997

The TreeBanker: a Tool for Supervised Training of Parsed Corpora

I describe the TreeBanker, a graphical tool for the supervised training involved in domain customization of the disambiguation component of a speech- or language-understanding system. The TreeBanker presents a user, who need not be a system expert, with a range of properties that distinguish competing analyses for an utterance and that are relatively easy to judge. This allows training on a corpus to be completed in far less time, and with far less expertise, than would be needed if analyses were inspected directly: it becomes possible for a corpus of about 20,000 sentences of the complexity of those in the ATIS corpus to be judged in around three weeks of work by a linguistically aware non-expert.

cmp-lg↗

arXiv1997

A Comparative Study of the Application of Different Learning Techniques to Natural Language Interfaces

In this paper we present first results from a comparative study. Its aim is to test the feasibility of different inductive learning techniques to perform the automatic acquisition of linguistic knowledge within a natural language database interface. In our interface architecture the machine learning module replaces an elaborate semantic analysis component. The learning module learns the correct mapping of a user's input to the corresponding database command based on a collection of past input data. We use an existing interface to a production planning and control system as evaluation and compare the results achieved by different instance-based and model-based learning algorithms.

cmp-lg↗

arXiv1997

Learning Parse and Translation Decisions From Examples With Rich Context

We present a knowledge and context-based system for parsing and translating natural language and evaluate it on sentences from the Wall Street Journal. Applying machine learning techniques, the system uses parse action examples acquired under supervision to generate a deterministic shift-reduce parser in the form of a decision structure. It relies heavily on context, as encoded in features which describe the morphological, syntactic, semantic and other aspects of a given parse state.

cmp-lg↗

arXiv1997

Three New Probabilistic Models for Dependency Parsing: An Exploration

After presenting a novel O(n^3) parsing algorithm for dependency grammar, we develop three contrasting ways to stochasticize it. We propose (a) a lexical affinity model where words struggle to modify each other, (b) a sense tagging model where words fluctuate randomly in their selectional preferences, and (c) a generative model where the speaker fleshes out each word's syntactic and conceptual structure without regard to the implications for the hearer. We also give preliminary empirical results from evaluating the three models' parsing performance on annotated Wall Street Journal training text (derived from the Penn Treebank). In these results, the generative (i.e., top-down) model performs significantly better than the others, and does about equally well at assigning part-of-speech tags.

cmp-lg↗

arXiv1997

Library of Practical Abstractions, Release 1.2

The library of practical abstractions (LIBPA) provides efficient implementations of conceptually simple abstractions, in the C programming language. We believe that the best library code is conceptually simple so that it will be easily understood by the application programmer; parameterized by type so that it enjoys wide applicability; and at least as efficient as a straightforward special-purpose implementation. You will find that our software satisfies the highest standards of software design, implementation, testing, and benchmarking. The current LIBPA release is a source code distribution only. It consists of modules for portable memory management, one dimensional arrays of arbitrary types, compact symbol tables, hash tables for arbitrary types, a trie module for length-delimited strings over arbitrary alphabets, single precision floating point numbers with extended exponents, and logarithmic representations of probability values using either fixed or floating point numbers. We have used LIBPA to implement a wide range of statistical models for both continuous and discrete domains. The time and space efficiency of LIBPA has allowed us to build larger statistical models than previously reported, and to investigate more computationally-intensive techniques than previously possible. We have found LIBPA to be indispensible in our own research, and hope that you will find it useful in yours.

cmp-lg↗

arXiv1997

A Corpus-Based Approach for Building Semantic Lexicons

Semantic knowledge can be a great asset to natural language processing systems, but it is usually hand-coded for each application. Although some semantic information is available in general-purpose knowledge bases such as WordNet and Cyc, many applications require domain-specific lexicons that represent words and categories for a particular topic. In this paper, we present a corpus-based method that can be used to build semantic lexicons for specific categories. The input to the system is a small set of seed words for a category and a representative text corpus. The output is a ranked list of words that are associated with the category. A user then reviews the top-ranked words and decides which ones should be entered in the semantic lexicon. In experiments with five categories, users typically found about 60 words per category in 10-15 minutes to build a core semantic lexicon.

cmp-lg↗

arXiv1997

A Linear Observed Time Statistical Parser Based on Maximum Entropy Models

This paper presents a statistical parser for natural language that obtains a parsing accuracy---roughly 87% precision and 86% recall---which surpasses the best previously published results on the Wall St. Journal domain. The parser itself requires very little human intervention, since the information it uses to make parsing decisions is specified in a concise and simple manner, and is combined in a fully automatic way under the maximum entropy framework. The observed running time of the parser on a test sentence is linear with respect to the sentence length. Furthermore, the parser returns several scored parses for a sentence, and this paper shows that a scheme to pick the best parse from the 20 highest scoring parses could yield a dramatically higher accuracy of 93% precision and recall.

cmp-lg↗

arXiv1997

Determining Internal and External Indices for Chart Generation

This paper presents a compilation procedure which determines internal and external indices for signs in a unification based grammar to be used in improving the computational efficiency of lexicalist chart generation. The procedure takes as input a grammar and a set of feature paths indicating the position of semantic indices in a sign, and calculates the fixed-point of a set of equations derived from the grammar. The result is a set of independent constraints stating which indices in a sign can be bound to other signs within a complete sentence. Based on these constraints, two tests are formulated which reduce the search space during generation.

cmp-lg↗

arXiv1997

Text Segmentation Using Exponential Models

This paper introduces a new statistical approach to partitioning text automatically into coherent segments. Our approach enlists both short-range and long-range language models to help it sniff out likely sites of topic changes in text. To aid its search, the system consults a set of simple lexical hints it has learned to associate with the presence of boundaries through inspection of a large corpus of annotated data. We also propose a new probabilistically motivated error metric for use by the natural language processing and information retrieval communities, intended to supersede precision and recall for appraising segmentation algorithms. Qualitative assessment of our algorithm as well as evaluation using this new metric demonstrate the effectiveness of our approach in two very different domains, Wall Street Journal articles and the TDT Corpus, a collection of newswire articles and broadcast news transcripts.

cmp-lg↗

arXiv1997

Name Searching and Information Retrieval

The main application of name searching has been name matching in a database of names. This paper discusses a different application: improving information retrieval through name recognition. It investigates name recognition accuracy, and the effect on retrieval performance of indexing and searching personal names differently from non-name terms in the context of ranked retrieval. The main conclusions are: that name recognition in text can be effective; that names occur frequently enough in a variety of domains, including those of legal documents and news databases, to make recognition worthwhile; and that retrieval performance can be improved using name searching.

cmp-lg↗