Megumi Kameyama

SRI International FASTUS system: MUC-6 test results and analysis

SRI International participated in the MUC-6 evaluation using the latest version of SRIs FASTUS system [1]. The FASTUS system was originally developed for participation in the MUC-4 evaluation [3] in 1992, and the performance of FASTUS in MUC-4 helped demonstrate the viability of finite state technologies in constrained natural-language understanding tasks. The system has undergone significant revision since MUC-4, and it is safe to say that the current system does not share a single line of code with the original. The fundamental ideas behind FASTUS, however, are retained in the current system: an architecture consisting of cascaded finite state transducers, each providing an additional level of analysis of the input, together with merging of the final results.

Recognizing referential links: an information extraction perspective

We present an efficient and robust reference resolution algorithm in an end-to-end state-of-the-art information extraction system, which must work with a considerably impoverished syntactic analysis of the input sentences. Considering this disadvantage, the basic setup to collect, filter, then order by salience does remarkably well with third-person pronouns, but needs more semantic and discourse information to improve the treatments of other expression types.

TEMPORAL CENTERING

We present a semantic and pragmatic account of the anaphoric properties of past and perfect that improves on previous work by integrating discourse structure, aspectual type, surface structure and commonsense knowledge. A novel aspect of our account is that we distinguish between two kinds of temporal intervals in the interpretation of temporal operators --- discourse reference intervals and event intervals. This distinction makes it possible to develop an analogy between centering and temporal centering, which operates on discourse reference intervals. Our temporal property-sharing principle is a defeasible inference rule on the logical form. Along with lexical and causal reasoning, it plays a role in incrementally resolving underspecified aspects of the event structure representation of an utterance against the current context.

FASTUS: a system for extracting information from text

FASTUS is a (slightly permuted) acronym for Finite State Automaton Text Understanding System. It is a system for extracting information from free text in English (Japanese is under development), for entry into a database, and potentially for other applications. It works essentially as a set of cascaded, nondeterministic finite state automata.

Resolving Translation Mismatches With Information Flow

Languages differ in the concepts and real-world entities for which they have words and grammatical constructs. Therefore translation must sometimes be a matter of approximating the meaning of a source language text rather than finding an exact counterpart in the target language. We propose a translation framework based on Situation Theory. The basic ingredients are an information lattice, a representation scheme for utterances embedded in contexts, and a mismatch resolution scheme defined in terms of information flow. We motivate our approach with examples of translation between English and Japanese.

ATOMIZATION IN GRAMMAR SHARING

We describe a prototype SHARED GRAMMAR for the syntax of simple nominal expressions in Arabic, English, French, German, and Japanese implemented at MCC. In this grammar, a complex inheritance lattice of shared grammatical templates provides parts that each language can put together to form language-specific grammatical templates. We conclude that grammar sharing is not only possible but also desirable. It forces us to reveal crosslinguistically invariant grammatical primitives that may otherwise remain conflated with other primitives if we deal only with a single language or language type. We call this the process of GRAMMATICAL ATOMIZATION. The specific implementation reported here uses categorial unification grammar. The topics include the mono-level nominal category N, the functional distinction between ARGUMENT and NON-ARGUMENT of nominals, grammatical agreement, and word order types.

SRI's Tipster II Project

The principal barrier to the widespread use of information extraction technology is the difficulty in defining the patterns that represent ones information requirements. Much of the work that has been done on SRIs Tipster II project has been directed at overcoming this barrier. In this paper, after some background on the basic structure of the FASTUS system, we present some of these developments. Specifically, we discuss the declarative pattern specification language FastSpec, compile-time transformations, and adapting rules from examples. In addition, we have developed the basic capabilities of FASTUS. We describe our efforts in one are---coreference resolution. We are now experimenting with the use of FASTUS in improving document retrieval and this is also described.

MET Name Recognition with Japanese FASTUS

SRIs Japanese FASTUS used in the Multilingual Entity Task (MET) evaluation is the initial Japanese system based on the FastSpec pattern specification language. We describe its system architecture, strengths, weaknesses, and its contribution to the prospects of a full information extraction system.

INFORMATION EXTRACTION RESEARCH AND APPLICATIONS: CURRENT PROGRESS AND FUTURE DIRECTIONS

Analysts face a daunting task: they must accurately analyze, categorize, and assimilate a large body of information from a variety of sources and for a variety of domains of interest. The complexity of the task necessitates a variety of information access and extraction tools which technology up to this point has not been able to provide. SRIs TIPSTER Phase III project has focused on two major obstacles to the development of such tools: inadequate degrees of accuracy and portability. We begin by providing an overview of SRIs information extraction (IE) system, FASTUS, and then describe our efforts in these two areas in turn. We then conclude with some thoughts concerning future directions.