A parsing system returning analyses in the form of sets of grammatical relations can obtain high precision if it hypothesises a particular relation only when it is certain that the relation is correct. We operationalise this technique---in a statistical parser using a manually-developed wide-coverage grammar of English---by only returning relations that form part of all analyses licensed by the grammar. We observe an increase in precision from 75% to over 90% (at the cost of a reduction in recall) on a test corpus of naturally-occurring text.

Designers routinely explain their designs to one another using sketches and verbal descriptions of behavior, both of which can be understood long before the device has been fully specified. But current design tools fail almost completely to support this sort of interaction, instead not only forcing designers to specify details of the design, but typically requiring that they do so by navigating a forest of menus and dialog boxes, rather than directly describing the behaviors with sketches and verbal explanations. We have created a prototype system, called assistance, capable of interpreting multimodal explanations for simple 2-D kinematic devices. The program generates a model of the events and the causal relationships between events that have been described via hand drawn sketches, sketched annotations, and verbal descriptions. Our goal is to make the designer's interaction with the computer more like interacting with another designer. This requires the ability not only to understand physical devices but also to understand the means by which the explanations of these devices are conveyed.

We have been working on a variety of projects aimed at providing natural forms of interaction with computers, centered primarily around the use of sketch understanding.

this paper is to highlight a area of MT usually ignored, and to propose a non-theory specific solution, we will not give an overview of all types of MT systems.

It is often argued that accurate machine translation requires reference to contextual knowledge for the correct treatment of linguistic phenomena such as dropped arguments and accurate lexical selection. One of the historical arguments in favor of the interlingua approach has been that, since it revolves around a deep semantic representation, it is better able to handle the types of linguistic phenomena that are seen as requiring a knowledge-based approach. In this paper we present an alternative approach, exemplified by a prototype system for machine translation of English and Korean which is implemented in Synchronous TAGs. This approach is essentially transfer based, and uses semantic feature unification for accurate lexical selection of polysemous verbs. The same semantic features, when combined with a discourse model which stores previously mentioned entities, can also be used for the recovery of topicalized arguments. In this paper we concentrate on the translation of Korean to English. 1

Grammatical relationships are an important level of natural language processing. We present a trainable approach to find these relationships through transformation sequences and-error-driven learning. Our approach finds grammatical relationships between core syntax groups and bypasses much of the parsing phase. On our training and test set, our procedure achieves 63.6% recall and 77.3% precision (f-score = 69.8).

This paper describes the use of verb class memberships as a means of capturing generalizations about manner-of-motion verbs in Synchronous Tree Adjoining Grammars, STAGs, [20, 21, 22]. This approach allows STAGs, which are essentially transfer-based, to take advantage of the same types of generalizations which are generally thought of as wholly the domain of interlingua systems- without giving up any of the lexical specificity unique to transfer-based systems. In this way a machine translation system based on STAGs can respond with seamless flexibility to a wide spectrum of phenomena being presented for translation ranging from idioms and idiosyncratic lexical items to well-behaved verbs that follow lexical rules. 1

This paper addresses various issues related to representing the Korean language using Tree Adjoining Grammars. Topics covered include Korean grammar using TAGs, Machine Translation between Korean and English using Synchronous Tree Adjoining Grammars (STAGs), handling scrambling using Multi Component TAGs(MC-TAGs), and recovering empty arguments. The data for the parsing is from US military telecommunication messages. Chapter 1 Overview Linguistics and computer science are merging closer together in natural language processing. Especially in Korean, many scholars have made notable contributions including a wide spectrum of studies such as pragmatics of compound verbs, indirect speech acts, and parsing methods. Unfortunately, most of them paid little attention to combining these ideas together to formalize linguistic theory into computer science, and vice versa. Beyond just observing a phenomenon, linguists should be able to formalize it, or give a reason to prove that their observatio...

This thesis concerns the notion of `information structure': informally, organization of information in an utterance with respect to the context. Information structure has been recognized as a critical element in a number of computer applications: e.g., selection of contextually appropriate forms in machine translation and speech generation, and analysis of text readability in computer-assisted writing systems. One of the problems involved in these applications is how to identify information structure in extended texts. This problem is often ignored, assumed to be trivial, or reduced to a sub-problem that does not correspond to the complexity of realistic texts. A handful of computational proposals face the problem directly, but they are generally limited in coverage and all suffer from lack of evaluation. To fully demonstrate ...

ion at which Discourse is Described: In general, approaches advocating fewer discourse relations tend to address higher levels of abstraction. Nature of Discourse Segments: A key question here is whether discourse segments have psychological reality or whether they are abstract linguistic units akin to phonemes. Recently, there have been attempts to identify the boundary features of discourse segments (Hirschberg & Grosz, 1992; Litman & Passoneau, 1993). Role of Intentions in Discourse: It is well-recognized that intentions play an important role in discourse. However, of the four predominant computational theories, only that of Grosz and Sidner provides an explicit treatment of intentionality. Mechanisms for Handling Key Linguistic Phenomena: Of the predominant theories, only RST fails to address the issues of discourse focus, reference resolution and cue phrases. Existing treatments of focus, however, suffer from terminological confusion between notions of focus, theme and topic, ...