Kevin Bartz
ABSTRACT
In sponsored search, advertisers bid on phrases representative of offered products or services. For large advertisers, these phrases often come from quasi-algorithmically generated lists of thousands of terms prone to poor linguistic construction. A bidded term by itself is usually unsuitable for direct insertion into an ad copy template; it must be rephrased and capitalized properly to fit the template, possibly with additional language to avoid semantic ambiguity. We develop a natural language generation system to automate these steps, preparing a list of terms for insertion into an ad template. For each input term, our system first finds a proper word ordering by mining a corpus of Web search query logs. Next it determines whether the term is ambiguous and--if semantics dictate--attaches a clarifying modifier culled from query logs. Finally, it applies proper capitalization by analyzing pages from Web search engine results. Each step yields a plausible set of displayable forms from which a machine-learned model selects the best. The models are trained and tested on a large set of human-labeled data. The overall system significantly outperforms baseline systems that use simple heuristics.
- H. Akaike. A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19(6):716--723, 1974.Google Scholar
Cross Ref
- I. Alegria, B. Arrieta, A. D. de Ilarraza, E. Izagirre, and M. Maritxalar. Using machine learning techniques to build a comma checker for basque. Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pages 1--8, 2006. Google ScholarDigital Library
- M. Arellano. Panel Data Econometrics. Oxford University Press, Oxford, UK, 2003.Google Scholar
- C. Chelba and A. Acero. Adaptation of maximum entropy capitalizer: Little data can help a lot. Computer Speech & Language, 20(4):382--399, 2006.Google Scholar
- D. Conway. An algorithmic approach to english pluralization. Proceedings of the Second Annual Perl Conference, 1998.Google Scholar
- B. DiEugenio, J. Moore, and M. Paolucci. Learning features that predict cue usage. Proceedings of the 35th Annual Meeting of the Association Computational Linguistics, 1997. Google ScholarDigital Library
- D. C. Fain and J. O. Pedersen. Sponsored search: A brief history. Proceedings of the ACM Conference on Electronic Commerce: Second Workshop on Sponsored Search Auctions, 2006.Google ScholarCross Ref
- D. Hardt. Comma checking in danish. Proceedings of the Corpus Linguistics 2001 Conference, pages 266--271, 2001.Google Scholar
- B. J. Jansen, A. Spink, and T. Saracevic. Real life, real users and real needs: A study and analysis of users' queries on the web. Information Processing and Management, 36(2):207--227, 2000. Google ScholarDigital Library
- D. McFadden. Conditional logit analysis of qualitative choice behavior. In P. Zarembka, editor, Frontiers in Econometrics. Academic Press, New York, 1974.Google Scholar
- J. Oberlander and C. Brew. Stochastic text generation. Philosophical Transactions: Mathematical, Physical and Engineering Science, 358:1373--1387, 2000.Google ScholarCross Ref
- M. Porter. An algorithm for suffix stripping. Program, 14(3):130--137, 1980.Google ScholarCross Ref
- D. R. Radev and K. R. McKeown. Generating natural language summaries from multiple on-line sources. Computational Linguistics, 24(3):470--500, 1998. Google ScholarDigital Library
- C. Reed and D. Long. Generating punctuation in written arguments. Technical Report RN/97/157, Department of Computer Science, University College, London, UK, 1997.Google Scholar
- C. Tillman and H. Ney. Word reordering and a dynamic programming beam search algorithm for statistical machine translation. Computational Linguistics, 29(1):97--133, 2003. Google ScholarDigital Library
- K. Train. Discrete Choice Methods with Simulation. Cambridge University Press, Cambridge, UK, 2003.Google ScholarCross Ref
Index Terms
- Natural language generation for sponsored-search advertisements
Recommendations
Sponsored Search: Is Money a Motivator for Providing Relevant Results?
Analysis of data from a major metasearch engine reveals that sponsored-link click-through rates appear lower than previously reported. Combining sponsored and nonsponsored links in a single listing, while providing some benefits to users, does not ...
The Brand Effect of Key Phrases and Advertisements in Sponsored Search
In this paper, we analyze the relationship between performance and use of brand terms in the key phrases that link advertisements to searcher queries. We use data that consist of more than 2.5 million daily records from a key word advertising campaign ...
Gender demographic targeting in sponsored search
CHI '10: Proceedings of the SIGCHI Conference on Human Factors in Computing SystemsIn this research, we evaluate the effect of gender in analyzing the performance of sponsored search advertising. We examine a log file with data comprised of nearly 7,000,000 records spanning 33 consecutive months of a search engine marketing campaign ...
Comments