1. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html CSC 9010: Text Mining Applications Fall, 2012 ANNIE Introduction Dr. Paula Matuszek Paula.Matuszek@gmail.com

2. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Recap l The goal of information extraction is to pull some well-defined information out of a large corpus of unstructured documents and put it in a more structured form, for easier access and understandability. l Typically you have –a domain model –a knowledge model –an extraction engine

3. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Examples l Some examples of information extraction in use: –Watson: http://www.youtube.com/watch?v=WFR3lOm_xhE&feature=player_detailpage http://www.youtube.com/watch?v=WFR3lOm_xhE&feature=player_detailpage –I2EOnDemand –ANNIE demo: http://services.gate.ac.uk/annie/ http://services.gate.ac.uk/annie/ –The MUC and TREC conferences sponsored by the Information Technology Laboratory of the National Institute of Standards (NIST)MUCTREC –The TIPSTER program of DARPATIPSTER

4. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Watson Information Sources l Software is built on top of UIMA: unstructured information management application: framework built by IBM and now open-source. l The information corpus was downloaded and indexed offline; no web access during the game. l For the game, Watson had access to 200 million pages of structured and unstructured content consuming four terabytes of disk storage, including the full text of Wikipedia. (http://en.wikipedia.org/wiki/Watson_(computer) )http://en.wikipedia.org/wiki/Watson_(computer) l Corpus was developed from a large variety of text sources: –baseline from wikipedia, Project Gutenberg, newspaper articles, thesauri, etc. –extend with web retrieval, extract potentially relevant text “nuggets”, score for informative, merge the best into corpus l Primary corpus started as unstructured text, not semantically tagged. l About 2% of Jeopardy! answers can be looked up directly. l Also leverages semistructured and structured sources such as Wordnet and Yago.

5. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html MUC tracks l MUC-1 (1987), MUC-2 (1989): Naval operations messages. l MUC-3 (1991), MUC-4 (1992): Terrorism in Latin American countries. l MUC-5 (1993): Joint ventures and microelectronics domain. l MUC-6 (1995): News articles on management changes. l MUC-7 (1998): Satellite launch reports.

6. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html TREC Tracks l Focus is information retrieval, not just information extraction l Ongoing: find them at http://trec.nist.gov/tracks.htmlhttp://trec.nist.gov/tracks.html l Some of the 2012 tracks: –Crowdsourcing Track –Knowledge Base Acceleration Track –Legal Track –Medical Records Track –Microblog Track l Some earlier tracks –Entity Track –Chemical IR Track –Genomics Track

7. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Knowledge-Based Approaches l Systems like GATE and I2E use an approach based in natural language processing and modeling knowledge –domain model –knowledge model l There are also machine-learning approaches using classifiers and sequence models l And, of course, hybrid approaches. GATE includes some machine-learning based tools (not in ANNIE)

8. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Domain Model l Terms: enumerated strings which are members of some class l Classes: Categories of terms, such as “locations”, “proteins”, “diseases Both are often organized into an ontology l Extraction rules

9. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Terms, Classes, Ontologies l I2EOnDemand has a rich ontology in the medical domain; we used it for searching l In ANNIE these are represented by gazetteer lists and by an index file which describes all the gazetteers, including their major type and possibly minor type and language. l GATE also has a number of ontology plugins and tools

10. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Domain Rules l LHS matches some pattern in the domain, RHS does something l In ANNIE, RHS typically adds an annotation l In I2EOnDemand –tag or annotate members of classes –identify and extract various kinds of relations

11. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Knowledge Model l What you’re trying to extract l Can be pretty simple and generic: –tuples of the form entity-relation-entity –entity:class relations l Can be more detailed and specific: Org NameVillanova University Org AliasNova, Villanova Org Description“The local university” Org TypeEducational Institution Org LocaleVillanova, PA

12. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Knowledge Model in ANNIE l The knowledge model isn’t specified explicitly; it can basically be considered as all of the annotations which the various processing resources can produce. Each processing resource has an implicit knowledge model l Additional models are defined in JAPE, which can create additional annotations.

13. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Extraction Engine l Tool which applies rules to text and extracts matches –Tokenizer –Part of Speech (POS) Tagger –Term and class tagger –Rule engine: match LHS, execute RHS l Rule engine is iterative l May include an interactive component which is essentially a query engine against already extracted information

14. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html ANNIE/GATE Extraction Engine l The entire GATE system can be considered as an extraction engine (although it does a lot more) l Most of the processing resources in ANNIE and many others available in CREOLE are specific extraction engines l Some systems (eg, AeroText, OpenCalais) make an explicit distinction among the domain model, the knowledge model, and the extraction engine. l The distinction in ANNIE is less clear

15. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html On to ANNIE: l A family of Processing Resources for language analysis included with GATE l Stands for A Nearly-New Information Extraction system. l Using finite state techniques to implement various tasks: tokenization, semantic tagging, verb phrase chunking, and so on. l (LaSIE is the forerunner of ANNIE, focused specifically on information extraction for the TREC conferences)

16. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html ANNIE IE Modules http://gate.ac.uk/sale/tao/splitch6.html#http://gate.ac.uk/sale/tao/splitch6.html#chap:annie

17. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html ANNIE Standard Components l These are what is loaded when you load ANNIE and run the default application –Document Reset –Tokenizer –Gazetteer: lists of entities –Sentence Splitter/Regex sentence splitter –Part of Speech Tagger –Named Entity Transducer –Orthomatcher

18. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Document Reset l Task: reset a document to its original state. Releases old annotations for garbage collection. l Parameters: –annotationTypes: specify annotations to remove. Default is all. –setsToKeep: –setsToRemove: –keepOriginalMarkupsAS: Boolean.

19. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html ANNIE Component: Tokenizer l Task: split text into simple tokens l In ANNIE, used as one piece of the English Tokenizer l Five types of tokens, some of which have attributes or subtypes l Uses tokenizer rules –left hand side (LHS): pattern to be matched –right hand side (RSH): action to be taken

20. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Default Token Types l Token Types. All have attributes string and length l Tokens –word. Any contiguous set of upper or lowercase letters, including a hyphen. –orthography attribute (orth): upperInitial, allCaps, lowerCase, mixedCaps –number. Any combination of successive digits. –symbol. Currency symbols, ^, +, =, etc.. –symbolkind attribute: currency –punctuation. –position attribute (position) startpunct, endpunct –subkind attribute (subkind) dashpunct l SpaceTokens –space. any non-control character –control. any control character

21. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Tokenizer Rule l Operations used on the LHS: – | (or) – * (0 or more occurrences) – ? (0 or 1 occurrences) – + (1 or more occurrences) l The RHS uses ’;’ as a separator, and has the following format: {LHS} > {Annotation type};{attribute1}={value 1};...;{attribute n}={value n}

22. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Example Tokenizer Rule –"UPPERCASE_LETTER" "LOWERCASE_LET TER"* –> –Token;orth=upperInitial;kind=word; –The sequence must begin with an uppercase letter, followed by zero or more lowercase letters. This sequence will then be annotated as type “Token”. The attribute “orth” (orthography) has the value “upperInitial”; the attribute “kind” has the value “word”.

23. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html English Tokenizer l Task: adapt generic tokenizer for POS tagger by dealing with constructs involving apostrophes –don’t --> do + n’t –you’ve --> you + ‘ve l Uses a JAPE transducer: Java Annotation Patterns Engine. –LHS: annotation pattern description –RHS: annotation manipulation statement l If you’re going to use the POS tagger, always use this tokenizer

24. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html ANNIE Component: Gazetteer l Task: identify entity names based on lists –Located in /plugins/ANNIE/resources/gazetee r –defined in lists.def, which gives name, major type, minor type, language l Example lists.def entries: –airports.lst:location:airport –city.lst:location:city –festival.lst:date:festival –day.list:date:day

25. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Gazetteer lists l The gazetteer lists used are plain text files, with one entry per line. l Typical lists include –named entities, such as locations, organizations, dates, names, –grammatical entities such as determiners –components of entities, such location prefixes –anything else that can usefully be enumerated l Don’t always have a minor type or language. Many are one-offs. (spur_ident)

26. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Gazetteer Parameters l Init-time parameters –listsURL: index file. Default is lists.def –encoding: default is UTF-8 –gazetteerFeatureSeparator. Not required. –caseSensitive (Boolean). Default is true. l Run-time parameters –document to process –annotationSetName: what to call the Lookup annotation set. Not required. –wholeWordsOnly: Default is true –longestMatchOnly: Default is true. EG: Amazon UK

27. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Gazetteer Editor l You can add or modify –the name of a list –the major and minor categories in the list –an entry in the list l You can delete a list by right-clicking the name l You can also add a new list l Or edit everything outside of GATE with a text editor.

28. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html ANNIE Component: Sentence Splitter l Task: just what it says: segments the text into sentences. l The splitter uses a gazetteer list of abbreviations to help distinguish sentence-marking full stops from other kinds. l This module is required for the POS tagger.

29. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html POS Tagger l Modified version (Hepple) of the Brill tagger, probably the best-known of the POS taggers –produces a POS tag as an annotation on each word or symbol –Uses a default lexicon and rule set –alternate lexicons for all upper-case and all lower-case corpora. l Must run English Tokenizer and Sentence Splitter first

30. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Partial List of Hepple (Penn treebank) Tags CC - coordinating conjunction: ‘and’, ‘but’, ‘nor’, ‘or’, ‘yet’, plus, minus, less. CD - cardinal number IN - preposition or subordinating conjunction JJ - adjective: Hyphenated compounds that are used as modifiers; happy-go-lucky. JJR - adjective - comparative: Adjectives with the comparative ending ‘-er’’. JJS - adjective - superlative: Adjectives with the superlative ending ‘-est’ (and ‘worst’)’. NN - noun - singular or mass NNS - noun - plural NP - proper noun - singular NPS - proper noun - plural POS - possessive ending: Nouns ending in ‘’s’ or ‘’’. PP - personal pronoun RB - adverb: most words ending in ‘-ly’. Also ‘quite’, ‘too’, ‘very’, others RBR - adverb - comparative: adverbs ending with ‘-er’ with a comparative meaning. RBS - adverb - superlative SYM - symbol: technical symbols or expressions that aren’t English words. UH - interjection: Such as ‘my’, ‘oh’, ‘please’, ‘uh’, ‘well’, ‘yes’. VBD - verb - past tense VBG - verb - gerund or present participle VBN - verb - past participle VBP - verb - non-3rd person singular present VB - verb - base form: subsumes imperatives, infinitives and subjunctives. VBZ - verb - 3rd person singular present

31. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Example Lexicon Entries l '30s CD NNS l & CC SYM l 1995-1999 CD l Announcement NN l Figuring VBG l Frequently RB l... l A total of over 17,000 entries

32. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Brill Tagger l A Brill tagger starts by assigning all the known words from the lexicon l It next assigns NNP to capitalized unknown words and NN to everything else unknown. l Finally, a bunch of replacement rules change the assignment based on various features and context.

33. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Example Brill Tagger Rules l replace(pos 'NN' 'JJ') # [suffix#less#[0]] –"replace tag NN with JJ if the word in question ends in "less"". l replace(pos 'VB' 'NN') # [canHave#'NN'#[0] pos#'DT'#[~1]] –"replace tag VB with NN if the the word in question can have tag NN (according to the lexicon) and if the previous word is tagged DT" From http://www.ling.gu.se/~lager/mogul/brill-tagger/index.htmlhttp://www.ling.gu.se/~lager/mogul/brill-tagger/index.html

34. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html LOTS of Parameters l Init-Time: all optional –encoding - encoding to be used for reading rules and lexicons –lexiconURL - The URL for the lexicon file –rulesURL - The URL for the ruleset file l Run-time: –document - The document to be processed. Required –inputASName - Input annotation set. Optional –outputASName - Output annotation set. Optional –baseTokenAnnotationType - name of annotation type for tokens ( default = Token). Required. –baseSentenceAnnotationType - name of annotation type for sentences ( default = Sentence). Required. –outputAnnotationType - default = Token. Required. –failOnMissingInputAnnotations - Default is true.

35. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Named Entity Transducer l Task: find terms that suggest entities l Hand-crafted grammars define patterns over the annotations l Written in JAPE l Doesn’t require that you run anything else, but doesn’t do much if you don’t already have annotations. l Adds new token types

36. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Required Parameters l Initialization –encoding. default is UTF-8 –grammar. default is /plugins/ANNIE/resources/N E/main.jape (which loads a bunch more) l Runtime –Corpus name (will default if there’s only one)

37. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Example JAPE rules Phase:Unknown Input: Location Person Date Organization Lookup Rule: Known Priority: 100 ( {Location}| {Person}| {Date}| {JobTitle}):known --> {} Rule:Unknown Priority: 50 ( {Token.category == NNP}) :unknown --> :unknown.Unknown = {kind = "PN", rule = Unknown} (This is only a part of the actual rules)

38. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Orthomatcher l Task: add co-reference information to Named Entities based on orthographic information. In a typical text, a NE may be referred to multiple times, with abbreviations and acronyms –Creates match lists for tagged NEs –May assign an entity type to previously unclassified entities –Won’t reassign already classified entities l Without NE Transducer annotations doesn’t actually do anything.

39. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Required Parameters l Required Init-time –definitionFileURL. Default is /plugins/ANNIE/resources/othomatc her/listsNM.def. –encoding. Default is UTF-8. –minimumNicknameLikehihood: default is 0.5.. l Run-time –corpus or document –Can also have: AnnotationTypes: list of types to be processed. Default: Organization, Person, Location, Date. Not required.

40. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Co-reference Editor l Can modify the reference chains within a document –Delete an existing member of the chain –Add a new item to a chain l This will change all relevant chains: adding an item to a chain will change the chain for all the items in it This will not change NE types or other annotations; it doesn’t propagate.

41. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Some Additional ANNIE Modules l These modules are not included in the default ANNIE load, but they are available in processing resources –Morphological analyzer (stemmer). Add “root” annotation –Pronomial Coreference. Add “coreference” annotation l May need to load tools from CREOLE manager first

42. ©2012 Paula Matuszek GATE and ANNIE Information taken primarily from the GATE user manual, gate.ac.uk/sale/tao, and GATE training materials, http://gate.ac.uk/wiki/training-materials-2011.htmlhttp://gate.ac.uk/wiki/training-materials-2011.html Summary l The default ANNIE application uses a sequence of processing resources to create annotations over unstructured text l The tokenizer, sentence splitter, POS tagger and orthomatcher are (mostly) domain-independent l The gazetteer lists and Named Entity Transducer are domain-dependent; ANNIE comes with a reasonably good default set. l The domain information is largely captured in gazetteer lists and JAPE rules.