Improving cross-language text retrieval with human interactions

Can we expect people to be able to get information from texts in languages they cannot read? We review two relevant lines of research bearing on this question and show how our results are being used in the design of a new Web interface for cross-language text retrieval. One line of research, "interactive IR", is concerned with the user interface issues for information retrieval systems such as how best to display the results of a text search. We review our current research, on "document thumbnail" visualizations, and discuss current Web conventions, practices and folklore. The other area of research, "Cross-Language Text Retrieval", is concerned with the design of automatic techniques, including Machine Translation, to retrieve texts in languages other than the language of the query. We review work we have done concerning query translation and multilingual text summarization. We then describe how these results are being applied and extended in the design a new demonstration interface, Keizai, an end-to-end, Web-based, cross-language text retrieval system. Beginning with an English query, the system will search Japanese and Korean Web data and display English summaries of the top ranking documents. A user should be able to accurately judge which foreign language documents are relevant to their information need and glean necessary information from the translation to schedule specific documents for human translation and subsequent analysis.