• Publications
  • Influence
Understanding user goals in web search
TLDR
A framework for understanding the underlying goals of user searches is described and the experience in using the framework to manually classify queries from a web search engine is illustrated.
Crowdsourcing for relevance evaluation
TLDR
A new approach to evaluation called TERC is described, based on the crowdsourcing paradigm, in which many online users, drawn from a large community, each performs a small evaluation task.
Legal information retrieval a hybrid approach
TLDR
SCALIR is a legal information retrieval system which uses a combination of symbolic and connectionist artificial intelligence techniques, especially appropriate for the legal domain, which requires both logical and associative inferences.
Reconciling information-seeking behavior with search user interfaces for the Web
TLDR
Several characteristics of user search behavior are examined: the variety of information-seeking goals, the cultural and situational context of search, and the iterative nature of the search task.
Content awareness in a file system interface: implementing the “pile” metaphor for organizing information
TLDR
A prototype implementation of content awareness capabilities for describing, organizing, and filing textual documents is described, and a detailed example of how they might appear to the user is given.
A Symbolic and Connectionist Approach To Legal Information Retrieval
TLDR
SCALIR develops a conceptual representation of document relationships without explicit knowledge engineering, and suggests a way to resolve the apparent incompatability between the two prominent paradigms in artificial intelligence, the "classical" symbol-manipulation approach and the neurally-inspired connectionist approach.
Summary attributes and perceived search quality
TLDR
A series of experiments in which surveyed web search users answered questions about the quality of search results on the basis of the result summaries found some attributes had no effect on users' quality judgments, while in other cases, changing an attribute had a "halo effect" which caused seemingly unrelated dimensions of result quality to be rated higher by users.
The Information-Seeking Funnel
TLDR
A new conceptual framework for information seeking called the information-seeking funnel is introduced, inspired by a common model of how people are attracted to products they end up buying, to better understand why current search tools are inadequate for several stages of theInformation-seeking process.
V-Twin: A Lightweight Engine for Interactive Use
TLDR
The phenomenon of very short queries generated by users of interactive search services is discussed, and a new technique is used in V-Twin to handle these queries more effectively to achieve a high level of performance.
...
1
2
...