Brian Milch
Brian Milch is a software engineer at Google's Santa Monica, CA office. He completed a B.S. in Symbolic Systems at Stanford University in 2000, and spent a year as an engineer at Google before entering the Ph.D. program in Computer Science at U.C. Berkeley. He received his Ph.D. in 2006. He then spent two years as a post-doctoral researcher at MIT before rejoining Google in 2008. His research interests are in machine learning and artificial intelligence, especially the combination of probabilistic and logical approaches. He was named one of the "10 to Watch in AI" by IEEE Intelligent Systems magazine in 2008.
Research Areas
Authored Publications
Sort By
Query-Free News Search
Monika Henzinger
Bay-Wei Chang
Proceedings of the 12th International World Wide Web Conference (WWW-2003), Budapest, Hungary
Preview abstract
Many daily activities present information in the form of a stream of text, and often people can benefit from additional information on
the topic discussed. TV broadcast news can be treated as one such stream of text; in this paper we discuss finding news articles on the
web that are relevant to news currently being broadcast.
We evaluated a variety of algorithms for this problem, looking at the impact of inverse document frequency, stemming, compounds, history, and query length on the relevance and coverage of news articles returned in real time during a broadcast. We also evaluated several postprocessing techniques for improving the precision, including reranking using additional terms, reranking by document similarity, and filtering on document similarity. For the best algorithm, 84%-91% of the articles found were relevant, with at least 64% of the articles being on the exact topic of the broadcast. In addition, a relevant article was found for at least 70% of the topics.
View details
Searching the Web by Voice
Alexander Franz
Proceedings of the 19th International Conference on Computational Linguistics (COLING) (2002), pp. 1213-1217
Preview abstract
Spoken queries are a natural medium for searching the Web in settings where typing on a keyboard is not practical. This paper describes a speech interface to the Google search engine. We present experiments with various statistical language models, concluding that a unigram model with collocations provides the best combination of broad coverage, predictive power, and real-time performance. We also report accuracy results of the prototype system.
View details
