1. 11 Chapter 20 Part 2 Computational Lexical Semantics Acknowledgements: these slides include material from Rada Mihalcea, Ray Mooney, Katrin Erk, and Ani Nenkova

2. Knowledge-based WSD Task definition 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 2

3. 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 3

4. 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 4

5. MRD – A Resource for Knowledge-based WSD A thesaurus adds: –An explicit synonymy relation between word meanings A semantic network adds: –Hypernymy/hyponymy (IS-A), meronymy/holonymy (PART-OF), antonymy, etc. WordNet synsets for the noun“plant” 1. plant, works, industrial plant 2. plant, flora, plant life WordNet related concepts for the meaning “plant life” {plant, flora, plant life} hypernym: {organism, being} hypomym: {house plant}, {fungus}, … meronym: {plant tissue}, {plant part} member holonym: {Plantae, kingdom Plantae, plant kingdom} 5

6. Lesk Algorithm (Michael Lesk 1986): Identify senses of words in context using definition overlap. That is, disambiguate more than one word. 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 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#3 = 0 6

7. 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) –Let’s review (from CS1571) 7

8. 8 Search Types –Backtracking state-space search –Local Search and Optimization –Constraint satisfaction search –Adversarial search

9. 9 Local Search Use a single current state and move only to neighbors. Use little space Can find reasonable solutions in large or infinite (continuous) state spaces for which the other algorithms are not suitable

10. 10 Optimization Local search is often suitable for optimization problems. Search for best state by optimizing an objective function.

11. 11 Visualization States are laid out in a landscape Height corresponds to the objective function value Move around the landscape to find the highest (or lowest) peak Only keep track of the current states and immediate neighbors

12. 12 Simulated Annealing Based on a metallurgical metaphor –Start with a temperature set very high and slowly reduce it.

13. 13 Simulated Annealing Annealing: harden metals and glass by heating them to a high temperature and then gradually cooling them At the start, make lots of moves and then gradually slow down

14. 14 Simulated Annealing More formally… –Generate a random new neighbor from current state. –If it’s better take it. –If it’s worse then take it with some probability proportional to the temperature and the delta between the new and old states.

15. 15 Simulated annealing Probability of a move decreases with the amount ΔE by which the evaluation is worsened A second parameter T is also used to determine the probability: high T allows more worse moves, T close to zero results in few or no bad moves Schedule input determines the value of T as a function of the completed cycles

16. 16 function Simulated-Annealing(problem, schedule) returns a solution state inputs:problem, a problem schedule, a mapping from time to “temperature” current ← Make-Node(Initial-State[problem]) for t ← 1 to ∞ do T ← schedule[t] if T=0 then return current next ← a randomly selected successor of current ΔE ← Value[next] – Value[current] if ΔE > 0 then current ← next else current ← next only with probability e ΔE/T

17. Intuitions the algorithm wanders around during the early parts of the search, hopefully toward a good general region of the state space Toward the end, the algorithm does a more focused search, making few bad moves 17

18. 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) Given: W, set of words we are disambiguating State: One sense for each word in W Neighbors of state: the result of changing one word sense Objective function: value(state) –Let DWs(state) be the words that appear in the union of the definitions of the senses in state; –value(state) = sum over words in DWs(state): # times it appears in the union of the definitions of the senses –The value will be higher, the more words appear in multiple definitions. Start state: the most frequent sense of each word 18

19. Lesk Algorithm: A Simplified Version Original Lesk definition: measure overlap between sense definitions for all words in the text –Identify simultaneously the correct senses for all words in the text Simplified Lesk (Kilgarriff & Rosensweig 2000): measure overlap between sense definitions of a word and its context in the text –Identify the correct sense for one word at a time Search space significantly reduced (the context in the text is fixed for each word instance) 19

20. Lesk Algorithm: A Simplified Version Example: 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 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 context of the word in the text 3.Choose the sense that leads to highest overlap 20

21. Selectional Preferences A way to constrain the possible meanings of words in a given context E.g. “Wash a dish” vs. “Cook a dish” –WASH-OBJECT vs. COOK-FOOD Alternative terminology –Selectional Restrictions –Selectional Preferences –Selectional Constraints 21

22. Acquiring Selectional Preferences From raw corpora –Frequency counts –Information theory measures 22

23. Preliminaries: Learning Word-to-Word Relations An indication of the semantic fit between two words 1. Frequency counts (in a parsed corpus) –Pairs of words connected by a syntactic relations 2. Conditional probabilities –Condition on one of the words 23

24. Learning Selectional Preferences Word-to-class relations (Resnik 1993) –Quantify the contribution of a semantic class using all the senses subsumed by that class (e.g., the class is an ancestor in WordNet) 24

25. Using Selectional Preferences for WSD Algorithm: –Let N be a noun that stands in relationship R to predicate P. Let s1…sk be its possible senses. –For i from 1 to k, compute: –Ci = {c |c is an ancestor of si} –Ai = max for c in Ci A(P,c,R) –Ai is the score for sense i. Select the sense with the highest score. For example: Letter has 3 senses in WordNet (written message; varsity letter; alphabetic character) and belongs to 19 classes in all. Suppose we have predicate “write”. For each sense, calculate a score, by measuring association of “write” & direct object, with each ancestor of that sense. 25