framenet meets the semantic web l.
Download
Skip this Video
Loading SlideShow in 5 Seconds..
FrameNet Meets the Semantic Web PowerPoint Presentation
Download Presentation
FrameNet Meets the Semantic Web

Loading in 2 Seconds...

play fullscreen
1 / 155

FrameNet Meets the Semantic Web - PowerPoint PPT Presentation


  • 737 Views
  • Uploaded on

FrameNet Meets the Semantic Web. Srini Narayanan Charles Fillmore Collin Baker Miriam Petruck. Outline of Presentation. Semantic Frames and the FrameNet Project Status of FrameNet Data and Software Details on the FrameNet process Comparison to other ontologies/resources

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

FrameNet Meets the Semantic Web


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
    Presentation Transcript
    1. FrameNet Meets the Semantic Web Srini Narayanan Charles Fillmore Collin Baker Miriam Petruck

    2. Outline of Presentation • Semantic Frames and the FrameNet Project • Status of FrameNet Data and Software • Details on the FrameNet process • Comparison to other ontologies/resources • Afternoon session: Going through the annotation process demo.

    3. The FrameNet Project • Phase I (NSF, 1997-2000) • ICSI, U-Colorado • Conceptual basis, used existing tools, and perl • Phase II (NSF, 2000-2003) • ICSI, U-Colorado, SRI, SDSU • Scaling up, uses SQL database and Java-based in house tools. Pilot applications developed.

    4. The FrameNet Project C Fillmore PI (ICSI) Co-PI’s: S Narayanan (ICSI, SRI)D Jurafsky (U Colorado) J M Gawron (San Diego State U) Staff: C Baker Project Manager B Cronin Programmer C Wooters Database Designer

    5. Applications An important goal of our work is to present information about the words in a form that will prove usable in various NLP applications: • Question Answering (Berkeley, Colorado) • Semantic Extraction (Berkeley, SRI, Colorado) • Machine Translation (San Diego State)

    6. Frames and Understanding • Hypothesis: People understand things by performing mental operations on what they already know. Such knowledge is describable in terms of information packets called frames.

    7. FrameNet in the Larger Context • The long-term goal is to reason about the world in a way that humans understand and agree with. • Such a system requires a knowledge representation that includes the level of frames. • FrameNet can provide such knowledge for a number of domains. • FrameNet representations complement ontologies and lexicons.

    8. The core work of FrameNet • characterize frames • find words that fit the frames • develop descriptive terminology • extract sample sentences • annotate selected examples • derive "valence" descriptions

    9. Lexicon Building • We study words, • describe the frames or conceptual structures which underlie them, • examine sentences that contain them (from a vast corpus of written English), • and record the ways in which information from the associated frames are expressed in these sentences.

    10. The Core Data The basic data on which FrameNet descriptions are based take the form of a collection of annotated sentences, each coded for the combinatorial properties of one word in it. The annotation is done manually, but several steps are computer-assisted.

    11. The Process • Sentences containing a given word are extracted from the corpus and made available for annotation. • Student annotators select the phrases that identify particular semantic roles in the sentences, and tag them with the name of these roles. • Automatic processes then provide grammatical information about the tagged phrases.

    12. SAMPLE ANNOTATIONS

    13. Types of Words / Frames • events • artifacts, built objects • natural kinds, parts and aggregates • terrain features • institutions, belief systems, practices • space, time, location, motion • etc.

    14. Event Frames Event frames have temporal structure, and generally have constraints on what precedes them, what happens during them, and what state the world is in once the event has been completed.

    15. Sample Event Frame:Commercial Transaction Initial state:Vendor has Goods, wants MoneyCustomer wants Goods, has Money Transition:Vendor transmits Goods to CustomerCustomer transmits Money to Vendor Final state:Vendor has Money Customer has Goods

    16. Sample Event Frame:Commercial Transaction Initial state:Vendor has Goods, wants MoneyCustomer wants Goods, has Money Transition:Vendor transmits Goods to CustomerCustomer transmits Money to Vendor Final state:Vendor has Money Customer has Goods (It’s a bit more complicated than that.)

    17. Partial Wordlist for Commercial Transactions Verbs: pay, spend, cost, buy, sell, charge Nouns: cost, price, payment Adjectives: expensive, cheap

    18. Meaning and Syntax • The various verbs that evoke this frame introduce the elements of the frame in different ways. • The identities of the buyer, seller, goods and money • Information expressed in sentences containing these verbs occurs in different places in the sentence depending on the verb.

    19. Sheboughtsome carrotsfrom the greengrocerfor a dollar. Customer Vendor from BUY for Goods Money

    20. Shepaida dollarto the greengrocerfor some carrots. Customer Vendor to PAY for Goods Money

    21. Shepaidthe greengrocera dollarfor the carrots. Customer Vendor PAY for Goods Money

    22. Shespenta dollaron the carrots. Customer Vendor SPEND on Goods Money

    23. The greengrocer sold some carrotsto herfor a dollar. Customer Vendor to SELL for Goods Money

    24. The greengrocersoldhersome carrotsfor a dollar. Customer Vendor SELL for Goods Money

    25. The greengrocerchargeda dollarfor a bunch of carrots. Customer Vendor CHARGE for Goods Money

    26. The greengrocerchargedhera dollarfor the carrots. Customer Vendor CHARGE for Goods Money

    27. A bunch of carrotscostsa dollar. Customer Vendor COST Goods Money

    28. A bunch of carrotscosthera dollar. Customer Vendor COST Goods Money

    29. Itcostsa dollarto ride the bus. IT Customer Vendor COST Goods to do X Money

    30. Itcostmea dollarto ride the bus. IT Customer Vendor COST Goods to do X Money

    31. FrameNet Product • For every target word, • describe the frames or conceptual structures which underlie them, • and annotate example sentences that cover the ways in which information from the associated frames are expressed in these sentences.

    32. FN work: characterizing frames • One of the things we do is characterize such information packets - beginning with informal descriptions. • We can begin with Revenge.

    33. The Revenge frame The Revenge frame involves a situation in which • A has done something to harm B and • B takes action to harm A in turn • B's action is carried out independently of any legal or other institutional setting

    34. FN work: finding words in frame • We look for words in the language that bring to mind the individual frames. • We say that the words evoke the frames.

    35. Vocabulary for Revenge • Nouns: revenge, vengeance, reprisal, retaliation • Verbs: avenge, retaliate, revenge, get back (at), get even (with), pay back • Adjectives: vengeful, vindictive

    36. FN work: choosing FE names • We develop a descriptive vocabulary for the components of each frame, called frame elements (FEs). • We use FE names in labeling the constituents of sentences exhibiting the frame.

    37. FEs for Revenge • Frame Definition: Because of some injury to something or someone important to an avenger, the avenger inflicts a punishment on the offender. The offender is the person responsible for the injury. The injured_party may or may not be the same individual as the avenger. • FE List: avenger, offender, injury, injured_party, punishment.

    38. FN work: collecting examples • We extract from our corpus examples of sentences showing the uses of each word in the frame.

    39. Obviously we need to conduct a more regimented search, grouping examples with related structures.

    40. Examples of simple use are swamped by the idiomatic phrase "with a vengeance".

    41. FN work: annotating examples • We select sentences exhibiting common collocations and showing all major syntactic contexts. • Using the names assigned to FEs in the frame, we label the constituents of sentences that express these FEs.

    42. FN work: summarizing results • Automatic processes summarize the results, linking FEs with information about their grammatical realization. • The output is presented in the form of various reports in the public website, in XML format in the data release.

    43. I avenged my brother.

    44. I avenged his death.

    45. Querying the data: meaning to form Through various viewers built on the FN database we can, for example, ask how particular FEs get expressed in sentences evoking a given frame.