Downloaded 15 times
![14 Minsky [1] “When one encounters a new situation […] one selects from memory a structure called a Frame. This is a remembered framework to be adapted to fit reality by changing details as necessary.” “A frame is a data-structure for representing a stereotyped situation, like being in a certain kind of living room, or going to a child's birthday party” “We can think of a frame as a network of nodes and relations.” “Collections of related frames are linked together into frame-systems” Fillmore [2] “[…] in characterising a language system we must add to the description of grammar and lexicon a description of the cognitive and interactional “frames” […]” “The evolution toward language must have consisted in part in the gradual acquisition of a reportory of frames and of mental processes for operating with them, and eventually the capacity to create new frames and to transmit them.” “[…] in order to perceive something or to attain a concept, what is […] necessary is to have in memory a repertoire of prototypes. The act of perception or conception being that of recognizing in what ways an object can be seens as an instance of one or another of these prototypes.”](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-14-2048.jpg)
![18 From entity-centric to frame-centric design and extraction Before: Key terms à classes/properties After: Key situationsà frames/patterns Frames as units of meaning [3]](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-18-2048.jpg)
![25 This is useful, but it’s not enough Semantic heterogeneity Lack of knowledge boundaries (context) [3] marriedWith firstMarriageWith spousemarriage spousedate](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-25-2048.jpg)
![26 The role of frames in knowledge representation, extraction and interaction Performingempirical observations on the web (in line with van Harmelen’s [4]) Using frames for driving the design of solutions to research problems andtest their performance Frames as units of meaning](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-26-2048.jpg)
![28 Frame-based knowledge extraction [5] http://wit.istc.cnr.it/stlab-tools/fred/ From text to linked data](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-28-2048.jpg)
![31 Automatic selection of relevant binary projections of frames Usable label generation Formal alignmentbetween frames and binary properties Binary relations [6]](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-31-2048.jpg)
![35 Semantic Web triples and properties generation “Rico Lebrun taught visual arts at the Chouinard Art Institute and at the Disney Studios. He was influenced by Michelangelo and maintained a lifelong affinity for Goya and Picasso.” dbpedia:Rico_Lebrun s:teachAbout dbpedia:Visual_arts . s:teachAbout a owl:ObjectProperty ; rdfs:subPropertyOf fred:Teach; rdfs:domain wibi:Artist ; rdfs:range wibi:Art ; grounding:definedFromFormalRepresentation fred-graph:a6705cedbf9b53d10bbcdedaa3be9791da0a9e94 ; grounding:derivedFromLinguisticEvidence s:linguisticEvidence ; owl:propertyChainAxiom([ owl:inverseOf s:AgentTeach ] s:TopicTeach) . _:b2 a alignment:Cell ; alignment:entity1 s:teachAbout ; alignment:entity2 <http://purl.org/vocab/aiiso/schema#teaches> ; alignment:measure "0.846"^xsd:float ; alignment:relation "equivalence" . domain, range, subsumption linguistic and formal scope alignment to existing LOD vocabularies](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-35-2048.jpg)
![36 Evaluation tasks [7] 3 6 Tool/Task Topics NER NE-RS TE TE-RS Senses Taxo Rel Roles Events Frames +SRL AIDA – + + – – + – – – – – Alchemy + + – + – + – + – – – Apache Stanbol – + + – – + – – – – – CiceroLite – + + + + + – + + + + DB Spotlight – + + – – + – – – – – FOX + + + + + + – – – – – FRED – + + + + + + + + + + NERD – + + – – + – – – – – Ollie – – – – – – – + – – – Open Calais + + – – – + – – – + – PoolParty KD + – – – – – – – – – – ReVerb – – – – – – – + – – – Semiosearch – – + – + – – – – – – Tagme – + + + + – – – – – – Wikimeta – + – + + + – – – – – Zemanta – + – – – + – – – – –](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-36-2048.jpg)
![37 Topic detection and Opinion holder detection [8] Sentiment propagation through frames and roles [9] Sentiment analysis “People hope that the President will be condemned by the judges”](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-37-2048.jpg)
![39 Frame-basedlinked data shows an effective representation of discourse Our ultimate goal is machine understanding, hence an important issue is the limited coverage of existing resources and their integration with factual world knowledge FrameBase [10] partially addresses this problem, starting from similar principles and intuitions STLab has develop Framester [11,12]: a general web-scale integrated resource which integrateslinguistic and world factual knowledge (see Aldo’s presentation later) Coverage and integration of linguistic and world knowledge](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-39-2048.jpg)
![45 References [1] Marvin Minsky: A Framework for Representing Knowledge. MIT-AI Laboratory Memo 306, June, 1974. [2] Charles J Fillmore. Frame Semantics and the Nature of Language. Annals of the New York Academy of Sciences, 280(1):20-32, 1976. [3] Aldo Gangemi, Valentina Presutti: Towards a pattern science for the Semantic Web. Semantic Web 1(1-2): 61-68 (2010) [4] Frank van Harmelen: The Web of Data: do we understand what we build? https://sssw.org/2016/?page_id=386 [5] Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero, Andrea Giovanni Nuzzolese, Francesco Draicchio, Misael Mongiovì: Semantic Web Machine Reading with FRED. Semantic Web (To appear) [6] Valentina Presutti, Andrea Giovanni Nuzzolese, Sergio Consoli, Aldo Gangemi, Diego Regorgiato Recupero: From hyperlinks to Semantic Web properties using Open Knowledge Extraction pp. 351-378, Semantic Web, Volume 7, Number 4 / 2016.](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-45-2048.jpg)
![46 [7] Aldo Gangemi: A Comparison of Knowledge Extraction Tools for the Semantic Web. ESWC 2013: 351-366 [8] Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero: Frame-Based Detection of Opinion Holders and Topics: A Model and a Tool. IEEE Comp. Int. Mag. 9(1): 20-30 (2014) [9] Diego Reforgiato Recupero, Valentina Presutti, Sergio Consoli, Aldo Gangemi, Andrea Giovanni Nuzzolese: Sentilo: Frame-Based Sentiment Analysis. Cognitive Computation 7(2): 211-225 (2015) [10] Jacobo Rouces, Gerard de Melo, and Katja Hose. Framebase: Representing n-ary relations using semantic frames. ESWC 2015: 505-521 [11] Aldo Gangemi, Mehwish Alam, Valentina Presutti, Luigi Asprino and Diego Reforgiato Recupero: Framester: A Wide Coverage Linguistic Linked Data Hub. In Proceedings of EKAW 2016 [12] Aldo Gangemi, Mehwish Alam, Valentina Presutti: Word Frame Disambiguation: Evaluating Linguistic Linked Data on Frame Detection. LD4IE@ISWC 2016: 23-31 References cont.](https://image.slidesharecdn.com/ld4ieiswc2016-161018000125/75/Knowledge-Extraction-and-Linked-Data-Playing-with-Frames-46-2048.jpg)
Uploaded byValentina Presutti
Knowledge Extraction and Linked Data: Playing with Frames
This document summarizes Valentina Presutti's presentation on using frames for knowledge extraction and linked data. It discusses how frames can be used as units of meaning to reconcile knowledge from different sources. It provides background on frames and examples of how they can represent situations and relationships described in text. The document then outlines several projects from STLab that use a frame-based approach for tasks like knowledge extraction, relation extraction, and sentiment analysis. It discusses tools like FRED and Framester that perform frame-based knowledge extraction and integrate linguistic and factual knowledge through linked data.
Knowledge Extraction and Linked Data: Playing with Frames
- 1. Knowledge Extraction andLinked Data: Playing with Frames Valentina Presutti STLab, ISTC-CNR Linked Data For Information Extraction @ ISWC 2016 Tuesday, October 18th 2016
- 2. STLab team Valentina PresuttiAldo Gangemi Andrea Nuzzolese Diego Reforgiato Martina Sangiovanni Mario Caruso Giorgia Lodi Alessandro Russo Luigi Asprino Piero Conca 2
- 3. 3 • Frames asunits of meaning (claim andintuition) • Background on frames • From entity-centric to frame-centric knowledge extraction • Some STLab research projects and results • Next and open issues Outline
- 4.
- 5. 5 Frames naturally supportknowledge reconciliation, regardless the logical, conceptual or syntactic representation of knowledge sources
- 6. To understand whospeaks to us or a text we read We identify the main entities and how they relate to each other within a schema (frame) Frame occurrences + context-dependent reasoning The intuition 6
- 7. 7 I went tothe disco and I met a friend, who had lost her keys. We spent the night looking for them.
- 8. 8 I went tothe disco and I met a friend, who had lost her keys. We spent the night looking for them.
- 9. 9 I went tothe disco and I met a friend, who had lost her keys. We spent the night looking for them.
- 10. 10 I went tothe disco and I met a friend, who had lost her keys. We spent the night looking for them.
- 11. I went tothe disco and I met a friend, who had lost her keys. We spent the night looking for them. 11
- 12. 12 We want machinesto perform this process
- 13.
- 14. 14 Minsky [1] “When oneencounters a new situation […] one selects from memory a structure called a Frame. This is a remembered framework to be adapted to fit reality by changing details as necessary.” “A frame is a data-structure for representing a stereotyped situation, like being in a certain kind of living room, or going to a child's birthday party” “We can think of a frame as a network of nodes and relations.” “Collections of related frames are linked together into frame-systems” Fillmore [2] “[…] in characterising a language system we must add to the description of grammar and lexicon a description of the cognitive and interactional “frames” […]” “The evolution toward language must have consisted in part in the gradual acquisition of a reportory of frames and of mental processes for operating with them, and eventually the capacity to create new frames and to transmit them.” “[…] in order to perceive something or to attain a concept, what is […] necessary is to have in memory a repertoire of prototypes. The act of perception or conception being that of recognizing in what ways an object can be seens as an instance of one or another of these prototypes.”
- 15. 15 Frame definition andrepresentation
- 16.
- 17. 17 N-ary relation f(e,e1,…en) f is a first order logic relation e is a variable for any event or situation described by f ei is a variable for any of the entity arguments of f An OWL n-ary relation pattern the n-ary relation is the reification of f, i.e. e the n objects represent the arguments of f the n argument relations are binary projections of f including e co-participation relations are binary projections of f not including e Representing frames “Hagrid rolled up a note for Harry in Hogwarts”
- 18. 18 From entity-centric to frame-centricdesign and extraction Before: Key terms à classes/properties After: Key situationsà frames/patterns Frames as units of meaning [3]
- 19. 19 From entity-centric toframe-centric knowledge extraction
- 20. 20 We want machinesto perform this process
- 21. This requires atleast three ingredients: Knowledge representation Knowledge extraction Automated reasoning and learning 21
- 22. The Semantic Weband Linked Data Knowledge representation Knowledge extraction Automated reasoning 22
- 23. Mary marriedWith John Mary weddingDate October 12th,2016 John weddingDate October 12th, 2016 Mary weddingPlace Kobe John weddingPlace Kobe Mary weddingPlace Rome The Semantic Web and Linked Data Knowledge representation Knowledge extraction Automated reasoning
- 24. 24 OL & KEtools main focus: Named Entity extraction Taxonomy induction, Relation extraction Axiom extraction, … The Semantic Web and Linked Data Knowledge representation Knowledge extraction Automated reasoning
- 25. 25 This is useful,but it’s not enough Semantic heterogeneity Lack of knowledge boundaries (context) [3] marriedWith firstMarriageWith spousemarriage spousedate
- 26. 26 The role offrames in knowledge representation, extraction and interaction Performingempirical observations on the web (in line with van Harmelen’s [4]) Using frames for driving the design of solutions to research problems andtest their performance Frames as units of meaning
- 27. 27 Some projects andresults
- 28. 28 Frame-based knowledge extraction[5] http://wit.istc.cnr.it/stlab-tools/fred/ From text to linked data
- 29. 29 Frame-based Linked Data “Rico Lebrun taughtvisual arts at the Chouinard Art Institute and at the Disney Studios. He was influenced by Michelangelo and maintained a lifelong affinity for Goya and Picasso.”
- 30. 30 FRED “The Black Handmight not have decided to barbarously assassinate Franz Ferdinand after he arrived in Sarajevo on June 28th, 1914”
- 31. 31 Automatic selection ofrelevant binary projections of frames Usable label generation Formal alignmentbetween frames and binary properties Binary relations [6]
- 32. 32 Binary relation assessment “RicoLebrun taught visual arts at the Chouinard Art Institute and at the Disney Studios. He was influenced by Michelangelo and maintained a lifelong affinity for Goya and Picasso.” Subject ObjectSubject Object http://wit.istc.cnr.it/stlab-tools/legalo
- 33. 33 Binary property generation vn.role:Actor1-> “with” vn.role:Actor2 -> “with” vn.role:Beneficiary -> “for” vn.role:Instrument -> “with” vn.role:Destination -> “to” vn.role:Topic -> “about” vn.role:Source -> “from” Subject Object legalo:teachArtAt teach art at “Rico Lebrun taught visual arts at the Chouinard Art Institute and at the Disney Studios. He was influenced by Michelangelo and maintained a lifelong affinity for Goya and Picasso.” http://wit.istc.cnr.it/stlab-tools/legalo
- 34. 34 vn.role:Actor1 -> “with” vn.role:Actor2 -> “with” vn.role:Beneficiary -> “for” vn.role:Instrument -> “with” vn.role:Destination -> “to” vn.role:Topic -> “about” vn.role:Source -> “from” Subject Object legalo:teachAbout teachabout Binary property generation “Rico Lebrun taught visual arts at the Chouinard Art Institute and at the Disney Studios. He was influenced by Michelangelo and maintained a lifelong affinity for Goya and Picasso.” http://wit.istc.cnr.it/stlab-tools/legalo
- 35. 35 Semantic Web triplesand properties generation “Rico Lebrun taught visual arts at the Chouinard Art Institute and at the Disney Studios. He was influenced by Michelangelo and maintained a lifelong affinity for Goya and Picasso.” dbpedia:Rico_Lebrun s:teachAbout dbpedia:Visual_arts . s:teachAbout a owl:ObjectProperty ; rdfs:subPropertyOf fred:Teach; rdfs:domain wibi:Artist ; rdfs:range wibi:Art ; grounding:definedFromFormalRepresentation fred-graph:a6705cedbf9b53d10bbcdedaa3be9791da0a9e94 ; grounding:derivedFromLinguisticEvidence s:linguisticEvidence ; owl:propertyChainAxiom([ owl:inverseOf s:AgentTeach ] s:TopicTeach) . _:b2 a alignment:Cell ; alignment:entity1 s:teachAbout ; alignment:entity2 <http://purl.org/vocab/aiiso/schema#teaches> ; alignment:measure "0.846"^xsd:float ; alignment:relation "equivalence" . domain, range, subsumption linguistic and formal scope alignment to existing LOD vocabularies
- 36. 36 Evaluation tasks [7] 3 6 Tool/TaskTopics NER NE-RS TE TE-RS Senses Taxo Rel Roles Events Frames +SRL AIDA – + + – – + – – – – – Alchemy + + – + – + – + – – – Apache Stanbol – + + – – + – – – – – CiceroLite – + + + + + – + + + + DB Spotlight – + + – – + – – – – – FOX + + + + + + – – – – – FRED – + + + + + + + + + + NERD – + + – – + – – – – – Ollie – – – – – – – + – – – Open Calais + + – – – + – – – + – PoolParty KD + – – – – – – – – – – ReVerb – – – – – – – + – – – Semiosearch – – + – + – – – – – – Tagme – + + + + – – – – – – Wikimeta – + – + + + – – – – – Zemanta – + – – – + – – – – –
- 37. 37 Topic detection andOpinion holder detection [8] Sentiment propagation through frames and roles [9] Sentiment analysis “People hope that the President will be condemned by the judges”
- 38. 38 50 sentencesfrom MPQAopinion corpus1 and Europarl corpus2 100 Sentence sentiment polarity of open rated hotel reviews (positive and negative) Evaluation Task Measure Value Holder detection F1 0.95 Topic detection F1 0.68 Sub-topic detection F1 0.77 Review sentiment vs. user scores Avg. correlation 0.81 2 http://www.statmt.org/europarl/ 1 http://mpqa.cs.pitt.edu/corpora/mpqacorpus/ 3 http://www.stlab.istc.cnr.it/documents/sentilo/reviewsposneg.zip
- 39. 39 Frame-basedlinked data showsan effective representation of discourse Our ultimate goal is machine understanding, hence an important issue is the limited coverage of existing resources and their integration with factual world knowledge FrameBase [10] partially addresses this problem, starting from similar principles and intuitions STLab has develop Framester [11,12]: a general web-scale integrated resource which integrateslinguistic and world factual knowledge (see Aldo’s presentation later) Coverage and integration of linguistic and world knowledge
- 40. 40 Abstract, formalised framemodel generalised model of roles Represents all resources’ entitiesin terms of its frame semantics Links linguistic data with ontologies and facts (~43M triples) Includes FrameBase’s ReDer rules Framester
- 41. 41 Word-Frame-Disambiguation (frame detection) anyword, e.g. Shakespeare, write, alone, nicely, etc. frames evoked by word senses Outperforms Semafor and FrameBase details to come in few minutes J !!!Spoiler Warning!!! http://lipn.univ-paris13.fr/framester/en/wfd/
- 42. 42 Helping people withDementia and their carers Natural language understanding questionnaire for cognitive ability assessment speech to tag (pictures, music, events, etc.) reminiscence games and suggestions suggesting missing words understanding with partial information Current project and challenge http://www.mario-project.eu Blah blah blah blah Blah blah blah blah Blah blah blah blah Blah blah blah blah Blah blah blah blah Blah blah blah blah Blah blah blah blah Blah blah blah blah Blah blah blah blah User-Robot KB
- 43. 43 Current work: To integrateFRED and Framester for normalising results Framester-driven Ontology Alignment (part of a PhD thesis under dev) MARIO understanding component and evaluation (with datasets and PwD) Open challenge: How to combine statistical learning with our approaches? we want FRED to learn from interaction experiences we want to learn new rules and procedures, not only data (algorithm learning), and get their formalisation, explicitly Next and open issues
- 44. 44 Stupid questions areonly those that are not asked (Prof. Paolo Ciancarini)
- 45. 45 References [1] Marvin Minsky:A Framework for Representing Knowledge. MIT-AI Laboratory Memo 306, June, 1974. [2] Charles J Fillmore. Frame Semantics and the Nature of Language. Annals of the New York Academy of Sciences, 280(1):20-32, 1976. [3] Aldo Gangemi, Valentina Presutti: Towards a pattern science for the Semantic Web. Semantic Web 1(1-2): 61-68 (2010) [4] Frank van Harmelen: The Web of Data: do we understand what we build? https://sssw.org/2016/?page_id=386 [5] Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero, Andrea Giovanni Nuzzolese, Francesco Draicchio, Misael Mongiovì: Semantic Web Machine Reading with FRED. Semantic Web (To appear) [6] Valentina Presutti, Andrea Giovanni Nuzzolese, Sergio Consoli, Aldo Gangemi, Diego Regorgiato Recupero: From hyperlinks to Semantic Web properties using Open Knowledge Extraction pp. 351-378, Semantic Web, Volume 7, Number 4 / 2016.
- 46. 46 [7] Aldo Gangemi:A Comparison of Knowledge Extraction Tools for the Semantic Web. ESWC 2013: 351-366 [8] Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero: Frame-Based Detection of Opinion Holders and Topics: A Model and a Tool. IEEE Comp. Int. Mag. 9(1): 20-30 (2014) [9] Diego Reforgiato Recupero, Valentina Presutti, Sergio Consoli, Aldo Gangemi, Andrea Giovanni Nuzzolese: Sentilo: Frame-Based Sentiment Analysis. Cognitive Computation 7(2): 211-225 (2015) [10] Jacobo Rouces, Gerard de Melo, and Katja Hose. Framebase: Representing n-ary relations using semantic frames. ESWC 2015: 505-521 [11] Aldo Gangemi, Mehwish Alam, Valentina Presutti, Luigi Asprino and Diego Reforgiato Recupero: Framester: A Wide Coverage Linguistic Linked Data Hub. In Proceedings of EKAW 2016 [12] Aldo Gangemi, Mehwish Alam, Valentina Presutti: Word Frame Disambiguation: Evaluating Linguistic Linked Data on Frame Detection. LD4IE@ISWC 2016: 23-31 References cont.