The process of microplanning encompasses a range of problems in Natural Language Generation (NLG), such as referring expression generation, lexical choice, and aggregation, problems in which a generator must bridge underlying domain-specific representations and general linguistic representations. In this paper, we describe a uniform approach to microplanning based on declarative representations of a generator's communicative intent. These representations describe the RE- SULTS of NLG: communicative intent associates the concrete linguistic structure planned by the generator with inferences that show how the meaning of that structure communicates needed information about some application domain in the current discourse context. Our approach, implemented in the SPUD (sentence planning using description) microplanner, uses the lexicalized treeadjoining grammar formalism (LTAG) to connect structure to meaning and uses modal logic programming to connect meaning to context. At the same time, communicative intent representations provide a RESOURCE for the PROCESS of NLG. Using representations of communicative intent, a generator can augment the syntax, semantics and pragmatics of an incomplete sentence simultaneously, and can assess its progress on the various problems of microplanning incrementally. The declarative formulation of communicative intent translates into a well-defined methodology for designing grammatical and conceptual resources which the generator can use to achieve desired microplanning behavior in a specified domain. Contents 1 Motivation 3 2

Grammars are core elements of many NLP applications. In this paper, we present a system that automatically extracts lexicalized grammars from annotated corpora. The data produced by this system have been used in several tasks, such as training NLP tools (such as Supertaggers) and estimating the coverage of harid-crafted grammars. We report experimental results on two of those tasks and compare our approaches with related work.

We present a method for the extraction of stochastic lexicalized tree grammars (SLTG) of different complexities from existing treebanks, which allows us to analyze the relationship of a grammar automatically induced from a treebank wrt. its size, its complexity, and its predictive power on unseen data. Processing

This paper shows how DATR, a widely used formal language for lexical knowledge representation, can be used to define an [TAG lexicon as an inheritance hierarchy with internal lexical rules. A bottom-up learural encoding is used for [TAG trees and this allows lexical rules to be implemen- ted as covariation constraints within fea- ture structures. Such an approach eliminates the considerable redundancy otherwise associated with an I_TAG lexicon.

In this paper we present some novel applications of Explanation-Based Learning (EBL) technique to parsing Lexicalized Tree-Adjoining grammars. The novel as- pects are (a) immediate generalization of parses in the training set, (b) generalization over recursive structures and (c) representation of generalized parses as Finite State Transducers. A highly impoverished parser called a "stapler" has also been introduced.

In this paper, we present a new technique called LightweightDependency Analysis which in conjunctionwith Supertag disambiguation provides a method for Robust Partial Parsing, called Almost Parsing. An overview is given of the XTAG system in which this technique is being developed. In addition, we propose alternate metrics for evaluation of partial parsers that can also serve to evaluate full parsers.

Any coherent text contains significant latent information, such as syntactic structure and patterns of language use. This information can be exploited to overcome the inadequacies of keywordbased retrieval and make information retrieval more effective. In this paper, we demonstrate quantitatively how syntactic information is useful in filtering out irrelevant documents. We also compare two different syntactic labelings -- simple Part-of-Speech (POS) labeling and Supertag labeling -- and show how the richer (more fine-grained) representation of supertags leads to more effective document filtering. We have implemented a system which exploits syntactic information in a flexible manner to filter documents. The system has been tested on a large collection of newswire sentences, and achieves recall and precision figures of 86% and 97% for filtering out irrelevant documents. Its performance and modularity makes it a promising postprocessing addition to any Information Retrieval system.

Dierent NLP applications have dierent eciency constraints (i.e. quality of the results and throughput) that reect on each core linguistic component. Syntactic processors are basic modules in some NLP application. A customization that permits the performance control of these components enables their reuse in dierent application scenarios. Throughput has been commonly improved using partial syntactic processors. On the other hand, specialized lexicons are generally employed to improve the quality of the syntactic material produced by speci c parsing (sub)process (e.g. verb argument detection or PPattachment disambiguation). Building upon the idea of grammar strati cation, in this paper a method to push modularity and lexical sensitivity, in parsing, in view of customizable syntactic analysers is presented. A framework for modular parser design is proposed and its main properties are discussed.

In this paper, we describe a system called Glean, which is predicated on the idea that any coherent text contains significant latent information, such as syntactic structure and patterns of language use, which can be used to enhance the performance of Information Retrieval systems. We propose an approach to information retrieval that makes use of syntactic information obtained using a tool called a supertagger. A supertagger is used on a corpus of training material to semi-automatically induce patterns that we call augmented-patterns. We show how these augmented patterns may be used along with a standard Web search engine or an IR system to retrieve information, and to identify relevant information and filter out irrelevant items. We describe an experiment in the domain of official appointments, where such patterns are shown to reduce the number of potentially irrelevant documents by upwards of 80%.

In this paper, we propose a classification of grammar development strategies according to two criteria : hand-written versus automatically acquired grammars, and grammars based on a low versus high level of syntactic abstraction. Our classification yields four types of grammars. For each type, we discuss implementation and evaluation issues.