PPT-Word Meaning and Similarity

Word Senses and Word Relations Reminder lemma and wordform A lemma or citation form Same stem part of speech rough semantics A wordfor m The inflected word as it appears in text. energies. D.A. . Artemenkov. , G.I. . . Lykasov. , . A.I. . . Malakhov. Joint Institute for Nuclear Research. malakhov@lhe.jinr.ru. Hadron Structure 2015, June 29 – July 3, 2015, . Horn. ý. . . Corpora and Statistical Methods. Lecture 6. Semantic similarity. Part 1. Synonymy. Different phonological. /orthographic. words. highly related meanings. :. sofa / couch. boy / lad. Traditional definition:. -. based Clustering. Mohammad. . Rezaei. , Pasi Fränti. rezaei@cs.uef.fi. Speech. and . Image. . Processing. . Unit. University of Eastern Finland. . August 2014. Keyword-Based Clustering. An object such as a text document, website, movie and service can be described by a set of keywords. CMPS 561-FALL 2014. SUMI SINGH. SXS5729. Protein Structure . 2. RPDFCLEPPYAGACRARIIRYFYNAKAGLCQ. Primary Structure. Sequence of Amino Acids. . Not . enough for functional prediction.. Tertiary Structure. Jing . Zhang, . Jie. . Tang . , Cong . Ma . , . Hanghang. . Tong . , Yu . Jing . , and . Juanzi. . Li. Presented by Moumita Chanda Das . Outline. Introduction. Problem formulation. Panther using path sampling. Story . #6 . – . My . Abuelita. wistful . wist-ful. . grateful grate-. ful. . grim gr-. im. raspy . ras-py. swarmed . swar. -med. revelers rev-el-. ers. irresistible . ir. -re-. sist. Story . #17. Nothing Happens on the Farm. hiatus . hi-a-. tus. embarked . em. -bar-ked. unimaginable . un-. im. -ag-in-able. extravagant . ex-. trav. -a-. gant. gourmet . gour. -met. throng . thr-ong. Dan Jurafsky. Stanford University. Introduction and Course Overview. What is Computational Lexical Semantics. Any computational process involving word meaning!. Computing . Word Similarity . Distributional (Vector) Models of . Warm Up. Solve each proportion.. 1.. . . 2.. . 3.. 4. . If . ∆. QRS . ~ . ∆. XYZ. , identify the pairs of congruent angles and write 3 proportions using pairs of corresponding sides.. . computing the similarity between words. “. fast. ” is similar to “. rapid. ”. “. tall. ” is similar to “. height. ”. Question answering:. Q. : “. How . tall. . is Mt. Everest?”. Candidate A: “The . Presenter. : Monica Farkash. Bryan Hickerson. . mfarkash@us.ibm.com. . bhickers@us.ibm.com. . 2. Outline. The challenge: Providing a subset from a regression test suite. Our new Jaccard/K-means (JK) approach . Quiz. Which pair of words exhibits the greatest similarity?. 1. Deer-elk. 2. Deer-horse. 3. Deer-mouse. 4. Deer-roof. Quiz Answer. Which pair of words exhibits the greatest similarity?. 1. Deer-elk. 2. Deer-horse. Jessica Chackoria. 1. , Brooke Nyberg. 1. , Melissa Vazquez. 1 . Suzanne Bell. 2. , . Alla. Vinokhodova. 3. , Vadim Gushin. 3. , Leslie DeChurch. 4 . , Noshir Contractor. 4 . 1. DePaul University, . Sketching, Locality Sensitive Hashing. SIMILARITY AND DISTANCE. Thanks to:. Tan, Steinbach, . and Kumar, “Introduction to Data Mining”. Rajaraman. . and . Ullman, “Mining Massive Datasets”. Similarity and Distance.