PPT-Non-Monotonic Parsing of

Fluent Umm I mean Disfluent Sentences Mohammad Sadegh Rasooli Columbia University Joel Tetreault Yahoo Labs This work conducted while both authors were at Nuances NLU Research Lab in Sunnyvale CA. Ling 571. Deep Processing Techniques for NLP. January 12, 2011. Roadmap . Motivation: . Parsing (In) efficiency. Dynamic Programming. Cocke. -. Kasami. -Younger Parsing Algorithm . Chomsky Normal Form. CS 4705. Julia Hirschberg. 1. Some slides adapted from Kathy McKeown and Dan Jurafsky. Syntactic Parsing. Declarative . formalisms like CFGs, FSAs define the . legal strings of a language. -- but only tell you whether a given string is legal in a particular language. Lana Lazebnik. UNC Chapel Hill. sky. sidewalk. building. road. car. person. car. mountain. The past: . “closed universe. ” datasets. Tens of classes, hundreds of images, offline learning. He et al. (2004), . In-domain vs out-domain. Annotated data in. Domain A. A. Parser. Training. Parsing texts in . Domain A. Parsing texts in Domain B . In-domain. Out-domain. Motivation. F. ew or no labeled resources exist for parsing text of the target domain.. Trifecta. Edward . Kmett. Iteratees. , Parsec, and . Monoids. Overview. The Problem. Deriving . Iteratees. á la Oleg. Buffered . Iteratees. Layering Parsec Over . Iteratees. Local Context-Sensitivity. Semi-supervised . dependency parsing. Supervised parsing . Training: Labeled data. Semi-supervised parsing. Training: Additional unlabeled data + labeled data. Unlabeled data. Labeled data. Semi-supervised Parsing. Bottom-up parsing. Bottom-up parsing builds a parse tree from the leaves (terminals) to the start symbol. int. E. int. T. *. T. E. +. T. int. (4). (2). (3). (5). (1). int. *. +. int. E . . T + E | T. Prof. O. . Nierstrasz. Thanks to Jens Palsberg and Tony Hosking for their kind permission to reuse and adapt the CS132 and CS502 lecture notes.. http://www.cs.ucla.edu/~palsberg/. http://www.cs.purdue.edu/homes/hosking/. David Kauchak. CS159 – Spring 2011. some slides adapted from Ray Mooney. Admin. Updated slides/examples on . backoff. with absolute discounting (I’ll review them again here today). Assignment 2. Excel can not only be used to process numbers, but also text.. This often . involves taking apart . (parsing) or . putting together text values (strings).. The parts into . which . we split a string will be called . Not all noun phrases (NPs) are (by nature) directly referential like names. Quantifiers. : . “. something to do with indicating the quantity of something. ”. Examples. :. every. child. nobody. two. Niranjan Balasubramanian. March 24. th. 2016. Credits: . Many slides from:. Michael Collins, . Mausam. , Chris Manning, . COLNG 2014 Dependency Parsing Tutorial, . Ryan McDonald, . . Joakim. . Nivre. 1. Some slides . adapted from Julia Hirschberg and Dan . Jurafsky. To view past videos:. http://. globe.cvn.columbia.edu:8080/oncampus.php?c=133ae14752e27fde909fdbd64c06b337. Usually available only for 1 week. Right now, available for all previous lectures. . &. Population-Monotonicity. In Cake-Cutting. Erel. Segal-. haLevi. Bar-. Ilan. . Univesity. , Israel. Joint . work with:. Balázs. . Sziklai. , . Hungarian . Academy of . Sciences, Hungary.