Semantic relationships among words and phrases are often marked by explicit syntactic or lexical clues that help recognize such relationships in texts. Within complex nominals, however, few overt clues are available. Systems that analyze such nominals must compensate for the lack of surface clues with other information. One way is to load the system with lexical semantics for nouns or adjectives. This merely shifts the problem elsewhere: how do we define the lexical se- mantics and build large semantic lexicons? Another way is to find constructions similar to a given complex nominal, for which the relationships are already known. This is the way we chose, but it too has drawbacks.

We describe a prototype intelligent information retrieval system that uses natural-language understanding to efficiently locate captioned data. Multimedia data generally require captions to explain their features and significance. Such descriptive captions often rely on long nominal compounds (strings of consecutive nouns) which create problems of disambiguating word sense. In our system, captions and user queries are parsed and interpreted to produce a logical form, using a detailed theory of the meaning of nominal compounds. A fine-grain match can then compare the logical form of the query to the logical forms for each caption. To improve system efficiency, we first perform a coarse-grain match with index files, using nouns and verbs extracted from the query. Our experiments with randomly selected queries and captions from an existing image library show an increase of 30 % in precision and 50 % in recall over the keyphrase approach currently used. Our processing times have a median of seven seconds as compared to eight minutes for the existing system, and our system is much easier to use.

Noun compound interpretation is the task of determining the semantic relations among the constituents of a noun compound. For example, “concrete floor” means a floor made of concrete, while “gymnasium floor” is the floor region of a gymnasium. We would like to enable knowledge acquisition systems to interpret noun compounds, as part of their overall task of translating imprecise and incomplete information into formal representations that support automated reasoning. However, if interpreting noun compounds requires detailed knowledge of the constituent nouns, then it may not be worth doing: the cost of acquiring this knowledge may outweigh the potential benefit. This paper describes an empirical investigation of the knowledge required to interpret noun compounds. It concludes that the axioms and ontological distinctions important for this task are derived from the top levels of a hierarchical knowledge base (KB); detailed knowledge of specific nouns is less important. This is good news, not only for our work on knowledge acquisition systems, but also for research on text understanding, where noun compound interpretation has a long history.

We describe ONIONS, a methodology for integrating ontologically-heterogeneous taxonomic knowledge and its current application to medical domain. Some clarification is given of our intended meaning of ontology and related notions, then main problems of ontology design are addressed, with a short comparison with alternative approaches. The methodology is described as a sequence of phases. The top-level of the current integrated ontology of heterogeneous medical taxonomies is presented in an order-sorted logic. ONIONS includes no claim of global objectivity (it performs an integration of explicit ---or explicited--- ontologies of given taxonomic sources), but provides a feasible solution to the problems of modelling stopover and cognitive basicality. ONIONS has been defined in order to be applied to sources within the same domain, nevertheless it has been applied to a very wide and inherently heterogeneous domain like medicine, so complex that it can be considered in itself an integration of subdomains. 1.

. Noun phrases carry much of the information in a text. Systems that attempt to acquire knowledge from text must first decompose complex noun phrases to get access to that information. In the case of noun compounds, this decomposition usually means bracketing the modifiers into nested modifierhead pairs. It is then possible to determine the semantic relationships among individual components of the noun phrase. This paper describes a semi-automatic system for bracketing an unlimited number of adjectival or nominal premodifiers. Since the system is intended to start processing with no prior knowledge, it gets trained as it brackets. That is, it starts from scratch and accumulates bracketing evidence while processing a text under user supervision. Experiments show that generalizations of the structure of complex modifier sequences allow the system to bracket previously unseen compounds correctly. Furthermore, as more compounds are bracketed, the number of bracketing decision...

This paper describes work in progress on part of HAIKU (Delisle et al. 1996), a system to extract semantic information from English technical text. Semantic processing in HAIKU consists of three parts: clause level relationship analysis, case analysis and noun modifier relationship analysis. This paper reports on early work on noun modifier relationship analysis. Research to date includes the construction of a set of semantic labels for the relationships between nouns and their modifiers, the design of algorithms to semi-automatically assign these labels to pairs of elements in noun phrases, as well as an implemented semi-automatic learning bracketer for sequences of multiple premodifiers of head nouns.

The Knowledge-Based Machine Translation paradigm requires a comprehensive analysis of input texts into an unambiguous machine-tractable representation of the propositional and meta-propositional meaning of that text, for which we use a particular framework referred to as ontological semantics. The work presented here begins with a definition of a representation language for lexical semantic specification (and syntax/semantics interface) to support such an analysis, as well as a generalized algorithm for building the meaning representation from these lexical semantic specifications, utilizing the ontology and a syntactic parse as knowledge sources. The core of the algorithm is an algorithm for semantic constraint satisfaction and relaxation, involving finding the best path over the ontology between a candidate filler of a relation and semantic constraints on that relation. The ontology is viewed as a multi-dimensional graph, with distinct topologies in each dimension reflecting specific semantic relations between nodes (representing concepts) , where weights or arc distance reflects strength of semantic relatedness in context (where the path-so-far context is maintained in a state transition table).

For natural language understanding systems designed for domains including relatively complex equipment, it is not sufficient to use general knowledge about this equipment. We show problems which can be solved only if the system has access to a detailed equipment model. We discuss the structure of such models in some detail and, in particular, the mixed static/dynamic nature of the model. As an illustration, we describe parts of a simulation model for an air compressor. Finally, we demonstrate how to find referents in this model for noun phrases.

In this paper we describe the organization and contents of the knowledge base (kb) developed for the processing of patient discharge summaries (pdss)---letters sent by a hospital consultant to a patient's own doctor. The processing system itself can be seen as a specialization of the Generic Information Extraction System outlined by Hobbs (Hobbs 1993). As it is stated in (Jacobs et al 1993) among the most succesfull information extraction systems "the main differentiator is not in the basic processing algorithms but in the way that knowledge ends up getting assigned to various system components". The kb is the major component in the processing of natural language by our system and includes both the conceptual and lexical knowledge represented in a uniform way. Conceptual knowledge in the kb is built and organized in a topdown fashion and explicitly targeted to represent information which was identified by domain experts to be important. Linguistic knowledge is built around t...

Semantic relationships among words and phrases are often marked by explicit syntactic or lexical clues that help recognize such relationships in texts. Within complex nominals, however, few overt clues are available. Systems that analyze such nominals must compensate for the lack of surface clues with other information. One way is to load the system with lexical semantics for nouns or adjectives. This merely shifts the problem elsewhere: how do we define the lexical se- mantics and build large semantic lexicons? Another way is to find constructions similar to a given complex nominal, for which the relationships are already known. This is the way we chose, but it too has drawbacks.