Advances in Word Sense Disambiguation.ppt

《Advances in Word Sense Disambiguation.ppt》由会员分享，可在线阅读，更多相关《Advances in Word Sense Disambiguation.ppt（208页珍藏版）》请在麦多课文档分享上搜索。

1、Advances in Word Sense Disambiguation,Tutorial at AAAI-2005 July 9, 2005Rada Mihalcea University of North Texas http:/www.cs.unt.edu/rada Ted Pedersen University of Minnesota, Duluth http:/www.d.umn.edu/tpederse,Goal of the Tutorial,Introduce the problem of word sense disambiguation (WSD), focusing

2、on the range of formulations and approaches currently practiced. Accessible to anyone with an interest in NLP or AI. Persuade you to work on word sense disambiguation Its an interesting problem Lots of good work already done, still more to do There is infrastructure to help you get started Persuade

3、you to use word sense disambiguation in your text applications.,Outline of Tutorial,Introduction (Ted) Methodolodgy (Rada) Knowledge Intensive Methods (Rada) Supervised Approaches (Ted) Minimally Supervised Approaches (Rada) / BREAK Unsupervised Learning (Ted) How to Get Started (Rada) Conclusion (T

4、ed),Part 1: Introduction,Outline,Definitions Ambiguity for Humans and Computers Very Brief Historical Overview Theoretical Connections Practical Applications,Definitions,Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. Sense Inventory u

5、sually comes from a dictionary or thesaurus. Knowledge intensive methods, supervised learning, and (sometimes) bootstrapping approaches Word sense discrimination is the problem of dividing the usages of a word into different meanings, without regard to any particular existing sense inventory. Unsupe

6、rvised techniques,Outline,Definitions Ambiguity for Humans and Computers Very Brief Historical Overview Theoretical Connections Practical Applications,Computers versus Humans,Polysemy most words have many possible meanings. A computer program has no basis for knowing which one is appropriate, even i

7、f it is obvious to a human Ambiguity is rarely a problem for humans in their day to day communication, except in extreme cases,Ambiguity for Humans - Newspaper Headlines!,DRUNK GETS NINE YEARS IN VIOLIN CASE FARMER BILL DIES IN HOUSE PROSTITUTES APPEAL TO POPE STOLEN PAINTING FOUND BY TREE RED TAPE

8、HOLDS UP NEW BRIDGE DEER KILL 300,000 RESIDENTS CAN DROP OFF TREES INCLUDE CHILDREN WHEN BAKING COOKIES MINERS REFUSE TO WORK AFTER DEATH,Ambiguity for a Computer,The fisherman jumped off the bank and into the water. The bank down the street was robbed! Back in the day, we had an entire bank of comp

9、uters devoted to this problem. The bank in that road is entirely too steep and is really dangerous. The plane took a bank to the left, and then headed off towards the mountains.,Outline,Definitions Ambiguity for Humans and Computers Very Brief Historical Overview Theoretical Connections Practical Ap

10、plications,Early Days of WSD,Noted as problem for Machine Translation (Weaver, 1949) A word can often only be translated if you know the specific sense intended (A bill in English could be a pico or a cuenta in Spanish) Bar-Hillel (1960) posed the following: Little John was looking for his toy box.

11、Finally, he found it. The box was in the pen. John was very happy. Is “pen” a writing instrument or an enclosure where children play?declared it unsolvable, left the field of MT!,Since then,1970s - 1980s Rule based systems Rely on hand crafted knowledge sources 1990s Corpus based approaches Dependen

12、ce on sense tagged text (Ide and Veronis, 1998) overview history from early days to 1998. 2000s Hybrid Systems Minimizing or eliminating use of sense tagged text Taking advantage of the Web,Outline,Definitions Ambiguity for Humans and Computers Very Brief Historical Overview Interdisciplinary Connec

13、tions Practical Applications,Interdisciplinary Connections,Cognitive Science & Psychology Quillian (1968), Collins and Loftus (1975) : spreading activation Hirst (1987) developed marker passing model Linguistics Fodor & Katz (1963) : selectional preferences Resnik (1993) pursued statistically Philos

14、ophy of Language Wittgenstein (1958): meaning as use “For a large class of cases-though not for all-in which we employ the word “meaning“ it can be defined thus: the meaning of a word is its use in the language.”,Outline,Definitions Ambiguity for Humans and Computers Very Brief Historical Overview T

15、heoretical Connections Practical Applications,Practical Applications,Machine Translation Translate “bill” from English to Spanish Is it a “pico” or a “cuenta”? Is it a bird jaw or an invoice? Information Retrieval Find all Web Pages about “cricket” The sport or the insect? Question Answering What is

16、 George Millers position on gun control? The psychologist or US congressman? Knowledge Acquisition Add to KB: Herb Bergson is the mayor of Duluth. Minnesota or Georgia?,References,(Bar-Hillel, 1960) The Present Status of Automatic Translations of Languages. In Advances in Computers. Volume 1. Alt, F

17、. (editor). Academic Press, New York, NY. pp 91-163. (Collins and Loftus, 1975) A Spreading Activation Theory of Semantic Memory. Psychological Review, (82) pp. 407-428. (Fodor and Katz, 1963) The structure of semantic theory. Language (39). pp 170-210. (Hirst, 1987) Semantic Interpretation and the

18、Resolution of Ambiguity. Cambridge University Press. (Ide and Vronis, 1998)Word Sense Disambiguation: The State of the Art Computational Linguistics (24) pp 1-40. (Quillian, 1968) Semantic Memory. In Semantic Information Processing. Minsky, M. (editor). The MIT Press, Cambridge, MA. pp. 227-270. (Re

19、snik, 1993) Selection and Information: A Class-Based Approach to Lexical Relationships. Ph.D. Dissertation. University of Pennsylvania. (Weaver, 1949): Translation. In Machine Translation of Languages: fourteen essays. Locke, W.N. and Booth, A.D. (editors) The MIT Press, Cambridge, Mass. pp. 15-23.

20、(Wittgenstein, 1958) Philosophical Investigations, 3rd edition. Translated by G.E.M. Anscombe. Macmillan Publishing Co., New York.,Part 2: Methodology,Outline,General considerations All-words disambiguation Targeted-words disambiguation Word sense discrimination, sense discovery Evaluation (granular

21、ity, scoring),Ex: “chair” furniture or person Ex: “child” young person or human offspring,Overview of the Problem,Many words have several meanings (homonymy / polysemy)Determine which sense of a word is used in a specific sentenceNote: often, the different senses of a word are closely related Ex: ti

22、tle - right of legal ownership- document that is evidence of the legal ownership, sometimes, several senses can be “activated” in a single context (co-activation) Ex: “This could bring competition to the trade”competition: - the act of competing- the people who are competing,Word Senses,The meaning

23、of a word in a given contextWord sense representations With respect to a dictionarychair = a seat for one person, with a support for the back; “he put his coat over the back of the chair and sat down“chair = the position of professor; “he was awarded an endowed chair in economics“ With respect to th

24、e translation in a second languagechair = chaisechair = directeur With respect to the context where it occurs (discrimination)“Sit on a chair” “Take a seat on this chair”“The chair of the Math Department” “The chair of the meeting”,Approaches to Word Sense Disambiguation,Knowledge-Based Disambiguati

25、on use of external lexical resources such as dictionaries and thesauri discourse properties Supervised Disambiguation based on a labeled training set the learning system has: a training set of feature-encoded inputs AND their appropriate sense label (category) Unsupervised Disambiguation based on un

26、labeled corpora The learning system has: a training set of feature-encoded inputs BUT NOT their appropriate sense label (category),All Words Word Sense Disambiguation,Attempt to disambiguate all open-class words in a text“He put his suit over the back of the chair”Knowledge-based approaches Use info

27、rmation from dictionaries Definitions / Examples for each meaning Find similarity between definitions and current context Position in a semantic network Find that “table” is closer to “chair/furniture” than to “chair/person” Use discourse properties A word exhibits the same sense in a discourse / in

28、 a collocation,All Words Word Sense Disambiguation,Minimally supervised approaches Learn to disambiguate words using small annotated corpora E.g. SemCor corpus where all open class words are disambiguated 200,000 running words Most frequent sense,Targeted Word Sense Disambiguation,Disambiguate one t

29、arget word “Take a seat on this chair” “The chair of the Math Department”WSD is viewed as a typical classification problem use machine learning techniques to train a system Training: Corpus of occurrences of the target word, each occurrence annotated with appropriate sense Build feature vectors: a v

30、ector of relevant linguistic features that represents the context (ex: a window of words around the target word) Disambiguation: Disambiguate the target word in new unseen text,Targeted Word Sense Disambiguation,Take a window of n word around the target word Encode information about the words around

31、 the target word typical features include: words, root forms, POS tags, frequency, An electric guitar and bass player stand off to one side, not really part of the scene, just as a sort of nod to gringo expectations perhaps.Surrounding context (local features) (guitar, NN1), (and, CJC), (player, NN1

32、), (stand, VVB) Frequent co-occurring words (topical features) fishing, big, sound, player, fly, rod, pound, double, runs, playing, guitar, band 0,0,0,1,0,0,0,0,0,0,1,0Other features: followed by “player“, contains “show“ in the sentence, yes, no, ,Unsupervised Disambiguation,Disambiguate word sense

33、s: without supporting tools such as dictionaries and thesauri without a labeled training text Without such resources, word senses are not labeled We cannot say “chair/furniture” or “chair/person” We can: Cluster/group the contexts of an ambiguous word into a number of groups Discriminate between the

34、se groups without actually labeling them,Unsupervised Disambiguation,Hypothesis: same senses of words will have similar neighboring words Disambiguation algorithm Identify context vectors corresponding to all occurrences of a particular word Partition them into regions of high density Assign a sense

35、 to each such region“Sit on a chair” “Take a seat on this chair” “The chair of the Math Department” “The chair of the meeting”,Evaluating Word Sense Disambiguation,Metrics: Precision = percentage of words that are tagged correctly, out of the words addressed by the system Recall = percentage of word

36、s that are tagged correctly, out of all words in the test set Example Test set of 100 words Precision = 50 / 75 = 0.66 System attempts 75 words Recall = 50 / 100 = 0.50 Words correctly disambiguated 50Special tags are possible: Unknown Proper noun Multiple senses Compare to a gold standard SEMCOR co

37、rpus, SENSEVAL corpus, ,Evaluating Word Sense Disambiguation,Difficulty in evaluation: Nature of the senses to distinguish has a huge impact on results Coarse versus fine-grained sense distinction chair = a seat for one person, with a support for the back; “he put his coat over the back of the chair

38、 and sat down“ chair = the position of professor; “he was awarded an endowed chair in economics“bank = a financial institution that accepts deposits and channels the money into lending activities; “he cashed a check at the bank“; “that bank holds the mortgage on my home“ bank = a building in which c

39、ommercial banking is transacted; “the bank is on the corner of Nassau and Witherspoon“ Sense maps Cluster similar senses Allow for both fine-grained and coarse-grained evaluation,Bounds on Performance,Upper and Lower Bounds on Performance: Measure of how well an algorithm performs relative to the di

40、fficulty of the task.Upper Bound: Human performance Around 97%-99% with few and clearly distinct senses Inter-judge agreement: With words with clear & distinct senses 95% and up With polysemous words with related senses 65% 70% Lower Bound (or baseline): The assignment of a random sense / the most f

41、requent sense 90% is excellent for a word with 2 equiprobable senses 90% is trivial for a word with 2 senses with probability ratios of 9 to 1,References,(Gale, Church and Yarowsky 1992) Gale, W., Church, K., and Yarowsky, D. Estimating upper and lower bounds on the performance of word-sense disambi

42、guation programs ACL 1992. (Miller et. al., 1994) Miller, G., Chodorow, M., Landes, S., Leacock, C., and Thomas, R. Using a semantic concordance for sense identification. ARPA Workshop 1994. (Miller, 1995) Miller, G. Wordnet: A lexical database. ACM, 38(11) 1995. (Senseval) Senseval evaluation exerc

43、ises http:/www.senseval.org,Part 3: Knowledge-based Methods for Word Sense Disambiguation,Outline,Task definition Machine Readable Dictionaries Algorithms based on Machine Readable Dictionaries Selectional Restrictions Measures of Semantic Similarity Heuristic-based Methods,Task Definition,Knowledge

44、-based WSD = class of WSD methods relying (mainly) on knowledge drawn from dictionaries and/or raw text Resources Yes Machine Readable Dictionaries Raw corpora No Manually annotated corpora Scope All open-class words,Machine Readable Dictionaries,In recent years, most dictionaries made available in

45、Machine Readable format (MRD) Oxford English Dictionary Collins Longman Dictionary of Ordinary Contemporary English (LDOCE) Thesauruses add synonymy information Roget Thesaurus Semantic networks add more semantic relations WordNet EuroWordNet,MRD A Resource for Knowledge-based WSD,For each word in t

46、he language vocabulary, an MRD provides: A list of meanings Definitions (for all word meanings) Typical usage examples (for most word meanings),MRD A Resource for Knowledge-based WSD,A thesaurus adds: An explicit synonymy relation between word meaningsA semantic network adds: Hypernymy/hyponymy (IS-

47、A), meronymy/holonymy (PART-OF), antonymy, entailnment, etc.,WordNet synsets for the noun “plant” 1. plant, works, industrial plant2. plant, flora, plant life,WordNet related concepts for the meaning “plant life” plant, flora, plant life hypernym: organism, beinghypomym: house plant, fungus, meronym

48、: plant tissue, plant partholonym: Plantae, kingdom Plantae, plant kingdom,Outline,Task definition Machine Readable Dictionaries Algorithms based on Machine Readable Dictionaries Selectional Restrictions Measures of Semantic Similarity Heuristic-based Methods,Lesk Algorithm,(Michael Lesk 1986): Iden

49、tify senses of words in context using definition overlap Algorithm: Retrieve from MRD all sense definitions of the words to be disambiguated Determine the definition overlap for all possible sense combinations Choose senses that lead to highest overlap,Example: disambiguate PINE CONEPINE 1. kinds of evergreen tree with needle-shaped leaves 2. waste away through sorrow or illnessCONE 1. solid body which narrows to a point 2. something of this shape whether solid or hollow 3. fruit of certain evergreen trees,