This paper describes the motivation and design of the Corpus Encoding Standard (CES) (Ide, et al., (1996); Ide, 1998), an encoding standard for linguistic corpora intended to meet the need for the development of standardized encoding practices for linguistic corpora. The CES identifies a minimal encoding level that corpora must achieve to be considered standardized in terms of descriptive representation (marking of structural and linguistic information). It also provides encoding conventions for more extensive encoding and for linguistic annotation, as well as general architecture for representing corpora annotated for linguistic features. The CES has been developed taking into account several practical realities surrounding the encoding of corpora intended for use in language engineering research and applications. Full documentation of the standard is available on the World Wide Web at http://www.cs.vassar.edu/CES/.
A long-standing goal for the field of artificial intelligence is to enable computer understanding of human languages. A core requirement in reaching this goal is the ability to transform individual sentences into a form better suited for computer manipulation. This ability, called semantic parsing, requires several knowledge sources, such as a grammar, lexicon, and parsing mechanism. Building natural language parsing systems by hand is a tedious, error-prone undertaking. We build on previous research in automating the construction of such systems using machine learning techniques. The result is a combined system that learns semantic lexicons and semantic parsers from one common set of training examples. The input required is a corpus of sentence/representation pairs, where the representations are in the output format desired. A new system, WOLFIE, learns semantic lexicons to be used as background knowledge by a previously developed parser acquisition system, CHILL. The combined system is tested on a real world domain of answering database queries. We also compare this combination to a combination of CHILL with a previously developed lexicon learner, demonstrating superior performance with our system. In addition, we show the ability of the system to learn to process natural languages other than English. Finally, we test the system on an alternate sentence representation, and on a set of large, artificial corpora with varying levels of ambiguity and synonymy. One difficulty in using machine learning methods for building natural language interfaces is building the required annotated corpus. Therefore, we also address this issue by using active learning to reduce the number of training examples required by both WOLFIE and CHILL. Experimental results show that the number of examples needed to reach a given level of performance can be significantly reduced with this method.
Phrase(cid:0)based language models have been recognized to have an advantage over word(cid:0)based language models since they allow us to capture long span(cid:0) ning dependencies(cid:1) Class based language models have been used to improve model generalization and overcome problems with data sparseness(cid:1) In this pa(cid:0) per(cid:2) we present a novel approach for combining the phrase acquisition with class construction process to automatically acquire phrase(cid:0)grammar fragments from a given corpus(cid:1) The phrase(cid:0)grammar learning is decomposed into two sub(cid:0)problems(cid:2) namely the phrase acquisition and feature selection(cid:1) The phrase acquisition is based on entropy minimizationand the feature selection is driven by the entropy reduction principle(cid:1) We further demonstrate that the phrase(cid:0) grammarbased n(cid:0)gram language model signi(cid:3)cantly outperforms a phrase(cid:0)based n(cid:0)gram language model in an end(cid:0)to(cid:0)end evaluation of a spoken language application(cid:1) (cid:0)
This paper investigates interactions between collocational properties and methods for organizing them into features for machine learning. In experiments performing an event categorization task, Wiebe et al. (1997a) found that di(cid:11)erent organizations are best for different properties. This paper presents a statistical analysis of the results across di(cid:11)erent machine learning algorithms. In the experiments, the relationship between property and organization was strikingly consistent across algorithms. This prompted further analysis of this relationship, and an investigation of criteria for recognizing bene(cid:12)cial ways to include collocational properties in machine learning experiments. While many types of collocational properties and methods of organizing them into features have been used in NLP, systematic investigations of their interaction are rare.
This paper describes a partial parser that assigns syntactic structures to sequences of part-of-speech tags. The program uses the maximum entropy parameter estimation method, which allows a flexible combination of different knowledge sources: the hierarchical structure, parts of speech and phrasal categories. In effect, the parser goes beyond simple bracketing and recognises even fairly complex structures. We give accuracy figures for different applications of the parser.
