Downloads & Free Reading Options - Results

This reports provides an overview of the findings and software that have evolved from the Use of Minimal Lexical Conceptual Structures for Single-Document Summarization project over the last six months. We present the major goals that have been achieved and discuss some of the open issues that we intend to address in the near future. This report also contains some details on the usage of some software that has been implemented during the project.

This paper describes a system for generating natural language sentences from an inter lingual representation, Lexical Conceptual Structure (LCS). This system has been developed as part of a Chinese-English Machine Translation system, however, it promises to be useful for many other MT language pairs. The generation system has also been used in Cross-Language information retrieval research (Levow et al., 2000). One of the big challenges in Natural Language processing efforts is to be able to make use of existing resources, a big difficulty being the sometimes large differences in syntax, semantics, and ontologies of such resources. A case in point is the interlingua representations used for machine translation and cross-language processing. Such representations are becoming fairly popular, yet there are widely different views about what these languages should be composed of, varying from purely conceptual knowledge-representations, having little to do with the structure of language, to very syntactic representations, maintaining most of the idiosyncrasies of the source languages. In our generation system we make use of resources associated with two different (kinds of) interlingua structures: Lexical Conceptual Structures (LCS), and the Abstract Meaning Representations used at USC/ISI (Langkilde and Knight, 1998).