The complexity and readability of text can vary widely. Compare, for example, a research article and a popular media article on the same topic. The articles may discuss the same material, but their usefulness for the reader can vary widely depending on the reader’s background; while the fundamental concepts of the research article may be accessible, the language and structure of the article may prohibit the lay-reader from understanding these concepts.
In this talk, David Kauchak will examine the problem of sentence simplification which aims to develop models to automatically reduce the reading complexity of a sentence.
Interested in working on a project in/with the CS department this summer? If so, join us at this week’s CS colloquium — all are invited:
Where: Galileo Pryne Auditorium
When: Thursday, January 27 at 4:15 pm
What: HMC and Pomona summer CS projects will be described,
along with how to express interest in them.
Not long ago, doing research in most disciplines meant spending long hours in libraries, reading dusty books and monographs. Today, it appears that searching for information has gotten so much easier — in some cases it seems that information is seeking us, not the other way around. The ever-improving search engines have played a significant role in this change, of course. But what makes search engines to evolve? And why does it appear that, sometimes, (when we realize it), they return unreliable results?
This talk will discuss how search engines work and why you should care, especially if you use the Web and the online social networks to be informed in your daily life. We will discuss how computing can learn from society’s long experience with misinformation and, in turn, help us make sense of what we believe as true and why.
Information Retrieval presents models for the retrieval and scoring of documents. While these models work great in idealized cases, they are only a start when applied a real world domain like local search.
This talk will cover the building blocks of a search engine. We will look at how those concepts are applied to Yelp’s local search and some of the difficulties inherent in maintaining user experience while scaling our local search system.