Presentation is loading. Please wait.

Presentation is loading. Please wait.

Outline Super-quick review of previous talk More on NER by token-tagging –Limitations of HMMs –MEMMs for sequential classification Review of relation extraction.

Similar presentations


Presentation on theme: "Outline Super-quick review of previous talk More on NER by token-tagging –Limitations of HMMs –MEMMs for sequential classification Review of relation extraction."— Presentation transcript:

1 Outline Super-quick review of previous talk More on NER by token-tagging –Limitations of HMMs –MEMMs for sequential classification Review of relation extraction techniques –Decomposition one: NER + segmentation + classifying segments and entities –Decomposition two: NER + segmentation + classifying pairs of entities Some case studies –ACE –Webmaster

2 Quick review of previous talk

3 What is “Information Extraction” Information Extraction = segmentation + classification + association + clustering As a family of techniques: October 14, 2002, 4:00 a.m. PT For years, Microsoft Corporation CEO Bill Gates railed against the economic philosophy of open-source software with Orwellian fervor, denouncing its communal licensing as a "cancer" that stifled technological innovation. Today, Microsoft claims to "love" the open- source concept, by which software code is made public to encourage improvement and development by outside programmers. Gates himself says Microsoft will gladly disclose its crown jewels--the coveted code behind the Windows operating system--to select customers. "We can be open source. We love the concept of shared source," said Bill Veghte, a Microsoft VP. "That's a super-important shift for us in terms of code access.“ Richard Stallman, founder of the Free Software Foundation, countered saying… Microsoft Corporation CEO Bill Gates Microsoft Gates Microsoft Bill Veghte Microsoft VP Richard Stallman founder Free Software Foundation NAME TITLE ORGANIZATION Bill Gates CEOMicrosoft Bill Veghte VP Microsoft RichardStallman founder Free Soft.. * * * *

4 What is “Information Extraction” Information Extraction = segmentation + classification + association + clustering As a family of techniques: October 14, 2002, 4:00 a.m. PT For years, Microsoft Corporation CEO Bill Gates railed against the economic philosophy of open-source software with Orwellian fervor, denouncing its communal licensing as a "cancer" that stifled technological innovation. Today, Microsoft claims to "love" the open- source concept, by which software code is made public to encourage improvement and development by outside programmers. Gates himself says Microsoft will gladly disclose its crown jewels--the coveted code behind the Windows operating system--to select customers. "We can be open source. We love the concept of shared source," said Bill Veghte, a Microsoft VP. "That's a super-important shift for us in terms of code access.“ Richard Stallman, founder of the Free Software Foundation, countered saying… Microsoft Corporation CEO Bill Gates Microsoft Gates Microsoft Bill Veghte Microsoft VP Richard Stallman founder Free Software Foundation NAME TITLE ORGANIZATION Bill Gates CEOMicrosoft Bill Veghte VP Microsoft RichardStallman founder Free Soft.. * * * * via token tagging

5 Token tagging and NER

6 NER by tagging tokens Yesterday Pedro Domingos flew to New York. Yesterday Pedro Domingos flew to New York Person name: Pedro Domingos Location name: New York Given a sentence: 2) Identify names based on the entity labels person name location name background 1) Break the sentence into tokens, and classify each token with a label indicating what sort of entity it’s part of: 3) To learn an NER system, use YFCL.

7 HMM for Segmentation of Addresses Simplest HMM Architecture: One state per entity type CA0.15 NY0.11 PA0.08 …… Hall0.15 Wean0.03 N-S0.02 …… [Pilfered from Sunita Sarawagi, IIT/Bombay]

8 HMMs for Information Extraction 1.The HMM consists of two probability tables Pr(currentState=s|previousState=t) for s=background, location, speaker, Pr(currentWord=w|currentState=s) for s=background, location, … 2.Estimate these tables with a (smoothed) CPT Prob(location|location) = #(loc->loc)/#(loc->*) transitions 3.Given a new sentence, find the most likely sequence of hidden states using Viterbi method: MaxProb(curr=s|position k)= Max state t MaxProb(curr=t|position=k-1) * Prob(word=w k-1 |t)*Prob(curr=s|prev=t) 00 : pm Place : Wean Hall Rm 5409 Speaker : Sebastian Thrun … …

9 “Naïve Bayes” Sliding Window vs HMMs GRAND CHALLENGES FOR MACHINE LEARNING Jaime Carbonell School of Computer Science Carnegie Mellon University 3:30 pm 7500 Wean Hall Machine learning has evolved from obscurity in the 1970s into a vibrant and popular discipline in artificial intelligence during the 1980s and 1990s. As a result of its success and growth, machine learning is evolving into a collection of related disciplines: inductive concept acquisition, analytic learning in problem solving (e.g. analogy, explanation-based learning), learning theory (e.g. PAC learning), genetic algorithms, connectionist learning, hybrid systems, and so on. Domain: CMU UseNet Seminar Announcements FieldF1 Speaker:30% Location:61% Start Time:98% FieldF1 Speaker:77% Location:79% Start Time:98%

10 Design decisions: What are the output symbols (states) ? What are the input symbols ? Cohen => “Cohen”, “cohen”, “Xxxxx”, “Xx”, … ? 8217 => “8217”, “9999”, “9+”, “number”, … ? Sarawagi et al: choose best abstraction level using holdout set

11 What is a symbol? Ideally we would like to use many, arbitrary, overlapping features of words. S t-1 S t O t S t+1 O t +1 O t - 1 identity of word ends in “-ski” is capitalized is part of a noun phrase is in a list of city names is under node X in WordNet is in bold font is indented is in hyperlink anchor … … … part of noun phrase is “Wisniewski” ends in “-ski” Lots of learning systems are not confounded by multiple, non- independent features: decision trees, neural nets, SVMs, …

12 What is a symbol? S t-1 S t O t S t+1 O t +1 O t - 1 identity of word ends in “-ski” is capitalized is part of a noun phrase is in a list of city names is under node X in WordNet is in bold font is indented is in hyperlink anchor … … … part of noun phrase is “Wisniewski” ends in “-ski” Idea: replace generative model in HMM with a maxent model, where state depends on observations

13 What is a symbol? S t-1 S t O t S t+1 O t +1 O t - 1 identity of word ends in “-ski” is capitalized is part of a noun phrase is in a list of city names is under node X in WordNet is in bold font is indented is in hyperlink anchor … … … part of noun phrase is “Wisniewski” ends in “-ski” Idea: replace generative model in HMM with a maxent model, where state depends on observations and previous state

14 What is a symbol? S t-1 S t O t S t+1 O t +1 O t - 1 identity of word ends in “-ski” is capitalized is part of a noun phrase is in a list of city names is under node X in WordNet is in bold font is indented is in hyperlink anchor … … … part of noun phrase is “Wisniewski” ends in “-ski” Idea: replace generative model in HMM with a maxent model, where state depends on observations and previous state history

15 Ratnaparkhi’s MXPOST Sequential learning problem: predict POS tags of words. Uses MaxEnt model described above. Rich feature set. To smooth, discard features occurring < 10 times.

16 Conditional Markov Models (CMMs) aka MEMMs aka Maxent Taggers vs HMMS S t-1 StSt OtOt S t+1 O t+1 O t-1... S t-1 StSt OtOt S t+1 O t+1 O t-1...

17 Extracting Relationships

18 What is “Information Extraction” Information Extraction = segmentation + classification + association + clustering As a family of techniques: October 14, 2002, 4:00 a.m. PT For years, Microsoft Corporation CEO Bill Gates railed against the economic philosophy of open-source software with Orwellian fervor, denouncing its communal licensing as a "cancer" that stifled technological innovation. Today, Microsoft claims to "love" the open- source concept, by which software code is made public to encourage improvement and development by outside programmers. Gates himself says Microsoft will gladly disclose its crown jewels--the coveted code behind the Windows operating system--to select customers. "We can be open source. We love the concept of shared source," said Bill Veghte, a Microsoft VP. "That's a super-important shift for us in terms of code access.“ Richard Stallman, founder of the Free Software Foundation, countered saying… Microsoft Corporation CEO Bill Gates Microsoft Gates Microsoft Bill Veghte Microsoft VP Richard Stallman founder Free Software Foundation NAME TITLE ORGANIZATION Bill Gates CEOMicrosoft Bill Veghte VP Microsoft RichardStallman founder Free Soft.. * * * *

19 What is “Information Extraction” Filling slots in a database from sub-segments of text. As a task: 23rd July 2009 05:51 GMT Microsoft was in violation of the GPL (General Public License) on the Hyper-V code it released to open source this week. After Redmond covered itself in glory by opening up the code, it now looks like it may have acted simply to head off any potentially embarrassing legal dispute over violation of the GPL. The rest was theater. As revealed by Stephen Hemminger - a principal engineer with open-source network vendor Vyatta - a network driver in Microsoft's Hyper-V used open-source components licensed under the GPL and statically linked to binary parts. The GPL does not permit the mixing of closed and open- source elements. … Hemminger said he uncovered the apparent violation and contacted Linux Driver Project lead Greg Kroah-Hartman, a Novell programmer, to resolve the problem quietly with Microsoft. Hemminger apparently hoped to leverage Novell's interoperability relationship with Microsoft. NAME TITLE ORGANIZATION Stephen Hemminger Greg Kroah-Hartman Vyatta Novell Linux Driver Proj. principal engineer programmer lead

20 What is “Information Extraction” NER + Segment + Classify Segments and Entities Technique 1: 23rd July 2009 05:51 GMT Microsoft was in violation of the GPL (General Public License) on the Hyper-V code it released to open source this week. After Redmond covered itself in glory by opening up the code, it now looks like it may have acted simply to head off any potentially embarrassing legal dispute over violation of the GPL. The rest was theater. As revealed by Stephen Hemminger - a principal engineer with open-source network vendor Vyatta - a network driver in Microsoft's Hyper-V used open-source components licensed under the GPL and statically linked to binary parts. The GPL does not permit the mixing of closed and open- source elements. … Hemminger said he uncovered the apparent violation and contacted Linux Driver Project lead Greg Kroah-Hartman, a Novell programmer, to resolve the problem quietly with Microsoft. Hemminger apparently hoped to leverage Novell's interoperability relationship with Microsoft.

21 What is “Information Extraction” NER + Segment + Classify Segments and Entities Technique 1: 23rd July 2009 05:51 GMT Microsoft was in violation of the GPL (General Public License) on the Hyper-V code it released to open source this week. After Redmond covered itself in glory by opening up the code, it now looks like it may have acted simply to head off any potentially embarrassing legal dispute over violation of the GPL. The rest was theater. As revealed by Stephen Hemminger - a principal engineer with open-source network vendor Vyatta - a network driver in Microsoft's Hyper-V used open-source components licensed under the GPL and statically linked to binary parts. The GPL does not permit the mixing of closed and open- source elements. … Hemminger said he uncovered the apparent violation and contacted Linux Driver Project lead Greg Kroah-Hartman, a Novell programmer, to resolve the problem quietly with Microsoft. Hemminger apparently hoped to leverage Novell's interoperability relationship with Microsoft.

22 What is “Information Extraction” NER + Segment + Classify Segments and Entities Technique 1: 23rd July 2009 05:51 GMT Microsoft was in violation of the GPL (General Public License) on the Hyper-V code it released to open source this week. After Redmond covered itself in glory by opening up the code, it now looks like it may have acted simply to head off any potentially embarrassing legal dispute over violation of the GPL. The rest was theater. As revealed by Stephen Hemminger - a principal engineer with open-source network vendor Vyatta - a network driver in Microsoft's Hyper-V used open-source components licensed under the GPL and statically linked to binary parts. The GPL does not permit the mixing of closed and open- source elements. … Hemminger said he uncovered the apparent violation and contacted Linux Driver Project lead Greg Kroah-Hartman, a Novell programmer, to resolve the problem quietly with Microsoft. Hemminger apparently hoped to leverage Novell's interoperability relationship with Microsoft. Does not contain worksAt fact Does contain worksAt fact Does not contain worksAt fact Does contain worksAt fact

23 What is “Information Extraction” NER + Segment + Classify Segments and Entities Technique 1: As revealed by Stephen Hemminger - a principal engineer with open-source network vendor Vyatta - a network driver in Microsoft's Hyper-V used open-source components licensed under the GPL and statically linked to binary parts. The GPL does not permit the mixing of closed and open- source elements. … Does contain worksAt fact Stephen Hemminger principal engineer Microsoft Vyatta Is in the worksAt fact Is not in the worksAt fact NAME TITLE ORGANIZATION Stephen HemmingerVyatta principal engineer

24 What is “Information Extraction” NER + Segment + Classify Segments and Entities Technique 1: Because of Stephen Hemminger’s discovery, Vyatta was soon purchased by Microsoft for $1.5 billion… Does contain an acquired fact Microsoft Vyatta Is in the acquired fact: role=acquiree Is in a acquired fact: role=acquirer Stephen Hemminger Is not in the acquired fact $1.5 billion Is in the acquired fact: role=price

25 What is “Information Extraction” NER + Segment + Classify Segments and Entities Technique 1: 23rd July 2009 05:51 GMT Hemminger said he uncovered the apparent violation and contacted Linux Driver Project lead Greg Kroah-Hartman, a Novell programmer, to resolve the problem quietly with Microsoft. Hemminger apparently hoped to leverage Novell's interoperability relationship with Microsoft. Does contain worksAt fact (actually two of them) - and that’s a problem

26 What is “Information Extraction” NER + Segment + Classify EntityPairs from same segment Technique 2: 23rd July 2009 05:51 GMT Hemminger said he uncovered the apparent violation and contacted Linux Driver Project lead Greg Kroah-Hartman, a Novell programmer, to resolve the problem quietly with Microsoft. Hemminger apparently hoped to leverage Novell's interoperability relationship with Microsoft. Hemminger programmer Microsoft Novell Greg Kroah-Hartman Linux Driver Project lead

27 ACE: Automatic Content Extraction A case study, or: yet another NIST bake-off

28 About ACE http://www.nist.gov/speech/tests/ace/ and http://projects.ldc.upenn.edu/ace/ The five year mission: “develop technology to extract and characterize meaning in human language”…in newswire text, speech, and images –EDT: Develop NER for: people, organizations, geo-political entities (GPE), location, facility, vehicle, weapon, time, value … plus subtypes (e.g., educational organizations) –RDC: identify relation between entities: located, near, part-whole, membership, citizenship, … –EDC: identify events like interaction, movement, transfer, creation, destruction and their arguments

29

30 … and their arguments (entities)

31

32 Event = sentence plus a trigger word

33

34

35

36 Events, entities and mentions In ACE there is a distinction between an entity—a thing that exists in the Real World—and an entity mention—which is something that exists in the text (a substring). Likewise, and event is something that (will, might, or did) happen in the Real World, and an event mention is some text that refers to that event. –An event mention lives inside a sentence (the “extent”) with a “trigger” (or anchor) –An event mention is defined by its type and subtype (e.g, Life:Marry, Transaction:TransferMoney) and its arguments –Every argument is an entity mention that has been assigned a role. –Arguments belong to the same event if they are associated with the same trigger. The entity-mention, trigger, extent, argument are markup and also define a possible decomposition of the event- extraction task into subtask.

37 How to find events? The approach in Ahn, “Stages of event extraction”: Find all the entities and sentences –Ahn uses ground-truth labels for entities (an ACE thing) –Entities=candidate event arguments; sentences=candidate event extents; these will be classified and paired up Find the event mentions –Classify words as anchors (for event type T:S) or not: 35 classes, mostly None –Classify (event-mention,entity-mention) pairs as arguments (with role R) or not: 36 classes, mostly None Q: Why not just classify entity-mentions by Role? –Classify event mentions by modality, polarity, … –Classify (event-mention i,event-mention j ) pairs as co-referent or not. For details: see the paper!

38 The Webmaster Project: A Case Study with Einat Minkov (LTI, now Haifa U), Anthony Tomasic (ISRI) See IJCAI-2005 paper

39 Overview and Motivations What’s new : –Adaptive NLP components –Learn to adapt to changes in domain of discourse –Deep analysis in limited but evolving domain Compared to past NLP systems : –Deep analysis in narrow domain (Chat-80, SHRDLU,...) –Shallow analysis in broad domain (POS taggers, NE recognizers, NP-chunkers,...) –Learning used as tool to develop non-adaptive NLP components Details : –Assume DB-backed website, where schema changes over time No other changes allowed (yet) –Interaction: User requests (via NL email) changes in factual content of website (assume update of one tuple) System analyzes request System presents preview page and editable form version of request Key points : –partial correctness is useful –user can verify correctness (vs case for DB queries, q/a,...) => source of training data...something in between...

40 POS tags NP chunks words,... features entity1, entity2,.... email msg Shallow NLPFeature Building C C C C requestType targetRelation targetAttrib Classification newEntity1,... oldEntity1,... keyEntity1,... otherEntity1,... NER database web page templates Update Request Construction preview page user-editable form version of request confirm? LEARNER offline training data User

41 Outline Training data/corpus –look at feasibility of learning the components that need to be adaptive, using a static corpus Analysis steps: –request type –entity recognition –role-based entity classification –target relation finding –target attribute finding –[request building] Conclusions/summary

42 Training data User1 User2 User3.... Mike Roborts should be Micheal Roberts in the staff listing, pls fix it. Thanks - W On the staff page, change Mike to Michael in the listing for “Mike Roberts”.

43 Training data User1 User2 User3.... Add this as Greg Johnson’s phone number: 412 281 2000 Please add “412-281-2000” to greg johnson’s listing on the staff page.

44 Training data – entity names are made distinct User1 User2 User3.... Add this as Greg Johnson’s phone number: 412 281 2000 Please add “543-341-8999” to fred flintstone’s listing on the staff page. Modification: to make entity-extraction reasonable, remove duplicate entities by replacing them with alternatives (preserving case, typos, etc)

45 Training data User1 User2 User3.... Request1 Request2 Request3.... message(user 1,req 1) message(user 2,req 1).... message(user 1,req 2) message(user 2,req 2).... message(user 1,req 3) message(user 2,req 3)....

46 Training data – always test on a novel user? User1 User2 User3.... Request1 Request2 Request3.... message(user 1,req 1) message(user 2,req 1).... message(user 1,req 2) message(user 2,req 2).... message(user 1,req 3) message(user 2,req 3).... test train Simulate a distribution of many users (harder to learn)

47 Training data – always test on a novel request? User1 User2 User3 Request1 Request2 Request3 message(user 1,req 1) message(user 2,req 1).... message(user 1,req 3) message(user 2,req 3).... test train message(user 1,req 2) message(user 2,req 2).... Simulate a distribution of many requests (much harder to learn) 617 emails total + 96 similar ones

48 Training data – limitations One DB schema, one off-line dataset –May differ from data collected on-line –So, no claims made for tasks where data will be substantially different (i.e., entity recognition) –No claims made about incremental learning/transfer All learning problems considered separate One step of request-building is trivial for the schema considered: –Given entity E and relation R, to which attribute of R does E correspond? –So, we assume this mapping is trivial (general case requires another entity classifier)

49 POS tags NP chunks words,... features entity1, entity2,.... email msg Shallow NLPFeature Building C C C C requestType targetRelation targetAttrib newEntity1,... oldEntity1,... keyEntity1,... otherEntity1,... Information Extraction

50 Entity Extraction Results We assume a fixed set of entity types –no adaptivity needed (unclear if data can be collected) Evaluated: –hand-coded rules ( approx cascaded FST in “Mixup” language) –learned classifiers with standard feature set and also a “tuned” feature set, which Einat tweaked –results are in F1 (harmonic avg of recall and precision) –two learning methods, both based on “token tagging” Conditional Random Fields (CRF) Voted-perception discriminative training for an HMM (VP-HMM)

51 Entity Extraction Results – v2 (CV on users)

52 POS tags NP chunks words,... features entity1, entity2,.... email msg Shallow NLPFeature Building C C C C requestType targetRelation targetAttrib newEntity1,... oldEntity1,... keyEntity1,... otherEntity1,... Information Extraction

53 Entity Classification Results Entity “roles”: –keyEntity: value used to retrieve a tuple that will be updated (“delete greg’s phone number”) –newEntity: value to be added to database (“William’s new office # is 5307 WH”). –oldEntity: value to be overwritten or deleted (“change mike to Michael in the listing for...”) –irrelevantEntity: not needed to build the request (“please add.... – thanks, William”) Features: closest preceding preposition closest preceding “action verb” (add, change, delete, remove,...) closest preceding word which is a preposition, action verb, or determiner (in “determined” NP) is entity followed by ‘s

54 POS tags NP chunks words,... features entity1, entity2,.... email msg Shallow NLPFeature Building C C C C requestType targetRelation targetAttrib newEntity1,... oldEntity1,... keyEntity1,... otherEntity1,... Information Extraction

55 POS tags NP chunks words,... features entity1, entity2,.... email msg Shallow NLPFeature Building C C C C requestType targetRelation targetAttrib newEntity1,... oldEntity1,... keyEntity1,... otherEntity1,... Information Extraction Reasonable results with “bag of words” features.

56 POS tags NP chunks words,... features entity1, entity2,.... email msg Shallow NLPFeature Building C C C C requestType targetRelation targetAttrib newEntity1,... oldEntity1,... keyEntity1,... otherEntity1,... Information Extraction

57 Request type classification: addTuple, alterValue, deleteTuple, or deleteValue? Can be determined from entity roles, except for deleteTuple and deleteValue. –“Delete the phone # for Scott” vs “Delete the row for Scott” Features : –counts of each entity role –action verbs –nouns in NPs which are (probably) objects of action verb –(optionally) same nouns, tagged with a dictionary Target attributes are similar Comments: Very little data is available Twelve words of schema-specific knowledge: dictionary of terms like phone, extension, room, office,...

58 POS tags NP chunks words,... features entity1, entity2,.... email msg Shallow NLPFeature Building C C C C requestType targetRelation targetAttrib newEntity1,... oldEntity1,... keyEntity1,... otherEntity1,... Information Extraction

59 POS tags NP chunks words,... features entity1, entity2,.... email msg Shallow NLPFeature Building C C C C requestType targetRelation targetAttrib newEntity1,... oldEntity1,... keyEntity1,... otherEntity1,... Information Extraction

60 Training data User1 User2 User3.... Request1 Request2 Request3.... message(user 1,req 1) message(user 2,req 1).... message(user 1,req 2) message(user 2,req 2).... message(user 1,req 3) message(user 2,req 3)....

61 Training data – always test on a novel user? User1 User2 User3.... Request1 Request2 Request3.... message(user 1,req 1) message(user 2,req 1).... message(user 1,req 2) message(user 2,req 2).... message(user 1,req 3) message(user 2,req 3).... test train Simulate a distribution of many users (harder to learn)

62 Training data – always test on a novel request? User1 User2 User3 Request1 Request2 Request3 message(user 1,req 1) message(user 2,req 1).... message(user 1,req 3) message(user 2,req 3).... test train message(user 1,req 2) message(user 2,req 2).... Simulate a distribution of many requests (much harder to learn) 617 emails total + 96 similar ones

63 Other issues: a large pool of users and/or requests usr

64 Webmaster: the punchline

65 Conclusions? System architecture allows all schema-dependent knowledge to be learned –Potential to adapt to changes in schema –Data needed for learning can be collected from user Learning appears to be possible on reasonable time-scales –10s or 100s of relevant examples, not thousands –Schema-independent linguistic knowledge is useful F1 is eighties is possible on almost all subtasks. –Counter-examples are rarely changed relations (budget) and distinctions for which little data is available There is substantial redundancy in different subtasks –Opportunity for learning suites of probabilistic classifiers, etc Even an imperfect IE system can be useful…. –With the right interface…

66 POS tags NP chunks words,... features entity1, entity2,.... email msg Shallow NLPFeature Building C C C C requestType targetRelation targetAttrib newEntity1,... oldEntity1,... keyEntity1,... otherEntity1,... Information Extraction micro- form query DB

67

68

69 Webmaster: the Epilog (VIO) Faster for request-submitter Zero time for webmaster Zero latency More reliable (!) Tomasic et al, IUI 2006 Entity F1 ~= 84, Micro-form selection accuracy =~ 80 Used UI for experiments on real people (human-human, human-VIO)

70 Conclusions and comments Two case studies of non-trivial IE pipelines illustrate: –In any pipeline, errors propogate –What’s the right way of training components in a pipeline? Independently? How can (and when should) we make decisions using some flavor of joint inference? Some practical questions for pipeline components: –What’s downstream? What do errors cost? –Often we can’t see the end of the pipeline… How robust is the method ? –new users, new newswire sources, new upsteam components… –Do different learning methods/feature sets differ in robustness? Some concrete questions for learning relations between entities: –(When) is classifying pairs of things the right approach? How do you represent pairs of objects? How to you represent structure, like dependency parses? Kernels? Special features?


Download ppt "Outline Super-quick review of previous talk More on NER by token-tagging –Limitations of HMMs –MEMMs for sequential classification Review of relation extraction."

Similar presentations


Ads by Google