1. Overview of Entity Discovery and Linking Tasks at KBP2014
Heng Ji (RPI)
Joel Nothman, Ben Hachey (Univ. of Sydney)
Thanks to KBP2014 Organizing Committee

2. Goals and The Task

3. Overview Motivations What’s New in 2014
14/08/12
Motivations
The most popular EL Trend: Collective Inference - disambiguate a set of relevant mentions simultaneously by leveraging the global topical coherence between entities
A 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 KB
One important research direction of KBP: “Cold-start”
What’s New in 2014
Extend English task to Entity Discovery and Linking (full Entity Extraction + Entity Linking + NIL Clustering)
Add discussion forums to Cross-lingual tracks
Share 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 pipeline
Provide automatic annotations, reading list, software tools
Some 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.

4. Entity 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 mid
Chicago VIII was one of the early 70s-era Chicago albums to catch my
ear, along with Chicago II.

5. Clustering: 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 mid
Chicago VIII was one of the early 70s-era Chicago albums to catch my
ear, along with Chicago II.

6. Linking: 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 mid
Chicago VIII was one of the early 70s-era Chicago albums to catch my
ear, along with Chicago II.

7. Evaluation Measures Added type matching variant into each measure
14/08/12
Added type matching variant into each measure
Some 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.

10. CEAF (Luo, 2005)
Idea: a mention or entity should not be credited more than once
Formulated as a bipartite matching problem
A special ILP problem
Efficient algorithm: Kuhn-Munkres

12. Participants
EDL: 20 teams, 75 runs; EL: 17 teams, 55 runs

13. The Results

14. General 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)

15. Overall Performance: Extraction + Linking
Scoring: span, type and KB ID match
Systems with > 60% NERL F1 are significantly better than others (90% confidence interval)

16. Overall Performance: Extraction + Clustering
Scoring: span, type and clustering
LCC and RPI systems are significantly better than others (90% confidence interval)

17. Impact 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_KBID
NER (extraction) correlates with NERL (Extraction + Linking) well
Bug in IBM system

18. Diagnostic Entity Linking Performance
IBM is somewhere here too!
High performance with perfect entity mentions (70%90%)

19. Entity Types and Textual Genres
Scoring: span, type and linking
Easiest: persons and discussion forum

20. Clustering Measures
B-cubed is very sensitive to mention extraction errors

21. Cross-lingual Entity Linking
Query
Team
B-cubed+ (%) P R F
Spanish
HITS1
78.9
68.4
73.2
IBM1
84.0
81.6
82.8
English
60.3
64.1
80.6
77.7
79.1
Both systems followed their English EL approaches
IBM 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

22. What’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 Blabla
R: You make me happy

23. Entity 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

24. Joint 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 other
Bosch will provide the rear axle.  Robert Bosch Tool Corporation  ORG
Parker 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  ORG
IBM (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 mentions
HITS team (Judea et al., 2014) proposed a joint approach that simultaneously solves extraction, linking and clustering using Markov Logic Networks
Document 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

25. Entity Linking to Improve Relation Extraction (Chan and Roth, 2010)
David
Cone , a
Kansas
City
native
was
originally
signed by
the
Royals
and
broke
into
majors
with
team
David 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.[1]
Contents
[hide]
1 Early years
2 Kansas City Royals
3 New York Mets
Partly 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

26. Task-specific / Genre-specific Mention Extraction
Extraction for Linking
4% entity mentions included nested mentions
Posters in discussion forum should be extracted
HITS (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

27. Toward Deep Understanding of Full Documents
Old Query-driven Entity Linking
Limited exploration of co-occurring entity mentions
Bag-of-words style
New EDL Task
Deep representation and understanding the relations among entities in the source documents
Natural Language Understanding style
e.g., Use Abstract Meaning Representation (details in RPI’s EDL talk)

28. Better 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 it
Ben Rhodes
(Speech Writer)
Go beyond sentence level

29. Select 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 Relation
McCain = John_McCain
Sarah = Sarah_Palin
Sarah was the nominee for Vice President in the 2008 presidential election alongside John McCain
KB:
The trial of Conrad Murray was the American criminal trial of Michael Jackson's personal physician, Conrad Murray.

30. Select Collaborators from Rich Context
Source:
Mubarak, the wife of deposed Egyptian President Hosni Mubarak, …
wife
Family
KB:
Suzanne Mubarak (born 28 February 1941) is the wife of former Egyptian President Hosni Mubarak…

31. Select 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.
Employment
Peter Brownback
Sam Brownback
KB:
Sam Brownback was elected Governor of Kansas in 2010 and took office in January 2011.

32. Select 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-whole
Rome, Georgia
Rome, Italy
KB:
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.

33. Select 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 Event
George W. Romney
Mitt Romney
KB:
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.

34. Graph-based NIL Entity Clustering
Bad News in EL2012
CUNY-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 EDL2014
LCC (Monahan et al., 2014) proved that graph partition based algorithm achieved significant gains.

35. Remaining Challenges

36. Name Tagging: “Old” Milestones
Year
Tasks & Resources
Methods
F-Measure
Example References
1966 -
First person name tagger with punch card
30+ decision tree type rules
(Borkowski et al., 1966)
1998
MUC-6
MaxEnt with diverse levels of linguistic features
97.12%
(Borthwick and Grishman, 1998)
2003
CONLL
System combination;
Sequential labeling with Conditional Random Fields
89%
(Florian et al., 2003; McCallum et al., 2003; Finkel et al., 2005)
2006
ACE
Diverse 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 algorithms
Not much active work after ACE because we tend to believe it’s a solved problem…

37. Cross-genre Name Tagging
Experiments on ACE2005 data

38. What’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 linking
Old unsolved problems
Identification: “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 Quality
Word 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)

39. Remaining Challenges for Linking
Popularity bias
Knowledge gap between source and KB
Commonsense Knowledge
Potential Solutions
Deep knowledge acquisition and representation (e.g., AMR)
Better graph search alignment algorithms
Make more people excited about Chinese and Spanish by providing more resources  Tri-lingual EDL in KBP2015

40. Popularity Bias If you are called Michael Jordan…
Quite impressive, bottleneck: adding more sophisticated contextual features does not help much
We do not want to level off here

41. A Little Better…
Quite impressive, bottleneck: adding more sophisticated contextual features does not help much
We do not want to level off here

42. Knowledge Gap between Source and KB
Source: breaking news/new information/rumors
KB: bio, summary, snapshot of life
Christies 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 Jersey
Translation out of hype-speak: some kook made threatening noises at Brownback and go arrested
Samuel 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 Charge
Connect/Sort
Background Knowledge
Long 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.

43. Commonsense 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 ( )

44. Conclusions and Looking Forward
The new EDL task has attracted much interests from the KBP community and produced some interesting research problems and new directions
KBP2015
Improve the annotation guideline and annotation quality of the training and evaluation data sets
Develop more open sources, data and resources for Spanish and Chinese EDL
Encourage researchers to re-visit the entity mention extraction problem in the new cold-start KBP setting
Propose a new tri-lingual EDL task on a source collection from three languages: English, Chinese and Spanish
Investigate the impact of EDL on the end-to-end cold-start KBP framework; joint inference between EDL and SF

45. We can do it!