Sanda harabagiu delivers the last grace series talk. Topic themes for multidocument summarization proceedings of the. This is a milestone because watson will compete directly against humans, and moreover against the champions of jeopardy. Journal of the american medical informatics association. Harabagiu is an expert in natural language processing, artificial intelligence, and information retrieval. Harabagiu and finley lacatusu using topic themes for multidocument summarization acm transactions on information systems, vol 28, no 3, article, june 2010 2010 publication s. Automatic discovery and processing of eeg cohorts from clinical records collaboration with temple university electronic medical records emr collected at every hospital across the country collectively contain a staggering wealth and breadth of biomedical knowledge. My research interests include natural language processing, information retrieval, knowledge processing, artificial intelligence and more recently medical informatics. Like the course, the various solutions will be divided into the following topics.
Sanda harabagiu, a leader in the field of humancomputer interaction for more than a decade. My research interests include natural language processing, information retrieval, knowledge processing, artificial intelligence and more recently medical. Sanda harabagiu, professor of computer science and research initiation chair in the erik jonsson school of engineering and computer science, received the homer r. Solutions of the various test exams of the information retrieval course unipi master informationretrieval exercises 161 commits 1 branch 0 packages 7 releases fetching contributors tex other. Medical question answering and patient cohort retrieval. Sanda harabagiu from university of texas at dallas presents a. A generative model for unsupervised discovery of relations and argument classes from clinical texts in the proceedings of the 2011 conference on empirical methods in natural language processing emnlp 2011, pages 519528, july 2011, edinburgh, scotland, uk. Travis goodwin bs11, ms, a computer science phd student at ut dallas, and dr. Citeseerx document details isaac councill, lee giles, pradeep teregowda.
This is important, and its a more realistic gauge than simply comparing a system to search engines. Sanda harabagiu professor and research initiation chair research interests. Bouadjenek m and sanner s relevancedriven clustering for visual information retrieval on twitter proceedings of the 2019 conference on human information interaction and retrieval, 349353 hu s, xiao c, qin j, ishikawa y and ma q autocompletion for prefixabbreviated input proceedings of the 2019 international conference on management of data. Harabagiu, sanda ut dallas department of computer science. We argue that combinations of information retrieval and extractions techniques cannot be used, due to the opendomain nature of the task. Harabagiu combines knowledge extracted from the world wide web with knowledge coerced from large lexical. The impact of belief values on the identification of patient cohorts travis goodwin and sanda harabagiu. The technology, which utilizes sophisticated software tools, has the potential to help security personnel simultaneously screen and analyze millions of voice and text communications in an attempt to uncover terrorist or other criminal activities. Language processing, information retrieval, knowledge processing.
Advances in open domain question answering semantic scholar. Qa is an information retrieval ir paradigm that re. Answering complex questions with random walk models. She currently researches how human communication works in a textual form across different genres and domains, with a special interest in the medical domain. Austin, where i was a faculty member in the department of computer sciences.
The impact of inferring treatments on information retrieval for precision medicine. Meet shah the university of texas at dallas dallas, texas. Harabagiu, sanda, lacatusu, finley, hickl, andrew 2006. Proceedings of the 29th annual international acm sigir conference on research and development in information retrieval, 2006. Zhang l and meng n how does execution information help with informationretrieval based bug localization. Lacatusu, satisfying information needs with multidocument summaries, information processes and management, 43 2007, pages 16191642.
1224 1478 1408 1010 1072 399 770 947 337 340 1235 910 497 1095 294 1577 461 1584 250 362 1448 1491 404 1501 1444 135 638 937 306 1079 1075 1386 534 861 867 199 806