that takes a raw, untagged text corpus as its only input (no open-class dictionary) and generates a partial list of verbs occurring in the text and the subcategorization frames (SFs) in which they occur. Verbs are detected by a novel technique based on the Case Filter of Rouvret and Vergnaud (1980). The completeness of the output list increases monotonically with the total number of occurrences of each verb in the corpus. Fakse positive rates are one to three percent of observations.

m we can carve o# next. `Partial parsing' is a cover term for a range of di#erent techniques for recovering some but not all of the information contained in a traditional syntactic analysis. Partial parsing techniques, like tagging techniques, aim for reliability and robustness in the face of the vagaries of natural text, by sacrificing completeness of analysis and accepting a low but non-zero error rate. 1 Tagging The earliest taggers [35, 51] had large sets of hand-constructed rules for assigning tags on the basis of words' character patterns and on the basis of the tags assigned to preceding or following words, but they had only small lexica, primarily for exceptions to the rules. TAGGIT [35] was used to generate an initial tagging of the Brown corpus, which was then hand-edited. (Thus it provided the data that has since been used to train other taggers [20].) The tagger described by Garside [56, 34], CLAWS, was a probabilistic version of TAGGIT, and the DeRose tagger improved on

This paper shows that decision trees can be used to improve the performance of casebased learning (CBL) systems. We introduce a performance task for machine learning systems called semi-flexible prediction that lies between the classification task performed by decision tree algorithms and the flexible prediction task performed by conceptual clustering systems. In semi-flexible prediction, learning should improve prediction of a specific set of features known a priori rather than a single known feature (as in classification) or an arbitrary set of features (as in conceptual clustering). We describe one such task from natural language processing and present experiments that compare solutions to the problem using decision trees, CBL, and a hybrid approach that combines the two. In the hybrid approach, decision trees are used to specify the features to be included in k-nearest neighbor case retrieval. Results from the experiments show that the hybrid approach outperforms both the decision ...

This paper describes a case-based approach to knowledge acquisition for natural language systems that simultaneously learns part of speech, word sense, and concept activation knowledge for all open class words in a corpus. The parser begins with a lexicon of function words and creates a case base of context-sensitive word definitions during a humansupervised training phase. Then, given an unknownwordand the context in which it occurs, the parser retrieves definitions from the case base to infer the word's syntactic and semantic features. By encoding context as part of a definition, the meaning of a word can change dynamically in response to surrounding phrases without the need for explicit lexical disambiguation heuristics. Moreover, the approach acquires all three classes of knowledge using the same case representation and requires relatively little training and no hand-coded knowledge acquisition heuristics. We evaluate it in experiments that explore two of many practical applications of the technique and conclude that the case-based method provides a promising approach to automated dictionary construction and knowledge acquisition for sentence analysis in limited domains. In addition, we present a novel case retrieval algorithm that uses decision trees to improve the performance of a k-nearest neighbor similarity metric.

this paper we outline a research program for computational linguistics, making extensive use of text corpora. We demonstrate how a semantic framework for lexical knowledge can suggest richer relationships among words in text beyond that of simple co-occurrence. The work suggests how linguistic phenomena such as metonymy and polysemy might be exploitable for semantic tagging of lexical items. Unlike with purely statistical collocational analyses, the framework of a semantic theory allows the automatic construction of predictions about deeper semantic relationships among words appearing in collocational systems. We illustrate the approach for the acquisition of lexical information for several classes of nominals, and how such techniques can fine-tune the lexical structures acquired from an initial seeding of a machine-readable dictionary. In addition to conventional lexical semantic relations, we show how information concerning lexical presuppositions and preference relations can also be acquired from corpora, when analyzed with the appropriate semantic tools. Finally, we discuss the potential that corpus studies have for enriching the data set for theoretical linguistic research, as well as helping to confirm or disconfirm linguistic hypotheses

The availability of on-line corpora is rapidly changing the field of natural language processing (NLP) from one dominated by theoretical models of often very specific linguistic phenomena to one guided by computational models that simultaneously account for a wide variety of phenomena that occur in real-world text. Thus far, among the best-performing and most robust systems for reading and summarizing large amounts of real-world text are knowledge-based natural language systems. These systems rely heavily on domain-specific, handcrafted knowledge to handle the myriad syntactic, semantic, and pragmatic ambiguities that pervade virtually all aspects of sentence analysis. Not surprisingly, however, generating this knowledge for new domain...

This paper describes a system, WOLIm (WOrd Learning From Interpreted Examples), that acquires a semantic lexicon from a corpus of sentences paired with representations of their meaning. The lexicon learned consists of words paired with meaning representations. WOLFIE is part of an integrated system that learns to parse novel sentences into semantic representations, such as logical database queries. Experimental results are presented demonstrating WOLFIE'S ability to learn useful lexicons for a database interface in four different natural lan- guages. The lexicons learned by WOLFIE are compared to those acquired by a comparable system developed by Siskind (1996).

Sentence syntax is the basis for organizing semantic relations in TANKA, a project that aims to acquire knowledge from technical text. Other hallmarks include an absence of precoded domain-specific knowledge; significant use of public-domain generic linguistic information sources; involvement of the user as a judge and source of expertise; and learning from the meaning representations produced during processing. These elements shape the realization of the TANKA project: implementing a trainable text processing system to propose correct semantic interpretations to the user. A three-level model of sentence semantics including a comprehensive Case system provides the framework for TANKA’s representations. Text is first processed by the DIPETT parser, which can handle a wide variety of unedited sentences. The semantic analysis module HAIKU then semi-automatically extracts semantic patterns from the parse trees and composes them into domain knowledge representations. HAIKU’s dictionaries and main algorithm are described with the aid of examples and traces of user interaction. Encouraging experimental results are described and evaluated.

We present a method for individuating dependencies between the semantic class of predicates and their associated subcategorization frames, and describe an implementation which allows the cquisition of such dependencies from bracketed texts.

Building accurate and efficient natural language processing (NLP) systems is an important and difficult problem. There has been increasing interest in automating this process. The lexicon, or the mapping from words to meanings, is one component that is typically difficult to update and that changes from one domain to the next. Therefore, automating the acquisition of the lexicon is an important task in automating the ac- quisition of NLP systems. This proposal describes a system, Wo.Fm (WOrd Learning From Interpreted Examples), that learns a lexicon from input consisting of sentences paired with representations of their meanings. Preliminary experimental results show that this system can learn correct and useful mappings. The correctness is evaluated by comparing a known lexicon to one learned from the training input. The usefulness is evaluated by examining the effect of using the lexicon learned by Woe. mE to assist a parser acquisition system, where previously this lexicon had to be hand-built. Future work in the form of extensions to the algorithm, further evaluation, and possible applications is discussed.