3Overview Motivations What’s New in 2014 14/08/12MotivationsThe most popular EL Trend: Collective Inference - disambiguate a set of relevant mentions simultaneously by leveraging the global topical coherence between entitiesA lot of research has been done in parallel in the Wikification community (Bunescu, 2006) - extract prominent ngrams as concept mentions, and link each concept mention to the KBOne important research direction of KBP: “Cold-start”What’s New in 2014Extend English task to Entity Discovery and Linking (full Entity Extraction + Entity Linking + NIL Clustering)Add discussion forums to Cross-lingual tracksShare some source collections and queries with regular and cold-start slot filling tracks, to investigate the role of EDL in the entire cold-start KBP pipelineProvide automatic annotations, reading list, software toolsSome recent in vivo tasks are shown here.Ratinov and Roth used d2w output to aid coreference resolution.For example, knowing that kursk can be a vessel helps link kursk to vessel.WP concepts present in a document help to make document similarity calculation more robust.Also, WP concepts are rich with information including coarse and fine grained properties that can shed light on,for example, a users intent during query formulation.
4Entity Mention Extraction It’s a version of Chicago – the standard classic Macintosh menu font, with that distinctive thick diagonal in the ”N”.Chicago was used by default for Mac menus through MacOS 7.6, and OS 8 was released midChicago VIII was one of the early 70s-era Chicago albums to catch myear, along with Chicago II.
5Clustering: Cross-doc Coreference Resolution It’s a version of Chicago – the standard classic Macintosh menu font, with that distinctive thick diagonal in the ”N”.Chicago was used by default for Mac menus through MacOS 7.6, and OS 8 was released midChicago VIII was one of the early 70s-era Chicago albums to catch myear, along with Chicago II.
6Linking: Disambiguation to KB It’s a version of Chicago – the standard classic Macintosh menu font, with that distinctive thick diagonal in the ”N”.Chicago was used by default for Mac menus through MacOS 7.6, and OS 8 was released midChicago VIII was one of the early 70s-era Chicago albums to catch myear, along with Chicago II.
7Evaluation Measures Added type matching variant into each measure 14/08/12Added type matching variant into each measureSome recent in vivo tasks are shown here.Ratinov and Roth used d2w output to aid coreference resolution.For example, knowing that kursk can be a vessel helps link kursk to vessel.WP concepts present in a document help to make document similarity calculation more robust.Also, WP concepts are rich with information including coarse and fine grained properties that can shed light on,for example, a users intent during query formulation.
14General Architecture Feedback from linking to improve extraction New ranking algorithm: Progamming with Personalized PageRank algorithm by CohenCMU (Mazaitis et al., 2014)A nice summary of the state-of-the-art ranking features by Tohoku NL (Zhou et al., 2014)
15Overall Performance: Extraction + Linking Scoring: span, type and KB ID matchSystems with > 60% NERL F1 are significantly better than others (90% confidence interval)
16Overall Performance: Extraction + Clustering Scoring: span, type and clusteringLCC and RPI systems are significantly better than others (90% confidence interval)
17Impact of Entity Mention Extraction 75%, Much lower than state-of-the-art name tagging (89%)NER: span; NERC: span_type; NERL: span_type_KBID KBIDs: docid_KBIDNER (extraction) correlates with NERL (Extraction + Linking) wellBug in IBM system
18Diagnostic Entity Linking Performance IBM is somewhere here too!High performance with perfect entity mentions (70%90%)
19Entity Types and Textual Genres Scoring: span, type and linkingEasiest: persons and discussion forum
20Clustering MeasuresB-cubed is very sensitive to mention extraction errors
21Cross-lingual Entity Linking QueryTeamB-cubed+ (%)PRFSpanishHITS178.968.473.2IBM184.081.682.8English60.364.180.677.779.1Both systems followed their English EL approachesIBM achieved similar performance with the top English EDL system (the difficulty level of queries are not comparable)Many Chinese teams chose to focus on English EDL (a cloned version in NLPCC2014 organized by PKU)Tri-lingual EDL in KBP2015
22What’s New and What Works - Or How to Make My Advisor Happy A roll-coaster-style conversation 12 hours before this presentation…R: I started to question why we are doing all of these…H: Please don’t tell me all of these are meaningless…R: Did EDL produce any new science?H: Of course! Blabla…blabla…blabla…blabla…and BlablaR: You make me happy
23Entity Linking Milestones 2006: The first definition of Wikification task (Bunescu and Pasca, 2006)2009: TAC-KBP Entity Linking launched (McNamee and Dang, 2009): Supervised learning-to-rank with diverse levels of features such as entity profiling, various popularity and similarity measures were developed (Gao et al., 2010; Chen and Ji, 2011; Ratinov et al., 2011; Zheng et al., 2010; Dredze et al., 2010; Anastacio et al., 2011): Collective Inference, Coherence measures were developed (Milne and Witten, 2008; Kulkarni et al., 2009; Ratinov et al., 2011; Chen and Ji, 2011; Ceccarelli et al., 2013; Cheng and Roth, 2013)2012: Various applications(e.g., Knowledge Acquisition (via grounding), Coreference resolution (Ratinov and Roth, 2012) and Document classification (Vitale et al., 2012; Song and Roth, 2014; Gao et al., 2014)2014: TAC-KBP Entity Discovery and Linking (end-to-end name tagging, cross-document entity clustering, entity linking): Many different versions of international evaluations were inspired from TAC-KBP; more than 130 papers have been published
24Joint Extraction and Linking Some recent work (Sil and Yates, 2013; Meij et al., 2012; Guo et al., 2013; Huang et al., 2014b) proved extraction and linking can mutually enhance each otherBosch will provide the rear axle. Robert Bosch Tool Corporation ORGParker was 15 for 21 from the field, putting up a season high while scoring nine of San Antonio’s final 10 points in regulation San Antonio Spurs ORGIBM (Sil and Florian, 2014), MSIIPL THU (Zhao et al., 2014), SemLinker (Meurs et al., 2014), UBC (Barrena et al., 2014) and RPI (Hong et al., 2014) used the properties in external KBs such as DBPedia as feedback to refine the identification and classification of name mentions.RPI system successfully corrected 11.26% wrong mentionsHITS team (Judea et al., 2014) proposed a joint approach that simultaneously solves extraction, linking and clustering using Markov Logic NetworksDocument Linking Event Extraction (Ji and Grishman, 2008)Entity Linking Relation Extraction (Chan and Roth, 2010)Toward more interactions and joint inferences between tasks Marry EDL and SF in KBP2015
25Entity Linking to Improve Relation Extraction (Chan and Roth, 2010) DavidCone,aKansasCitynativewasoriginallysignedbytheRoyalsandbrokeintomajorswithteamDavid Brian Cone (born January 2, 1963) is a former Major League Baseball pitcher. He compiled an 8–3 postseason record over 21 postseason starts and was a part of five World Series championship teams (1992 with the Toronto Blue Jays and 1996, 1998, 1999 & 2000 with the New York Yankees). He had a career postseason ERA of He is the subject of the book A Pitcher's Story: Innings With David Cone by Roger Angell. Fans of David are known as "Cone-Heads."Cone lives in Stamford, Connecticut, and is formerly a color commentator for the Yankees on the YES Network.Contents[hide]1 Early years2 Kansas City Royals3 New York MetsPartly because of the resulting lack of leadership, after the 1994 season the Royals decided to reduce payroll by trading pitcher David Cone and outfielder Brian McRae, then continued their salary dump in the 1995 season. In fact, the team payroll, which was always among the league's highest, was sliced in half from $40.5 million in 1994 (fourth-highest in the major leagues) to $18.5 million in 1996 (second-lowest in the major leagues)25
26Task-specific / Genre-specific Mention Extraction Extraction for Linking4% entity mentions included nested mentionsPosters in discussion forum should be extractedHITS (Judea et al., 2014), LCC (Monahan et al., 2014), MSIIPL THU (Zhao et al., 2014), NYU (Nguyen et al., 2014) and RPI (Hong et al., 2014) developed heuristic rules to significantly improve name tagging
27Toward Deep Understanding of Full Documents Old Query-driven Entity LinkingLimited exploration of co-occurring entity mentionsBag-of-words styleNew EDL TaskDeep representation and understanding the relations among entities in the source documentsNatural Language Understanding stylee.g., Use Abstract Meaning Representation (details in RPI’s EDL talk)
28Better Meaning Representation It was a pool report typo. Here is exact Rhodes quote: ”this is not gonna be a couple of weeks. It will be a period of days.”At a WH briefing here in Santiago, NSA spox Rhodes came with a litany of pushback on idea WH didn’t consult with Congress.Rhodes singled out a Senate resolution that passed on March 1st which denounced Khaddafy’s atrocities. WH says UN rez incorporates itBen Rhodes(Speech Writer)Go beyond sentence level
29Select Collaborators from Rich Context Source: No matter what, he never should have given Michael Jackson that propofol. He seems to think a “proper” court would have let Murray go free.Social RelationMcCain = John_McCainSarah = Sarah_PalinSarah was the nominee for Vice President in the 2008 presidential election alongside John McCainKB:The trial of Conrad Murray was the American criminal trial of Michael Jackson's personal physician, Conrad Murray.
30Select Collaborators from Rich Context Source:Mubarak, the wife of deposed Egyptian President Hosni Mubarak, …wifeFamilyKB:Suzanne Mubarak (born 28 February 1941) is the wife of former Egyptian President Hosni Mubarak…
31Select Collaborators from Rich Context Source:Hundreds of protesters from various groups converged on the state capitol in Topeka, Kansas today…Second, I have a really hard time believing that there were any ACTUAL “explosives” since the news story they link to talks about one guy getting arrested for THREATENING Governor Brownback.EmploymentPeter BrownbackSam BrownbackKB:Sam Brownback was elected Governor of Kansas in 2010 and took office in January 2011.
32Select Collaborators from Rich Context Source:AT&T coverage in GA is good along the interstates and in the major cities like Atlanta, Athens, Rome, Roswell and Albany.Part-wholeRome, GeorgiaRome, ItalyKB:At the 2010 census, Rome had a total population of 36,303, and is the largest city in Northwest [Georgia] and the 19th largest city in the state.
33Select Collaborators from Rich Context Source:Going into the big Super Tuesday, Romney had won the most votes, states and delegates, Santorum had won some contests and was second, Gingrich had only one contest.Start-position EventGeorge W. RomneyMitt RomneyKB:The Super Tuesday primaries took place on March 6. Mitt Romney carried six states, Rich Santorum carried three, and Newt Gingrich won only in his home state of Georgia.
34Graph-based NIL Entity Clustering Bad News in EL2012CUNY-BLENDER (Tamang et al., 2012) explored more than 40 clustering algorithms and found that advanced graph-based clustering algorithms did not significantly out-perform single baseline “All-in-one” clustering algorithm on the overall queries (except the most difficult ones)Good News in EDL2014LCC (Monahan et al., 2014) proved that graph partition based algorithm achieved significant gains.
36Name Tagging: “Old” Milestones YearTasks & ResourcesMethodsF-MeasureExample References1966-First person name tagger with punch card30+ decision tree type rules(Borkowski et al., 1966)1998MUC-6MaxEnt with diverse levels of linguistic features97.12%(Borthwick and Grishman, 1998)2003CONLLSystem combination;Sequential labeling with Conditional Random Fields89%(Florian et al., 2003; McCallum et al., 2003; Finkel et al., 2005)2006ACEDiverse levels of linguistic features, Re-ranking, joint inference~89%(Florian et al., 2006; Ji and Grishman, 2006)Our progress compared to 1966:More data, a few more features and more fancy learning algorithmsNot much active work after ACE because we tend to believe it’s a solved problem…
37Cross-genre Name Tagging Experiments on ACE2005 data
38What’s Wrong?Name taggers are getting old (trained from 2003 news & test on 2012 news)Genre adaptation (informal contexts, posters)Revisit the definition of name mention – extraction for linkingOld unsolved problemsIdentification: “Asian Pulp and Paper Joint Stock Company , Lt. of Singapore”Classification: “FAW has also utilized the capital market to directly finance,…” (FAW = First Automotive Works)Potential Solutions for QualityWord clustering, Lexical Knowledge Discovery (Brown, 1992; Ratinov and Roth, 2009; Ji and Lin, 2010)Feedback from Linking, Relation, Event (Sil and Yates, 2013; Li and Ji, 2014)
39Remaining Challenges for Linking Popularity biasKnowledge gap between source and KBCommonsense KnowledgePotential SolutionsDeep knowledge acquisition and representation (e.g., AMR)Better graph search alignment algorithmsMake more people excited about Chinese and Spanish by providing more resources Tri-lingual EDL in KBP2015
40Popularity Bias If you are called Michael Jordan… Quite impressive, bottleneck: adding more sophisticated contextual features does not help muchWe do not want to level off here
41A Little Better…Quite impressive, bottleneck: adding more sophisticated contextual features does not help muchWe do not want to level off here
42Knowledge Gap between Source and KB Source: breaking news/new information/rumorsKB: bio, summary, snapshot of lifeChristies denial of marriage privledges to gays will alienate independents and his “I wanted to have the people vote on it” will ring hollow.Christie has said that he favoured New Jersey's law allowing same-sex couples to form civil unions, but would veto any bill legalizing same-sex marriage in New JerseyTranslation out of hype-speak: some kook made threatening noises at Brownback and go arrestedSamuel Dale "Sam" Brownback (born September 12, 1956) is an American politician, the 46th and current Governor of Kansas.Man Accused Of Making Threatening Phone Call To Kansas Gov. Sam Brownback May Face Felony ChargeConnect/SortBackground KnowledgeLong long time ago there was a fight between MT and distillation; Every one complains about MT; but most complaints are from distillation people…because…We should be ‘guided’ by each other, then we can collaborate and benefit from each other.…MT …a few names…. Not using ie in approriate way… 50% names are not translated correctly so it affects ie performace.
43Commonsense Knowledge During talks in Geneva attended by William J. Burns Iran refused to respond to Solana’s offers.William_Joseph_Burns (1956- )William_J._Burns ( )
44Conclusions and Looking Forward The new EDL task has attracted much interests from the KBP community and produced some interesting research problems and new directionsKBP2015Improve the annotation guideline and annotation quality of the training and evaluation data setsDevelop more open sources, data and resources for Spanish and Chinese EDLEncourage researchers to re-visit the entity mention extraction problem in the new cold-start KBP settingPropose a new tri-lingual EDL task on a source collection from three languages: English, Chinese and SpanishInvestigate the impact of EDL on the end-to-end cold-start KBP framework; joint inference between EDL and SF