PPT-Statistical NLP

Lecture 18 Bayesian grammar induction amp machine translation Roger Levy Department of Linguistics UCSD Thanks to Percy Liang Noah Smith and Dan Klein for slides Plan Recent developments in Bayesian unsupervised grammar induction. John Blitzer. 自然语言计算组. http://research.microsoft.com/asia/group/nlc/. Why should I know about machine learning? . This is an NLP summer school. Why should I care about machine learning?. By Cindy Carless. 14 Nov 14. What a mouthful…. So much in fact that I thought I had bitten off more than I could chew…. Yet for “Tasting” . LetsTest. it seems very appropriate. Some appetisers to focus on. Subproblems. . Meliha. . Yetisgen-Yildiz. From last week’s discussion. Presentation. Schedule. : . http. ://faculty.washington.edu/melihay/. MEBI591C.htm. 50 . minutes . presentation+discussion+question. In the Context of the ETC Project. SAW Intro. Wiki. Users collaboratively develop and organize content. Information Analysis is up to the user. Goal: . “Self-aware wiki that can develop and organize its content. Introduction. Polysemy. Words have multiple senses. Example. Let’s have a drink in the bar. I have to study for the bar. Bring me a chocolate bar. Homonymy. May I come in?. Let’s meet again in May. Who wrote which Federalist papers?. 1787-8: anonymous essays try to convince New York to ratify U.S Constitution: . . Jay, Madison, Hamilton. . Authorship of 12 of the letters in dispute. 1963: solved by . S . -> NP VP. NP -> DT N | NP PP. PP -> PRP NP. VP -> V NP | VP PP. DT -> 'a' | 'the'. N -> 'child' | 'cake' | 'fork'. PRP -> 'with' | 'to'. Parser. Earley. parser. Problems with left recursion in top-down parsing. VP . . VP PP. Background. Developed by Jay Earley in 1970. No need to convert the grammar to CNF. Left to right. Complexity. Semantic Parsing. Converting natural language to a logical form. e.g., executable code for a specific application. Example:. Airline reservations. Geographical query systems. Stages of Semantic . Parsing. Text Similarity. Motivation. People can express the same concept (or related concepts) in many different ways. For example, “the plane leaves at 12pm” vs “the flight departs at noon”. Text similarity is a key component of Natural Language Processing. Biomedical Informatics. UC San Diego. October 13, 2016. Chunnan Hsu. Ramana. . Seerapu. Scott Duvall. Olga Patterson. Hua Xu. Michael Matheny. Glenn . Gobbel. Tsung. -Ting . Kuo. Current members. The NLP working group is tasked to accurately extract phenotypes for three clinical conditions: Kawasaki Disease (KD), Weight Management / Obesity (WM/O), and Congestive Heart Failure (CHF), from tens of millions of clinical notes shared by participating institutes in . Jiho . Han. Ronny (. Dowon. ) . Ko. Objective:. automatically generate the summary of review extracting the strength/weakness of the product. Use NLP techniques to predict ratings. Similar to sentimental analysis. by Hua Xu. Recent Activities. ETL tool development. Note Type Normalization. COVID-19 lab test normalization . A Potential ETL Workflow for NLP. Note. Note_NLP. Measure-. ment. Condition. Procedure. Drug. Elected member: International Statistical Institute. US Chair: International Statistical Literacy Project. 17 July 2014 ICOTS-9. www.StatLit.org/pdf/2014-Schield-ICOTS-Slides.pdf. ODYSSEY: A Journey to .