Top Banner
http://alias-i.com/ lingpipe Coreference in NLP Breck Baldwin [email protected]
23

Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin [email protected].

Dec 29, 2015

Download

Documents

Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Coreference in NLP

Breck Baldwin [email protected]

Page 2: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Outline

Phenomenon Relevant features Applying features to examples Algorithms

Page 3: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Page 4: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Page 5: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Pronouns

Guiliani left Bloomberg to be mayor of a city with a big budget problem. It’s unclear how he’ll be able to handle it during his term.

Page 6: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

“That” References According to John, Bob bought Sue an

Integra, and Sue bought Fred a Legend. But that turned out to be a lie. (a speech

act) But that was false. (proposition)– That struck me as a funny way to describe

the situation. (manner of description)– That caused Sue to become rather poor.

(event)– That caused them both to become rather

poor. (combination of multiple events)

Page 7: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Across Documents

John Smith in Doc 1 =? John Smith in Doc 2 DB id 12123 =? John Smith in Doc 2 What are other classes of coreference?

Page 8: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Constraints on Coreference Number agreement

John’s parents like opera. John hates it/John hates them.

Person and case agreement Nominative: I, we, you, he, she, they Accusative: me,us,you,him,her,them Genitive: my,our,your,his,her,theirGeorge and Edward brought bread and

cheese. They shared them.

Page 9: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Gender agreement John has a Porsche. He/it/she is attractive.

Syntactic constraints: binding theoryJohn bought himself a new Volvo. (himself =

John)John bought him a new Volvo (him = not

John) Selectional restrictions

John left his plane in the hangar.He had flown it from Memphis this morning.

Page 10: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Gender agreement John has a Porsche. He/it/she is attractive.

Syntactic constraints: binding theoryJohn bought himself a new Volvo. (himself =

John)John bought him a new Volvo (him = not

John) Selectional restrictions

John left his plane in the hangar.He had flown it from Memphis this morning.

Page 11: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

And so does…repeated mention– John needed a car to go to his new job. He

decided that he wanted something sporty. Bill went to the dealership with him. He bought a Miata.

Who bought the Miata? What about grammatical role preference?

Parallel constructionsSaturday, Mary went with Sue to the farmer’s

market. Sally went with her to the bookstore.Sunday, Mary went with Sue to the mall.Sally told her she should get over her

shopping obsession.

Page 12: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Verb semantics/thematic rolesJohn telephoned Bill. He’d lost the directions

to his house.John criticized Bill. He’d lost the directions to

his house.

Page 13: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

He had dodged the press for 36 hours, but yesterday the Buck House Butler came out of the cocoon of his room at the Millennium Hotel in New York and shoveled some morsels the way of the panting press. First there was a brief, if obviously self-serving, statement, and then, in good royal tradition, a walkabout.

Dapper in a suit and colourfully striped tie, Paul Burrell was stinging from a weekend of salacious accusations in the British media. He wanted us to know: he had decided after his acquittal at his theft to trial to sell his story to the Daily Mirror because he needed the money to stave off "financial ruination". And he was here in America further to spill the beans to the ABC TV network simply to tell "my side of the story".

Page 14: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

If he wanted attention in America, he was getting it. His lawyer in the States, Richard Greene, implored us to leave alone him, his wife, Maria, and their two sons, Alex and Nicholas, as they spent three more days in Manhattan. Just as quickly he then invited us outside to take pictures and told us where else the besieged family would be heading: Central Park, the Empire State Building and ground zero. The "blabbermouth", as The Sun – doubtless doubled up with envy at the Mirror's coup – has taken to calling Mr Burrell, said not a word during the 10-minute outing to Times Square. But he and his wife, in pinstripe jacket and trousers, wore fixed smiles even as they struggled to keep their footing against a surging scrum of cameramen and reporters. Only the two boys looked resolutely miserable.

Page 15: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Page 16: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

A Harder Case

Tracker Aliases: “Jayson Terril Taylor”, “The Game” Properties: “Person, Male” Contexts: http://..., http://... Relationships:

34234 (Dr.Dre) 21433 (Jay-Z) ...

Page 17: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Page 18: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Fixing “The Game”

Find common phrases in English “The Game” common “Jay-Z” is not

If common, require supporting context via Proper Noun part-of-speech Speculative entity detection has to have found it

as well Could also use related entities

Page 19: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Neuroligin 4 (NLGN4) is a member of a cell adhesion protein family that appears to play a role in the maturation and function of neuronal synapses. Mutations in the X-linked NLGN4 gene are a potential cause of autistic spectrum disorders, and mutations have been reported in several patients with autism, Asperger syndrome, and mental retardation. We describe here a family with a wide variation in neuropsychiatric illness associated with a deletion of exons 4, 5, and 6 of NLGN4. The proband is an autistic boy with a motor tic. His brother has Tourette syndrome and attention deficit hyperactivity disorder. Their mother, a carrier, has a learning disorder, anxiety, and depression. This family demonstrates that NLGN4 mutations can be associated with a wide spectrum of neuropsychiatric conditions and that carriers may be affected with milder symptoms.

NLGN4: human ::: 57502 a: fruit fly ::: 32103,, fruit fly ::: 252438,, house mouse ::: 50518 X: fruit fly ::: 31557,, fruit fly ::: 42032,, fruit fly ::: 45451,, fruit fly ::: 45552 The: Norway rat ::: 25085 an: house mouse ::: 23803 anxiety: house mouse ::: 493091 can: house mouse ::: 12329

Page 20: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Page 21: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Page 22: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

Using Features

Old school within-document Semantic Pass Antecedent Ordering Pick highest match

Hobbs, Lappin & Lease My contribution—also Old School

Impose a partial order on candidate antecedents Pick nothing in the face of ties High precision at decent recall possible

Page 23: Http://alias-i.com/lingpipe Coreference in NLP Breck Baldwin breck@alias-i.com.

http://alias-i.com/lingpipe

New School

Reason over all possible coreference relations as sets (within-doc) Culotta, Hall and McCallum '07

Reasoning over proper probabalistic models of clustering (across doc) Haghighi and Klein '07