Emre, Onur, and I presented our short paper on distilling the outcomes Ben carterette thesis personal experiences from social media timelines.
Within IR, my main focus has been on aggregated search—the task of providing users with integrated access to multiple search services within a single system. Grateful to Fernando Diaz and Shane Culpepper for organizing it and for inviting me!
If you want to check out the updated slide decks, you can find them here. You can check out the static version of my slides here.
For some of my take-aways check out my tweets: May I was a panelist on the " Humanitarian Technology and Innovation: Also, within the eRuleMaking ProjectI worked on semi-supervised methods for identifying stakeholder communities and recognizing evidence-citation in public comment corpora emails sent by the public to a government agency that is proposing new regulation.
Ben carterette thesis the videos here and plan to submit for the next year. Pre-print of camera ready version is now available. This was a short version of our tutorial at The Web Conference. My methods address the task of deciding when and how to surface vertical content in response to a Web search query.
Great audience, great questions, and a beautiful building: Prior to working on aggregated search, I conducted research in various areas Ben carterette thesis information retrieval. In particular, my thesis is on aggregated search within the context of Web search, which is a task familiar to many.
You can check our short paper here. In addition to retrieving Web content, commercial search engines also function as a single point of access to specialized services known as verticals e. Biases, Methodological Pitfalls, and Ethical Boundaries ".
I expect to graduate in the early summer of Watson Research Center, NY. The static version of my slides is here. Our slides and other materials can be found on the tutorial webpage. In addition to IR, I am also interested in machine learning, human-computer interaction, and text data-mining. ChaTo, Emre, Fernando, and I offered a tutorial on limits of social data.
I am from Tegucigalpa, Honduras: National Institute of Standards and Technology, special publication. We were also happy to present an updated version of our Social Data limits tutorial. My focus was on topic-segmentation of transcribed dialogue and on developing visualizations and interactions for organizing dialogue-segments into thematic clusters.
Quite impressed with all the teams and the organization. The Case of Hate Speech Detection" check the extended abstract here. Gave an invited talk on "Challenges, Problem Selection, and Impact:Document Features Predicting Assessor Disagreement, Praveen Chandar, William Webber, and Ben Carterette, Proc.
ACM-SIGIR, Dublin, Ireland, Julypages (published version). Assessor Disagreement and Text Classifier Accuracy, William Webber and Jeremy Pickens, Proc.
ACM-SIGIR, Dublin, Ireland, Julypages. Thesis advisor Author Javed Aslam Stefan Savev Collection Construction Methodologies for Learning to Rank Abstract Ranking documents in response to user queries is one of the fundamental problems Sundaram, Mirek Riedewald and Ben Carterette for serving on my committee.
North American Chapter of the Association for Computational Linguistics: Human Language Technologies Of the accepted papers, seven were research papers and v e were thesis proposals. Each Ben Carterette, University of Delaware.
This thesis addresses a limitation of the fundamental retrieval models, the term mismatch problem, which happens when query terms fail to appear in the documents that are relevant to the query.
The term mismatch problem is a long standing problem in information retrieval. Alexandra Olteanu, Carlos Castillo, Nicholas Diakopoulos, and Karl Aberer.
In Proceedings of 9th International AAAI Conference on Web and Social Media, Oxford, UK, May [CSCW'15] What to Expect When the Unexpected Happens: Social Media Communications Across Crises.
Alexandra Olteanu, Sarah Vieweg, and Carlos Castillo. SIGIR Tutorial: "Advances on the Development of Evaluation Measures", with Ben Carterette and Emine Yilmaz.
SIGIR Tutorial: "Low-Cost Evaluation in IR", with Ben Carterette and Emine Yilmaz. RuSSIR/EDBT Summer School Course: Advances in Information Retrieval Evaluation, with Ben Carterette and Emine Yilmaz.Download