Presentation on theme: "Non Monotonic Reasoning for Disambiguation and Parsing Arthi Murugesan."— Presentation transcript:
Non Monotonic Reasoning for Disambiguation and Parsing Arthi Murugesan
Outline what you're doing overall tell us your plan what you've accomplished so for tell us your next few steps remind us of where you're going to get to in the end
Objective : To deal with ambiguity in Parsing using non-monotonic reasoning What does parsing & ambiguity share with non-monotonic reasoning ? –All conditions are not predefined –Assume a default but can take it back –‘bug’ – insect, verb
Defining the problem Ambiguity : –Distorts a one to one relationship between a sentence and a “meaning” Types of ambiguity : –Lexical –Structural –Referential …
Structural Ambiguity I saw an (astronomer) (with a telescope) I (saw) a mouse in the field (with a telescope) Ambiguity in attachment of phrases.
Other Ambiguities Referential Ambiguity –Grounding in real world (Metonym) –Pronouns Colloquial way of speech –With stutters –Changing sentences midway
What has been done : The frog ate the bug. frogThe bug the ate The-frog-NPThe-bug-NP Ate-the-bug The-frog-ate-the-bug det NP VP S
Existing Work HPSG Parsing mechanism has been used for predetermined unambiguous lexical entries. Phrases or Output: assertions in the assumption base
Future Step : To automate the selection of LEXICAL entry: –Probability ( POS tagger ) –Context & Semantics Constraints -Forms Valid sentences? -Maybe earlier heuristics? -Worst case - Alternate worlds -Likely concept
Requirements : Part of speech: –Probability ( POS tagger) Integration with a tool [ Penn tree bank or wordnet] Net Input – Prioritized list of lexical entries of a word –If no sentence is formed : A mechanism of taking back inferences A mechanism of introducing the lexical entry on the next greater priority - HARD
Requirements : Context and Semantics : Semantics of a sentence can be checked against existing knowledge –Semantics of a parsed sentence should be generated (HUGE! Planning to underplay) Lambda expressions –System's knowledge should in a format interoperable with parser’s output knowledge.
Plan Shallow implementation : –Prioritized lists –Semantic generation from parse tree Concentrate on –Varying strengths of rules –Understanding the process by which a proposition or rule is taken back –Explicitly creating worlds & controlling transfer of information between worlds
Expected Output Again and Theory of Working Example word : “bug” Preference of Word senses according to WordNet : (http://wordnet.princeton.edu/perl/webwn) Noun –S: (n) bug (general term for any insect or similar creeping or crawling invertebrate)S: –S: (n) bug, glitch (a fault or defect in a system or machine)S:glitch –S: (n) bug (a small hidden microphone; for listening secretly)S: Verb –S: (v) tease, badger, pester, bug, beleaguer (annoy persistently) "The children teased the boy because of his stammer"S:teasebadgerpesterbeleaguer –S: (v) wiretap, tap, intercept, bug (tap a telephone or telegraph wire to get information) "The FBI was tapping the phone line of the suspected spy"; "Is this hotel room bugged?"S:wiretaptapintercept I saw a bug crawling on the carpet (or) The frog ate the bug - –Using the first sense (Insect) : No contradiction I bug my dad for money – –Using the first 3 senses (NOUN) will result in no valid sentence. So these lexical senses are to be retracted –The first verb sense forms a valid sentence ( tease, badger, pester or annoy) The spy used the bug to eavesdrop. –The first sense (Insect) is used –Forms a contradiction in meaning or “Semantics” [ insect cannot eavesdrop ] –(Probably hack this contradiction for now) –Next sense is introduced (defect) and retracted similarly (Another contradiction in semantics) –Finally the third sense (microphone) is introduced and retained
Existing work ning.htmlhttp://citeseer.ist.psu.edu/anthony00reaso ning.html Reasoning with Output from Parsing Using World Knowledge (2000)