With the emergence of broad-coverage parsers, quantitative evaluation of parsers becomes increasingly more important. We propose a dependency-based method for evaluating broad-coverage parsers that offers more meaningful performance measures than previous approaches. We also present a structural pattern-matching mechanism that can be used to eliminate inconsequential differences among different parse trees. Previous evaluation methods have only evaluated the overall performance of parsers. The dependency-based method can also evaluate parsers with respect to different kinds of grammatical relationships or different types of lexical categories. An algorithm for transforming constituency trees into dependency trees is presented, which makes the evaluation method applicable to both constituency grammars and dependency grammars.

This paper describes tactical generation in Turkish, a free constituent order language, in which the order of the constituents may change according to the information structure of the sentences to be generated. In the absence of any information regarding the information structure of a sentence (i.e. topic, focus, background, etc.), the constituents of the sentence obey a default order, but the order is almost freely changeable, depending on the constraints of the text flow or discourse. We have used a recursively structured finite state machine (much like a Recursive Transition Network (RTN)) for handling the changes in constituent order, implemented as a right-linear grammar backbone. Our implementation environment is the GenKit system, developed at Carnegie Mellon University, Center for Machine Translation. Morphological realization has been implemented using an external morphological analysis/generation component which performs concrete morpheme selection and handles morphographemic processes.

This paper describes two experiments: one exploring the amount of information relevant to sense disambiguation contained in the part-of-speech field of entries in a Machine Readable Dictionary (MRD); the other, more practical, experiment attempts sense disambiguation of all content words in a text assigning MRD homographs as sense tags using only part-of-speech information. We have implemented a simple sense tagger which successfully tags 94% of words using this method. A plan to extend this work and implement an improved sense tagger is included.

This paper deals with the development of parsing techniques for the analysis of natural language sentences. We present a paradigm of a multi- path shift-reduce parser which combines two differently structured computational subsystems. The first uses information concerning native speakers' preferences, and the second deals with the linguistic knowledge. To apply preferences on parsing, we propose a method to rank the alternative partial analyses on the basis of parse context and frequency of use effects. The method is mainly based on psycholinguistic evidence, since we hope eventually to build a parser working as closely as possible to the way native speakers analyse natural sentences. We also discuss in detail techniques for optimizing the effectiveness of the proposed model. The system has worked successfully in parsing sentences in Modern Greek, a language where the relatively free word order characteristic results in many ambiguity problems. The proposed parsing model is consistent with many directions in the field of preference-based parsing, and it is proved to be adequate in building effective and maintainable natural language analysers. It is believed that this model can also be used in parsing sentences in languages other than Greek.