~ ROA Version, 8/2002. Essentially identical to the Tech Report, with new pagination (but the same footnote and example numbering); correction of typos, oversights & outright errors; improved typography; and occasional small-scale clarificatory rewordings. Citation should include reference to this version.

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

A distributed neural network model called SPEC for processing sentences with recursive relative clauses is described. The model is based on separating the tasks of segmenting the input word sequence into clauses, forming the case-role representations, and keeping track of the recursive embeddings into di erent modules. The system needs to be trained only with the basic sentence constructs, and it generalizes not only to new instances of familiar relative clause structures, but to novel structures as well. SPEC exhibits plausible memory degradation as the depth of the center embeddings increases, its memory is primed by earlier constituents, and its performance is aided by semantic constraints between the constituents. The ability to process structure is largely due to a central executive network that monitors and controls the execution of the entire system. This way, in contrast to earlier subsymbolic systems, parsing is modeled as a controlled high-level process rather than one based on automatic re ex responses. 1

This paper describes techniques for integrating neural networks and symbolic components into powerful hybrid systems. Neural networks have unique processing characteristics that enable tasks to be performed that would be di cult or intractable for a symbolic rule-based system. However, a stand-alone neural network requires an interpretation either by ahuman or a rulebased system. This motivates the integration of neural/symbolic techniques within a hybrid system. Anumber of integration possibilities exist: some systems consist of neural network components performing symbolic tasks while other systems are composed of several neural networks and symbolic components, each component acting as a self-contained module communicating with the others. Other hybrid systems are able to transform subsymbolic representations into symbolic ones and vice-versa. This paper providesanoverview and evaluation of the state of the artofseveral hybrid neural systems for rule-based processing. 1

The main claim of this paper is that connectionism offers cognitive science a number of excellent opportunities for turning methodological, theoretical. and meta-theoretica! schisms into powerfnl integrations--opportunities for forging constructive synergy out of the destructive interference which plagues the field. The paper begins with an analysis of the rifts in tile field and what it would take to overcome them. We argue that while connectionism ha,s often contributed to the deepexLing of these schisms, ]t is nonetheless possible to turn this trend around--possible for connectionism to play a central role in a unification of cognitive science. Essential o this process is the development of strong theoretical principles founded (in part) on connectionist computation; a main goal of this paper is to demonstrate that such principles are indeed within the reach of a connectionist-grounded theory of cognition. The enterprise rests on a willingness to entertain, analyze, and extend characterizations of cognitive problems, and hypothesized solutions, which are deliberately overly simple and general--in order to disco4'er the insights they can offer through mathematical a.na.lyses which this simplicity and generality are makes possible.

This paper is a survey of the current machine translation research in the US, Europe and Japan. A short history of machine translation is presented first, followed by an overview of the current research work. Representative examples of a wide range of different approaches adopted by machine translation researchers are presented. These are described in detail along with a discussion of the practicalities of scaling up these approaches for operational environments. In support of this discussion, issues in, and techniques for, evaluating machine translation systems are addressed.

A general definition of rationalist and empiricist natural language processing is attempted. A classification of empiricist machine translation systems is given based on the rationalist/empiricist distinction. Examples of approaches falling into the two different strategies are discussed. Research results are reported from attempts to break new ground in what is referred to as "pure " or non-hybrid example-based machine translation.

Introduction Natural language processing appears on the surface to be a strongly symbolic activity. Words are symbols that stand for objects and concepts in the real world, and they are put together into sentences that obey well-specified grammar rules. It is no surprise that for several decades natural language processing research has been dominated by the symbolic approach. Linguists have focused on describing language systems based on versions of the Universal Grammar. Artificial Intelligence researchers have built large programs where linguistic and world knowledge is expressed in symbolic structures, usually in LISP. Relatively little attention has been paid to various cognitive effects in language processing. Human language users perform differently from their linguistic competence, that is, from their knowledge of how to communicate correctly using language. Some linguistic structures (such as deep embeddings) are harder to deal with than others. People make mistakes wh

Current connectionist parsing systems lack the ability to parse sentences of arbitrary length and to compute complex syntax trees. We propose that by using symbolic procedures within an connectionist architecture these problems can be solved. In addition, symbolic procedures can be used to hardwire a priori knowledge about the problem domain into the system. By doing this we get smaller networks which are easy to train. In the ProPars system symbolic procedures are used to implement a hybrid architecture that can parse sentences of arbitrary length, compute complex syntax trees, and integrate semantic and prosodic information from the speech signal into the parsing process. 1 Introduction Linguistic theory is traditionally divided into subfields such as phonetics, phonology, morphology, syntax, semantics, and pragmatics. Though each of these fields have independently developed quite powerful theories, interactions between different fields or the integration into one theory are still n...

or so, neural or connectionist networks have produced an explosion of results and a great deal of interest. Yet this approach to the computational modeling of intelligent cognitive systems faces fundamental problems. The research proposed here has a major connectionist component, but it distinguishes itself from the bulk of connectionist research in the following respects: (0) a. It is strongly guided by symbolic computation, but not a "hybrid" in the usual sense: the connectionist and symbolic computation involved are not two components of a composite system, but two descriptions of a single system. We call this "integrated connection- ist/symbolic computation." b. The emphasis is on higher level cognitive processes, with a main focus on language, which provides a particularly chaJJenging testbed, since symbolic computation is so central to existing theory. c. The main emphasis in the language research is on formal grammars for natural language, with supporting research on the gram