Word Sense Disambiguation

Transcription

1 Word Sense Disambiguation D. De Cao R. Basili Corso di Web Mining e Retrieval a.a May 21, 2009 Excerpt of the R. Mihalcea and T. Pedersen AAAI 2005 Tutorial, at: tpederse/tutorials/advances-in-wsd-aaai-2005.ppt

2 Definitions Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities.

3 Definitions Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. Sense Inventory usually comes from a dictionary or thesaurus. Knowledge intensive methods, supervised learning, and (sometimes) bootstrapping approaches.

4 Definitions Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. Sense Inventory usually 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.

5 Definitions Word sense disambiguation is the problem of selecting a sense for a word from a set of predefined possibilities. Sense Inventory usually 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. Unsupervised techniques.

6 Computers versus Humans Polysemy: most words have many possible meanings.

7 Computers versus Humans Polysemy: most words have many possible meanings. A computer program has no basis for knowing which one is appropriate, even if it is obvious to a human...

8 Computers versus Humans Polysemy: most words have many possible meanings. A computer program has no basis for knowing which one is appropriate, even if it is obvious to a human... Ambiguity is rarely a problem for humans in their day to day communication, except in extreme cases...

9 Computers versus Humans Polysemy: most words have many possible meanings. A computer program has no basis for knowing which one is appropriate, even if it is obvious to a human... Ambiguity is rarely a problem for humans in their day to day communication, except in extreme cases... Example: The fisherman jumped off the bank and into the water. The bank down the street was robbed!

10 Brief Historical Overview 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. 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!

11 Brief Historical Overview 1970s s Rule based systems Rely on hand crafted knowledge sources 1990s Corpus based approaches Dependence on sense tagged text (Ide and Veronis, 1998) overview history from early days to s Hybrid Systems Minimizing or eliminating use of sense tagged text Taking advantage of the Web

12 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?

13 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?

14 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 George Miller s position on gun control? The psychologist or US congressman?

15 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 George Miller s position on gun control? The psychologist or US congressman? Knowledge Acquisition Add to KB: Herb Bergson is the mayor of Duluth. Minnesota or Georgia?

16 Overview of the Problem Many words have several meanings (homonymy / polysemy) Ex: chair - furniture or person Ex: child - young person or human offspring

17 Overview of the Problem Many words have several meanings (homonymy / polysemy) Ex: chair - furniture or person Ex: child - young person or human offspring Determine which sense of a word is used in a specific sentence

18 Overview of the Problem Many words have several meanings (homonymy / polysemy) Ex: chair - furniture or person Ex: child - young person or human offspring Determine which sense of a word is used in a specific sentence Note: often, the different senses of a word are closely related Ex: title : right of legal ownership document that is evidence of the legal ownership

19 Overview of the Problem Many words have several meanings (homonymy / polysemy) Ex: chair - furniture or person Ex: child - young person or human offspring Determine which sense of a word is used in a specific sentence Note: often, the different senses of a word are closely related Ex: title : 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: the act of competing the people who are competing

20 Word Senses The meaning of a word in a given context

21 Word Senses The meaning of a word in a given context Word sense representations With respect to a dictionary chair = 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

22 Word Senses The meaning of a word in a given context Word sense representations With respect to a dictionary chair = 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 the translation in a second language chair = chaise chair = directeur

23 Word Senses The meaning of a word in a given context Word sense representations With respect to a dictionary chair = 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 the translation in a second language chair = chaise chair = 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

24 Approaches to Word Sense Disambiguation Knowledge-Based Disambiguation use of external lexical resources such as dictionaries and thesauri discourse properties

25 Approaches to Word Sense Disambiguation Knowledge-Based Disambiguation 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)

26 Approaches to Word Sense Disambiguation Knowledge-Based Disambiguation 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 unlabeled corpora The learning system has: a training set of feature-encoded inputs BUT NOT their appropriate sense label (category)

27 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

28 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

29 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 information from dictionaries Definitions / Examples for each meaning Find similarity between definitions and current context

30 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 information 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

31 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 information 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 a collocation

32 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

33 Targeted Word Sense Disambiguation Disambiguate one target word Take a seat on this chair The chair of the Math Department

34 Targeted Word Sense Disambiguation Disambiguate one target 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

35 Targeted Word Sense Disambiguation Disambiguate one target 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 vector of relevant linguistic features that represents the context (ex: a window of words around the target word)

36 Targeted Word Sense Disambiguation Disambiguate one target 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 vector 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

37 Targeted Word Sense Disambiguation Take a window of n word around the target word

38 Targeted Word Sense Disambiguation Take a window of n word around the target word Encode information about the words around the target word

39 Targeted Word Sense Disambiguation Take a window of n word around the target word Encode information about the words around the target word typical features include: words, root forms, POS tags, frequency,...

40 Targeted Word Sense Disambiguation Take a window of n word around the target word Encode information about the words around 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.

41 Targeted Word Sense Disambiguation Take a window of n word around the target word Encode information about the words around 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), (stand, VVB) ]

42 Targeted Word Sense Disambiguation Take a window of n word around the target word Encode information about the words around 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), (stand, VVB) ] Frequent co-occurring words (topical features) [fishing, big, sound, player, fly, rod, pound, double, runs, playing, guitar, band] [0,0,0,1,0,0,0,0,0,0,1,0]

43 Targeted Word Sense Disambiguation Take a window of n word around the target word Encode information about the words around 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), (stand, VVB) ] Frequent co-occurring words (topical features) [fishing, big, sound, player, fly, rod, pound, double, runs, playing, guitar, band] [0,0,0,1,0,0,0,0,0,0,1,0] Other features: [followed by player, contains show in the sentence,... ] [yes, no,... ]

44 Unsupervised Disambiguation Disambiguate word senses: without supporting tools such as dictionaries and thesauri without a labeled training text

45 Unsupervised Disambiguation Disambiguate word senses: 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

46 Unsupervised Disambiguation Disambiguate word senses: 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 these groups without actually labeling them

47 Unsupervised Disambiguation Hypothesis: same senses of words will have similar neighboring words

48 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 to each such region

49 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 to each such region Sit on a chair Take a seat on this chair

50 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 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

51 Evaluating Word Sense Disambiguation Metrics: Precision = percentage of words that are tagged correctly, out of the words addressed by the system Recall = percentage of words that are tagged correctly, out of all words in the test set Special tags are possible: Unknown Proper noun Multiple senses Compare to a gold standard SEMCOR corpus, SENSEVAL corpus,...

52 Evaluating Word Sense Disambiguation Difficulty in evaluation: Nature of the senses to distinguish has a huge impact on results

53 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

54 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 and sat down chair = the position of professor; he was awarded an endowed chair in economics

55 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 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 commercial banking is transacted; the bank is on the corner of Nassau and Witherspoon

56 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 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 commercial 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

57 Knowledge-based Methods for Word Sense Disambiguation Knowledge-based WSD = class of WSD methods relying (mainly) on knowledge drawn from dictionaries and/or raw text

58 Knowledge-based Methods for Word Sense Disambiguation Knowledge-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

59 Knowledge-based Methods for Word Sense Disambiguation Knowledge-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

60 Machine Readable Dictionaries In recent years, most dictionaries made available in Machine Readable format (MRD) Oxford English Dictionary Collins Longman Dictionary of Ordinary Contemporary English (LDOCE)

61 Machine Readable Dictionaries In recent years, most dictionaries made available in Machine Readable format (MRD) Oxford English Dictionary Collins Longman Dictionary of Ordinary Contemporary English (LDOCE) Thesauruses - add synonymy information Roget Thesaurus

62 Machine Readable Dictionaries In recent years, most dictionaries made available in 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

63 MRD - A Resource for Knowledge-based WSD For each word in the language vocabulary, an MRD provides: A list of meanings Definitions (for all word meanings) Typical usage examples (for most word meanings)

64 MRD - A Resource for Knowledge-based WSD For each word in the language vocabulary, an MRD provides: A list of meanings Definitions (for all word meanings) Typical usage examples (for most word meanings) WordNet definitions/examples for the noun plant 1 buildings for carrying on industrial labor; they built a large plant to manufacture automobiles 2 a living organism lacking the power of locomotion 3 something planted secretly for discovery by another; the police used a plant to trick the thieves ; he claimed that the evidence against him was a plant 4 an actor situated in the audience whose acting is rehearsed but seems spontaneous to the audience

65 MRD - A Resource for Knowledge-based WSD A thesaurus adds: An explicit synonymy relation between word meanings

66 MRD - A Resource for Knowledge-based WSD A thesaurus adds: An explicit synonymy relation between word meanings WordNet synsets for the noun plant 1 plant, works, industrial plant 2 plant, flora, plant life

67 MRD - A Resource for Knowledge-based WSD A thesaurus adds: An explicit synonymy relation between word meanings WordNet synsets for the noun plant 1 plant, works, industrial plant 2 plant, flora, plant life A semantic network adds: Hypernymy/hyponymy (IS-A), meronymy/holonymy (PART-OF), antonymy, entailnment, etc.

68 MRD - A Resource for Knowledge-based WSD A thesaurus adds: An explicit synonymy relation between word meanings WordNet synsets for the noun plant 1 plant, works, industrial plant 2 plant, flora, plant life A semantic network adds: Hypernymy/hyponymy (IS-A), meronymy/holonymy (PART-OF), antonymy, entailnment, etc. WordNet related concepts for the meaning plant life - {plant, flora, plant life} hypernym: {organism, being} hypomym: {house plant}, {fungus},... meronym: {plant tissue}, {plant part} holonym: {Plantae, kingdom Plantae, plant kingdom}

69 Lesk Algorithm (Michael Lesk 1986): Identify senses of words in context using definition overlap Algorithm: 1 Retrieve from MRD all sense definitions of the words to be disambiguated 2 Determine the definition overlap for all possible sense combinations 3 Choose senses that lead to highest overlap

70 Lesk Algorithm: Example disambiguate PINE CONE PINE 1 kinds of evergreen tree with needle-shaped leaves 2 waste away through sorrow or illness CONE 1 solid body which narrows to a point 2 something of this shape whether solid or hollow 3 fruit of certain evergreen trees

71 Lesk Algorithm: Example disambiguate PINE CONE PINE 1 kinds of evergreen tree with needle-shaped leaves 2 waste away through sorrow or illness CONE 1 solid body which narrows to a point 2 something of this shape whether solid or hollow 3 fruit of certain evergreen trees Pine#1 Cone#1 = 0 Pine#2 Cone#1 = 0 Pine#1 Cone#2 = 1 Pine#2 Cone#2 = 0 Pine#1 Cone#3 = 2 Pine#2 Cone#4 = 0

72 Lesk Algorithm for More than Two Words? I saw a man who is 98 years old and can still walk and tell jokes

73 Lesk Algorithm for More than Two Words? I saw a man who is 98 years old and can still walk and tell jokes nine open class words: see(26), man(11), year(4), old(8), can(5), still(4), walk(10), tell(8), joke(3)

74 Lesk Algorithm for More than Two Words? I saw a man who is 98 years old and can still walk and tell jokes nine open class words: see(26), man(11), year(4), old(8), can(5), still(4), walk(10), tell(8), joke(3) 43,929,600 sense combinations! How to find the optimal sense combination?

75 Lesk Algorithm for More than Two Words? I saw a man who is 98 years old and can still walk and tell jokes nine open class words: see(26), man(11), year(4), old(8), can(5), still(4), walk(10), tell(8), joke(3) 43,929,600 sense combinations! How to find the optimal sense combination? Simulated annealing (Cowie, Guthrie, Guthrie 1992) Define a function E = combination of word senses in a given text. Find the combination of senses that leads to highest definition overlap (redundancy)

76 Lesk Algorithm for More than Two Words? I saw a man who is 98 years old and can still walk and tell jokes nine open class words: see(26), man(11), year(4), old(8), can(5), still(4), walk(10), tell(8), joke(3) 43,929,600 sense combinations! How to find the optimal sense combination? Simulated annealing (Cowie, Guthrie, Guthrie 1992) Define a function E = combination of word senses in a given text. Find the combination of senses that leads to highest definition overlap (redundancy) 1 Start with E = the most frequent sense for each word 2 At each iteration, replace the sense of a random word in the set with a different sense, and measure E 3 Stop iterating when there is no change in the configuration of senses

77 Lesk Algorithm: A Simplified Version Original Lesk definition: measure overlap between sense definitions for all words in context. Identify simultaneously the correct senses for all words in context

78 Lesk Algorithm: A Simplified Version Original Lesk definition: measure overlap between sense definitions for all words in context. Identify simultaneously the correct senses for all words in context Simplified Lesk (Kilgarriff & Rosensweig 2000): measure overlap between sense definitions of a word and current context Identify the correct sense for one word at a time Search space significantly reduced Algorithm for simplified Lesk: 1 Retrieve from MRD all sense definitions of the word to be disambiguated 2 Determine the overlap between each sense definition and the current context 3 Choose the sense that leads to highest overlap

79 Example of simplified Lesk disambiguate PINE in Pine cones hanging in a tree PINE 1 kinds of evergreen tree with needle-shaped leaves 2 waste away through sorrow or illness

80 Example of simplified Lesk disambiguate PINE in Pine cones hanging in a tree PINE 1 kinds of evergreen tree with needle-shaped leaves 2 waste away through sorrow or illness Pine#1 Sentence = 1 Pine#2 Sentence = 0

81 Evaluations of Lesk Algorithm Initial evaluation by M. Lesk 50-70% on short samples of text manually annotated set, with respect to Oxford Advanced Learner s Dictionary Simulated annealing 47% on 50 manually annotated sentences Evaluation on Senseval-2 all-words data, with back-off to random sense (Mihalcea & Tarau 2004) Original Lesk: 35% Simplified Lesk: 47% Evaluation on Senseval-2 all-words data, with back-off to most frequent sense (Vasilescu, Langlais, Lapalme 2004) Original Lesk: 42% Simplified Lesk: 58%

82 Semantic Similarity Words in a discourse must be related in meaning, for the discourse to be coherent (Haliday and Hassan, 1976) Use this property for WSD - Identify related meanings for words that share a common context

83 Semantic Similarity Words in a discourse must be related in meaning, for the discourse to be coherent (Haliday and Hassan, 1976) Use this property for WSD - Identify related meanings for words that share a common context Context span: 1 Local context: semantic similarity between pairs of words 2 Global context: lexical chains

84 Semantic Similarity in a Local Context Similarity determined between pairs of concepts, or between a word and its surrounding context Relies on similarity metrics on semantic networks (Rada et al. 1989)

85

86

87

88 Decision List for WSD (Yarowsky, 1994) Identify collocational features from sense tagged data. Word immediately to the left or right of target : I have my bank/1 statement. The river bank/2 is muddy. Pair of words to immediate left or right of target : The world s richest bank/1 is here in New York. The river bank/2 is muddy. Words found within k positions to left or right of target, where k is often : My credit is just horrible because my bank/1 has made several mistakes with my account and the balance is very low.

89 Decision List for WSD (Yarowsky, 1994) Sort order of collocation tests using log of conditional probabilities. Words most indicative of one sense (and not the other) will be ranked highly.

90 Decision List for WSD (Yarowsky, 1994) Sort order of collocation tests using log of conditional probabilities. Words most indicative of one sense (and not the other) will be ranked highly. ( Abs log p(s = 1 F ) i = Collocation i ) p(s = 2 F i = Collocation i )

91 Decision List for WSD (Yarowsky, 1994)

92 Decision List for WSD (Yarowsky, 1994)

93 Decision List for WSD (Yarowsky, 1994)

94 References I (Gale, Church and Yarowsky 1992) Gale, W., Church, K., and Yarowsky, D. Estimating upper and lower bounds on the performance of word-sense disambiguation programs ACL (Miller et. al., 1994) Miller, G., Chodorow, M., Landes, S., Leacock, C., and Thomas, R. Using a semantic concordance for sense identification. ARPA Workshop (Miller, 1995) Miller, G. Wordnet: A lexical database. ACM, 38(11) (Senseval) Senseval evaluation exercises (Agirre and Rigau, 1995) Agirre, E. and Rigau, G. A proposal for word sense disambiguation using conceptual distance. RANLP (Banerjee and Pedersen 2002) Banerjee, S. and Pedersen, T. An adapted Lesk algorithm for word sense disambiguation using WordNet. CICLING 2002.

95 References II (Cowie, Guthrie and Guthrie 1992), Cowie, L. and Guthrie, J. A. and Guthrie, L.: Lexical disambiguation using simulated annealing. COLING (Jiang and Conrath 1997) Jiang, J. and Conrath, D. Semantic similarity based on corpus statistics and lexical taxonomy. COLING (Lesk, 1986) Lesk, M. Automatic sense disambiguation using machine readable dictionaries: How to tell a pine cone from an ice cream cone. SIGDOC (Lin 1998) Lin, D An information theoretic definition of similarity. ICML (Mihalcea, Tarau, Figa 2004) R. Mihalcea, P. Tarau, E. Figa PageRank on Semantic Networks with Application to Word Sense Disambiguation, COLING (Patwardhan, Banerjee, and Pedersen 2003) Patwardhan, S. and Banerjee, S. and Pedersen, T. Using Measures of Semantic Relatedeness for Word Sense Disambiguation. CICLING 2003.

96 References III (Resnik 1995) Resnik, P. Using information content to evaluate semantic similarity. IJCAI (Vasilescu, Langlais, Lapalme 2004) F. Vasilescu, P. Langlais, G. Lapalme Evaluating variants of the Lesk approach for disambiguating words, LREC (Yarowsky, 1994) Decision lists for lexical ambiguity resolution: Application to accent restoration in Spanish and French. In Proceedings of ACL. pp (Yarowsky, 2000) Hierarchical decision lists for word sense disambiguation. Computers and the Humanities, 34.