Word Meaning & Word Sense Disambiguation

Transcription

1 Word Meaning & Word Sense Disambiguation CMSC 723 / LING 723 / INST 725 MARINE CARPUAT marine@cs.umd.edu

2 Today Representing word meaning Word sense disambiguation as supervised classification Word sense disambiguation without annotated examples

3 Drunk gets nine year in violin case. beatrice/humor/headlines.html

4 How do we know that a word (lemma) has distinct senses? Linguists often design tests for this purpose e.g., zeugma combines distinct senses in an uncomfortable way Which flight serves breakfast? Which flights serve Tuscon? *Which flights serve breakfast and Tuscon?

5 Where can we look up the meaning of words? Dictionary?

6 Word Senses Word sense = distinct meaning of a word Same word, different senses Homonyms (homonymy): unrelated senses; identical orthographic form is coincidental Polysemes (polysemy): related, but distinct senses Metonyms (metonymy): stand in, technically, a subcase of polysemy Different word, same sense Synonyms (synonymy)

7 Homophones: same pronunciation, different orthography, different meaning Examples: would/wood, to/too/two Homographs: distinct senses, same orthographic form, different pronunciation Examples: bass (fish) vs. bass (instrument)

8 Relationship Between Senses IS-A relationships From specific to general (up): hypernym (hypernymy) From general to specific (down): hyponym (hyponymy) Part-Whole relationships wheel is a meronym of car (meronymy) car is a holonym of wheel (holonymy)

9 WordNet: a lexical database for English Includes most English nouns, verbs, adjectives, adverbs Electronic format makes it amenable to automatic manipulation: used in many NLP applications WordNets generically refers to similar resources in other languages

10 WordNet: History Research in artificial intelligence: How do humans store and access knowledge about concept? Hypothesis: concepts are interconnected via meaningful relations Useful for reasoning The WordNet project started in 1986 Can most (all?) of the words in a language be represented as a semantic network where words are interlinked by meaning? If so, the result would be a large semantic network

11 Synonymy in WordNet WordNet is organized in terms of synsets Unordered set of (roughly) synonymous words (or multi-word phrases) Each synset expresses a distinct meaning/concept

12 WordNet: Example Noun {pipe, tobacco pipe} (a tube with a small bowl at one end; used for smoking tobacco) {pipe, pipage, piping} (a long tube made of metal or plastic that is used to carry water or oil or gas etc.) {pipe, tube} (a hollow cylindrical shape) {pipe} (a tubular wind instrument) {organ pipe, pipe, pipework} (the flues and stops on a pipe organ) Verb {shriek, shrill, pipe up, pipe} (utter a shrill cry) {pipe} (transport by pipeline) pipe oil, water, and gas into the desert {pipe} (play on a pipe) pipe a tune {pipe} (trim with piping) pipe the skirt What do you think of the sense granularity?

13 The Net Part of WordNet {conveyance; transport} hyperonym {vehicle} hyperonym {bumper} {motor vehicle; automotivevehicle} meronym hyperonym {car dor} {car window} {car; auto; automobile; machine; motorcar} {armrest} meronym hyperonym hyperonym {cruiser; squadcar; patrol car; policecar; prowl car} {cab; taxi; hack; taxicab; } {car miror} meronym meronym {hinge; flexiblejoint} {dorlock}

14 WordNet 3.0: Size Part of speech Word form Synsets Noun 117,798 82,115 Verb 11,529 13,767 Adjective 21,479 18,156 Adverb 4,481 3,621 Total 155, ,659

15 Word Sense From WordNet: Noun {pipe, tobacco pipe} (a tube with a small bowl at one end; used for smoking tobacco) {pipe, pipage, piping} (a long tube made of metal or plastic that is used to carry water or oil or gas etc.) {pipe, tube} (a hollow cylindrical shape) {pipe} (a tubular wind instrument) {organ pipe, pipe, pipework} (the flues and stops on a pipe organ) Verb {shriek, shrill, pipe up, pipe} (utter a shrill cry) {pipe} (transport by pipeline) pipe oil, water, and gas into the desert {pipe} (play on a pipe) pipe a tune {pipe} (trim with piping) pipe the skirt

16 WORD SENSE DISAMBIGUATION

17 Word Sense Disambiguation Task: automatically select the correct sense of a word Input: a word in context Output: sense of the word Can be framed as lexical sample (focus on one word type at a time) or all-words (disambiguate all content words in a document) Motivated by many applications: Information retrieval Machine translation

18 How big is the problem? Most words in English have only one sense 62% in Longman s Dictionary of Contemporary English 79% in WordNet But the others tend to have several senses Average of 3.83 in LDOCE Average of 2.96 in WordNet Ambiguous words are more frequently used In the British National Corpus, 84% of instances have more than one sense Some senses are more frequent than others

19 Ground Truth Which sense inventory do we use?

20 Existing Corpora Lexical sample line-hard-serve corpus (4k sense-tagged examples) interest corpus (2,369 sense-tagged examples) All-words SemCor (234k words, subset of Brown Corpus) Senseval/SemEval (2081 tagged content words from 5k total words)

21 Evaluation Intrinsic Measure accuracy of sense selection wrt ground truth Extrinsic Integrate WSD as part of a bigger end-to-end system, e.g., machine translation or information retrieval Compare WSD

22 Baseline Performance Baseline: most frequent sense Equivalent to take first sense in WordNet Does surprisingly well! 62% accuracy in this case!

23 Upper Bound Performance Upper bound Fine-grained WordNet sense: 75-80% human agreement Coarser-grained inventories: 90% human agreement possible

24 WSD as Supervised Classification Training Testing training data? unlabeled document label 1 label 2 label 3 label 4 supervised machine learning algorithm Feature Functions Classifier label 1? label 2? label 3? label 4?

25 WSD Approaches Depending on use of manually created knowledge sources Knowledge-lean Knowledge-rich Depending on use of labeled data Supervised Semi- or minimally supervised Unsupervised

26 Simplest WSD algorithm: Lesk s Algorithm Intuition: note word overlap between context and dictionary entries Unsupervised, but knowledge rich The bank can guarantee deposits will eventually cover future tuition costs because it invests in adjustable-rate mortgage securities. WordNet

27 Lesk s Algorithm Simplest implementation: Count overlapping content words between glosses and context Lots of variants: Include the examples in dictionary definitions Include hypernyms and hyponyms Give more weight to larger overlaps (e.g., bigrams) Give extra weight to infrequent words

28 WSD Accuracy Generally Supervised approaches yield ~70-80% accuracy However depends on actual word, sense inventory, amount of training data, number of features, etc.

29 WORD SENSE DISAMBIGUATION: MINIMIZING SUPERVISION

30 Minimally Supervised WSD Problem: annotations are expensive! Solution 1: Bootstrapping or co-training (Yarowsky 1995) Start with (small) seed, learn classifier Use classifier to label rest of corpus Retain confident labels, add to training set Learn new classifier Repeat Heuristics (derived from observation): One sense per discourse One sense per collocation

31 One Sense per Discourse A word tends to preserve its meaning across all its occurrences in a given discourse Gale et al words with two-way ambiguity, e.g. plant, crane, etc. 98% of the two-word occurrences in the same discourse carry the same meaning Krovetz 1998 Heuristic true mostly for coarse-grained senses and for homonymy rather than polysemy Performance of one sense per discourse measured on SemCor is approximately 70%

32 One Sense per Collocation A word tends to preserve its meaning when used in the same collocation Strong for adjacent collocations Weaker as the distance between words increases Evaluation: 97% precision on words with two-way ambiguity Again, accuracy depends on granularity: 70% precision on SemCor words

33

34

35

36

37 Yarowsky s Method: Stopping Stop when: Error on training data is less than a threshold No more training data is covered

38 Yarowsky s Method: Discussion Advantages Accuracy is about as good as a supervised algorithm Bootstrapping: far less manual effort Disadvantages Seeds may be tricky to construct Works only for coarse-grained sense distinctions Snowballing error with co-training

39 WSD with 2 nd language as supervision Problems: annotations are expensive! What s the proper sense inventory? How fine or coarse grained? Application specific? Observation: multiple senses translate to different words in other languages Use the foreign language as the sense inventory Added bonus: annotations for free! (Using machine translation data)

40 Today Representing word senses & word relations WordNet Word Sense Disambiguation Lesk Algorithm Supervised classification Minimizing supervision Co-training: combine 2 views of data Use parallel text Next: general techniques for learning without annotated training examples If needed review probability, expectations