Presentation is loading. Please wait.

Presentation is loading. Please wait.

CS 4705 Lecture 21 Algorithms for Reference Resolution.

Similar presentations


Presentation on theme: "CS 4705 Lecture 21 Algorithms for Reference Resolution."— Presentation transcript:

1 CS 4705 Lecture 21 Algorithms for Reference Resolution

2 Issues Which features should we make use of? How should we order them? I.e. which override which? What should appear in our discourse model? I.e., what types of information do we need to keep track of? How to evaluate?

3 Lappin & Leass ‘94 Weights candidate antecedents by recency and syntactic preference (86% accuracy) Two major functions to perform: –Update the discourse model when an NP that evokes a new entity is found in the text, computing the salience of this entity for future anaphora resolution –Find most likely referent for current anaphor by considering possible antecedents and their salience values Partial example for 3P, non-reflexives

4 Salience Factors and Weights (Trained)

5 Implicit ordering of arguments: subj/exist pred/obj/indobj-oblique/dem.advPP On the sofa, the cat was eating bonbons. sofa: 100+40+80=220 cat: 100+80+50+80=310 bonbons: 100+50+50+80=280 Update: –Weights accumulate over time –Cut in half after each sentence processed –Salience values for subsequent referents accumulate for equivalence class of correferential items (exceptions, e.g. multiple references in same sentence)

6 The bonbons were clearly very tasty. sofa: 140/2=70 cat: 310/2=155 bonbons: 280/2 +(100+80+50+80)=450 –Additional salience weights for grammatical role parallelism (35) and cataphora (-175) calculated when pronoun to be resolved –Additional constraints on gender/number agrmt/syntax They were a gift from an unknown admirer. sofa: 70/2=35 cat: 155/2=77.5 bonbons: 450/2=225 (+35)

7 Reference Resolution Collect potential referents (up to four sentences back): {sofa,cat,bonbons} Remove those that don’t agree in number/gender with pronoun {bonbons} Remove those that don’t pass intra-sentential syntactic coreference constraints The cat washed it. (it  cat) Add applicable values for role parallelism (+35) or cataphora (-175) to current salience value for each potential antecedent Select referent with highest salience; if tie, select closest referent in string

8 Solution They were a gift from an unknown admirer. (they=bonbons) bonbons: 225/2=112.5 (+35) Why? Only potential antecedent to agree in gender/number Also has highest salience (147.5) Or… It ate them all. (it=?) sofa: 70/2=35 cat: 155/2=77.5 bonbons: 225/2=112.5

9 Centering (Grosz et al ‘95;Brennan et al ‘87) Adds concept of discourse center –Un: an utterance –Backward-looking center C b (U n ): current focus after U n interpreted –Forward-looking centers C f (U n ): ordered list of potential focii referred to in U n C b (U n+1 ) is highest ranked member of Cf(U n ) C p (U n ): preferred center of C f (U n ) Other C f ordered subj<exist. Prednom<obj<indobj- oblique<dem. advPP (Brennan et al)

10 Transitions from Un to Un+1

11 Rules If any element of C f (U n ) is pronominalized in U n+1, then C b (U n+1 ) must be Preference: Continue > Retain > Smooth-Shift > Rough-Shift Algorithm –Generate C b -C f combinations for all possible reference assignments –Filter by constraints (syntactic coreference, selectional restrictions,…) –Rank by preference among transition orderings

12 Example U 1 :George saw a mouse on the floor. U 2 :He showed it to Harry. U 3 :He ate it. Grammatical role hierarchy –C f (U 1 ): {George,mouse,floor} –C p (U 1 ): George –C b (U 1 ): undefined Assume it=mouse –C f (U 2 ): {George, mouse,Harry} –C p (U 2 ): George –C b (U 2 ): George –Continue (C p (U 2 )=C b (U 2 ); C b (U 1 ) undefined

13 Assume it=floor –C f (U 2 ): {George,floor,Harry} –C p (U 2 ): George –C b (U 2 ): George –Continue (C p (U 2 )=C b (U 2 ); C b (U 1 ) undefined) What did George show Harry? –How to break a tie? Ordering of previous C f list? U 3 : He ate it. Assume he=George, it=mouse –C f (U 3 ): {George,mouse} –C p (U 3 ): George –C b (U 3 ): George –Continue (C p (U 3 )=C b (U 3 ); C b (U 3 )=C b (U 2 ))

14 Assume he=Harry, it=mouse –C f (U3): {Harry,mouse} –C p (U3): Harry –C b (U 3 ): Harry –Continue (C p (U 3 )=C b (U 3 ); C b (U 3 )  C b (U 2 )) So, who ate the mouse?

15 Centering Theory vs. Lappin & Leass Centering sometimes prefers an antecedent Lappin and Leass (or Hobbs) would consider to have low salience –Always prefers a single pronominalization strategy: prescriptive, assumes discourse coherent –Constraints too simple: grammatical role, recency, repeated mention –Assumes correct syntactic information available as input

16 Hobbs ‘78: Syntax-Based Reference Resolution Search for antecedent in parse tree of current sentence, then prior sentences in order of recency –For current S, search for NP nodes to the left of a path p from the pronoun up to the first NP or S node (X) above it in L2R, breadth-first –Propose as pronoun’s antecedent any NP you find as long as it has an NP or S node between itself and X –If X is highest node in sentence, search prior sentences, L2R breadth-first, for candidate NPs –O.w., continue searching current tree by going to next S or NP above X before going to prior sentences

17 Evaluation Centering only now being specified enough to be tested automatically on real data –Specifying the Parameters of Centering Theory: A Corpus-Based Evaluation using Text from Application- Oriented Domains (Poesio et al., ACL 2000) Walker ‘89 manual comparison of Centering vs. Hobbs ‘78 –Only 281 examples from 3 genres –Assumed correct features given as input to each –Centering 77.6% vs. Hobbs 81.8% –Lappin and Leass’ 86% accuracy on test set from computer training manuals


Download ppt "CS 4705 Lecture 21 Algorithms for Reference Resolution."

Similar presentations


Ads by Google