natural language processing applied to archival description of textual e-records william underwood...
TRANSCRIPT
Natural Language Processing Natural Language Processing Applied to Applied to
Archival Description Archival Description of Textual E-recordsof Textual E-records
William UnderwoodGeorgia Tech Research Institute
Atlanta, Georgia
WVU/NETL/ERA Workshop on Digital Preservation of Complex Engineering Data
WVU NRCCE, Morgantown, West VirginiaApril 20-21, 2009
OverviewOverview
Archival DescriptionMethod for extracting metadata from
textual e-recordsUse of the metadata in archival
descriptionNext Steps
Archival DescriptionArchival Description
Archival Description includes:◦The titling of records that do not have titles◦The summary of the content of records, folders
of records and series of records.◦When time allows, the creation of other finding
aids such as subject indexes to record series.
Archival Description:Archival Description:Research MotivationResearch Motivation
Archivists cannot describe a series until the record series has been manually read and reviewed. ◦ With increasing volumes of e-records, it may be decades, even
centuries, before new acquisitions are described. In responding to FOIA requests, Archivists need to be able
to search collections of e-records with high precision and recall. ◦ However, at the time of responding to FOIA requests, archivists
have not read all of the records, so cannot index the records and search on document types, dates of records, author’s and addressee’s names and the topics of records.
◦ The results set of a query is a list of file names, not record titles and summaries of content
Archival Description: Archival Description: Item Scope and Content NoteItem Scope and Content Note
Descriptions of records include names of author(s) and addressees, topics, actions and sometimes dates.
Example of an item (record) description from NARA’s Archival Research Catalog (ARC)
This letter was typewritten by President George H. W. Bush and addressed to his children: George, Jeb, Neil, Marvin, and Doro. He expresses his happiness at their Christmas celebration held at Camp David, then writes concerning his conflicted feelings as he prepares for the possibility of war with Iraq.
A Method for Extracting Metadata for A Method for Extracting Metadata for Archival DescriptionArchival Description
Input: Textual Document
1. Information Extraction2. Document Type Recognition3. Speech Act Transducer4. Discourse Analysis for Topic Recognition
Output: [document(e1), author(e1, S), addressee(e1, H), act(e1 F(P)), topic(e1, T), date(e1, D)]
Information Extraction: MethodInformation Extraction: Method
Information extraction (semantic tagging) is a technology used to identify and annotate semantic categories in text (e.g. names of persons, organizations and locations, job titles, dates).
1. Document Reader2. English Tokenizer3. Wordlist Lookup + enhanced wordlists4. Sentence Splitter 5. Hepple POS Tagger + lexicon6. Semantic Tagger + Named Entity Rules
Information Extraction: Information Extraction: Wordlist LookupWordlist Lookup
Person_female_first.lst (8263)Person_female_first_ambig.lst (117)Person_male_first.lst (3704)Person_male_first_ambig.lst (1,117)Person_surname.lst (83,805)Person_surname_ambig.lst (6,802)Person_headofstate_90.lst (478)Location_city_US.lst (33,017)Location_city_us_ambig.lst (5,478)Location_foreign_city.lst (3802)
Java Annotation Pattern Engine Java Annotation Pattern Engine (JAPE) Rules(JAPE) Rules
Annotated Person Names Annotated Person Names and Job Titlesand Job Titles
Information Extraction: Information Extraction: PerformancePerformance
Document TypesDocument Types
AgendaBar ChartBiographyBriefing MemoDecision MemoCorrespondenceDiaryExecutive OrderInformation MemoJob ApplicationList of Candidates for Federal
OfficeMailing ListMemoMinutes of MeetingNational Security Directive
(NSD)
NewsletterNomination to Federal OfficeNotesPresidential StatementPress Pool ReportPress ReleaseReferral MemoResumeScheduleSignature MemoSituation ReportSummaryTranscript of SpeechTelephone Call
RecommendationTranscript of News Conference
Document Type RecognitionDocument Type Recognition
Input: Annotated text from Information Extractor
1. Intellectual Element Annotator + Intellectual Element Rules
2. SUPPLE Parser/Interpreter + Document Type Grammars augmented with Semantics
3. Extract MetadataOutput: [document(e1), author(e1, S),
addressee(e1, H), topic(e1, T), date(e1, D)]
Document Types:Document Types:Intellectual Element RecognitionIntellectual Element Recognition
Document Types: Grammar for the Document Types: Grammar for the Structure of a MemorandumStructure of a Memorandum
Document Types: Grammar for Document Types: Grammar for Memorndum with Semantic RulesMemorndum with Semantic Rules
Parse Tree and Semantics Parse Tree and Semantics of a Documentof a Document
Extracted Metadata andExtracted Metadata andItem DescriptionItem Description
Document_Type = memoDate = April 27, 1992Author = SAM SKINNERAddressee = EDE HOLIDAYTopic = California
Earthquake
A memorandum dated April 27, 1992 from EDE Holiday to Sam Skinner regarding California Earthquake.
Speech Act TransducerSpeech Act Transducer
1. Annotation of Explicit Speech Acts2. Annotation of Implicit Speech Acts3. Annotation of Speech Acts Indicated by Text
Structure4. Annotation of Indirect Speech Acts5. Annotation of the Primary Speech Acts
Speech Acts
Performative verb - Verb whose action is accomplished merely by saying it or writing it.
I recommend that you attend the conference. Illocutionary force of a message.
recommend Propositional content of a message
you attend the conference An explicit performative sentence is a sentence in which the
illocutionary force is made explicit by naming the force.I promise to be there
An implicit performative sentence is a sentence in which the illocutionary force is not made explicit by naming the force.
I shall be there
Speech Acts: Implicit
Declarative, imperative and interrogative sentences also express speech acts.
Declarative (state)◦You completed the report.
Imperative (request)◦Please, complete the report.
Interrogative (ask)◦Did you complete the report?
Speech Acts
An indirect speech act is a speech act that is performed indirectly by way of performing another.
Can you pass the salt? (ask)in the appropriate context means
Please, pass the salt. (request)Textual structure can also indicate
illocutionary force.Example: a section heading RECOMMENDATIONS can
indicate the sentences in a section have the illocutionary force recommend.
Speech Acts in Presidential Speech Acts in Presidential RecordsRecords
assert, deny, state, declare(1), tell(1), report, advise(1), remind, inform, certify(1), agree(1), acknowledge, praise(1), commit, pledge, direct, request, ask(1), ask(2), urge, encourage, invite, order(1), prohibit, suggest(2), propose, recommend, declare(2), resign, confirm, nominate, appoint, authorize, pray, terminate, veto, approve(1), disapprove, revoke, mourn, congratulate, thank, apologize, and welcome(2).
concur, salute, amend, counsel, welcome(1), tender(2), call on, block, retire, proclaim, delegate, designate, determine, find, reject(2), endorse, appreciate, regret, trust(1) , believe, want, desire, and intend.
Uses of Extracted Metadata Uses of Extracted Metadata in Automatic Descriptionin Automatic Description
Signature Memorandum from Boyden Gray to the President recommending the nomination of Ronald B. Leighton to be a US District Judge.
Letter from President Bush to President Mikhail Gorbachev suggesting an informal meeting.
Memorandum from President Bush to Boyden Gray requesting an analysis of the War Powers Resolution.
Letter from Susan Black to President Bush expressing appreciation for nomination and commitment to serve.
Referral Memorandum from Sally Kelley to FEMA requesting appropriate action to a letter from Beryl Anthony to the President.
Next StepsNext Steps
Inducing grammars for documentary form from samples
Create rules for annotating implicit speech acts and speech acts indicated by textual structure.
Evaluate performance of Speech act recognition method
Recognition of the topics of sentencesDiscourse Analysis to identify primary topic(s) of
recordsGenerate item, folder and series descriptions and
evaluate the method
Additional InformationAdditional Information
Website: perpos.gtri.gatech.edu
W. Underwood and S. Isbell, Semantic Annotation of Presidential E-Records, Technical Report ITTL/CSITD 08-01, May 2008
W. Underwood and S. Laib. Automatic Recognition of Documentary Forms, Technical Report ITTL/CSITD 08-02, May 2008
W. Underwood. Recognizing Communication Acts in Presidential E-Records. Technical Report ITTL/CSITD 08-03, October 2008