Recent Publications

Summary Generation through Intelligent Cutting and Pasting of the Input Document, Hongyan Jing, Ph.D. thesis proposal, February, 1998.
We present a framework for fast generating concise and coherent summaries in domain-independent, single-document summarization. The proposed generation approach, called cut-and-paste , generates summaries through reusing the input document. Rather than using the extracted document sentences directly for producing summaries, the cut-and-paste approach edits the sentences in some way so that they are more concise, coherent, and appropriate for summaries.
The Decomposition of Human-Written Summary Sentences, Hongyan Jing and Kathleen McKeown, In the Proceedings of the 22nd International Conference on Research and Development in Information Retrieval (SIGIR'99). August, 1999. University of Berkeley, CA.
We define the problem of decomposing human-written summary sentences and propose a novel Hidden Markov Model solution to the problem. Human summarizers often rely on cutting and pasting of the full document to generate summaries. Decomposing a human-written summary sentence requires determining: (1) whether it is constructed by cutting and pasting, (2) what components in the sentence come from the original document, and (3) where in the document the components come from. Solving the decomposition problem can potentially lead to the automatic acquisition of large corpora for summarization. It also sheds light on the generation of summary text by cutting and pasting. The evaluation shows that the proposed decomposition algorithm performs well.
Combining Multiple, Large-Scale Resources in a Reusable Lexicon for Natural Language Generation , Hongyan Jing and Kathleen McKeown, In the Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics (COLING-ACL'98). August 10-14, 1998. University de Montreal. Montreal, Quebec, Canada.
A lexicon is an essential component in a generation system but few efforts have been made to build a rich, large-scale lexicon and make it reusable for different generation applications. In this paper, we describe our work to build such a lexicon by combining %existing linguistic resources multiple, heterogeneous linguistic resources which have been developed for other purposes. Novel transformation and integration of resources is required to reuse them for generation. We also applied the lexicon to the lexical choice and realization component of a practical generation application by using a multi-level feedback architecture. The integration of the lexicon and the architecture is able to effectively improve the system paraphrasing power, minimize the chance of grammatical errors, and simplify the development process substantially.