1 / 48

Linguistic Research And The CLARIN Infrastructure Jan Odijk

Linguistic Research And The CLARIN Infrastructure Jan Odijk Digital Humanities Lecture, Utrecht 23 Oct 2012. Introduction Basic Facts & Research Questions Do the Research Consult Grammars Select from relevant data from multiple sources Apply tools to enrich data Analyze the data

garciajoyce
Download Presentation

Linguistic Research And The CLARIN Infrastructure Jan Odijk

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Linguistic Research And The CLARIN Infrastructure Jan Odijk Digital Humanities Lecture, Utrecht 23 Oct 2012

  2. Introduction Basic Facts & Research Questions Do the Research Consult Grammars Select from relevant data from multiple sources Apply tools to enrich data Analyze the data Conclusions Overview

  3. Supposeyou’re a linguistic researcher in 1980 (no internet, no computers,…) And librarieswouldnotexist…. I am a linguistic researcher in 2012 Butnoinfrastructurefor data and tools exists! thoughthere are many data and tools CLARIN has as itsmain goal to remedythis Introduction

  4. Heel, erg, and zeer are synonyms (‘very’) Zeer, erg canmodifyverbs, adjectivalpredicates and prepositionalpredicates Heel canonlymodifyadjectivalpredicates A: Hij is daar zeer/erg/heel blij mee P: Hij is daar zeer/erg/*heel meein zijn nopjes V: Dat verbaast ons zeer/erg/*heel. Basic Facts

  5. English very is like heel in these respects; P: *He is very in love A: He is very amorous V: It surprised us very *(much)) Basic Facts

  6. Difference: not due to semantics Purely syntactic As far as we know: does not follow from a general rule So it must be ‘learned’ by a child acquiring Dutch as first language Basic Facts

  7. How does a child acquiring Dutch as a first language get to ‘know’ that zeer and erg can modify verbs, prepositional and adjectival predicates? Research Question (1)

  8. Hypothesis 1a Once a word is encountered for the first time, a critical phase (‘training phase’) starts in which the word properties will be determined based on input; after this phase the word properties are fixed. A sufficient number of actual examples occurring in this period sets the word properties (positive evidence) Hypotheses (1)

  9. Hypothesis 2a Once a word is encountered for the first time, its grammatical properties are initially set by Semantic Bootstrapping: D (semcat) -> syncat A sufficient number of actual examples occurring in this period will add to the word properties (positive evidence) Sufficient amount of input that is contradictory to the semantically bootstrapped properties overrules them Hypotheses (1)

  10. How can a child acquiring Dutch as first language get to ‘know’ that heel cannot modify prepositional predicates and verbs? Children are never taught that it is not possible; They are also never or seldom corrected for language errors, and if they are, they seem to ignore it (Negative evidence plays no role) Research Question (2)

  11. Hypothesis 1b Absence of relevant constructions in the training phase of a word leads to absence of the property (indirect negative evidence) Hypothesis 2b Absence of relevant constructions in the training phase of a word does not lead to absence of the property for semantically bootstrapped properties Hypotheses (2)

  12. Do children ever make errors against this? Is a ‘training phase’ for word properties real? How ‘long’ is this training phase? What is a ‘sufficiently large’ number of actual examples Does semantic bootstrapping play a role, and if so which one Are these words acquired in different language acquisition stages? Related Questions

  13. Can this be related to the different modification potential? Is there a relation with the fact that zeer appears to be rather formal, while heel and erg are not? Related Questions

  14. adverb-adjective agreement (substandard): heel/heledikkeboeken ‘very thick books’ erg/ergedikkeboeken Zeer/*zeredikkeboeken Is this somehow related? What about other, closely related, words? Related Questions

  15. Currently Consult paper and electronic grammars ANS and e-ANS e.g. section 15-3-1-1 In the near Future Consult Taalportaal with (I hope/expect) All examples formally marked as such All examples parsed/tagged, using ISOCAT DCs and searchable Links to (possibly complex queries) to illustrate with real data from treebanks and other annotated data Consult Grammars

  16. Which data and tools (LRs) exist that might contribute to answering these questions? Currently: you have to search for them in multiple places Many relevant data are not publicly visible (you will encounter them by personal contacts only) Or you have to create them yourself Find Data

  17. There is no place/site where you query: Give me a list of all LRs for the Dutch language What is the size of all Dutch text corpora (in #tokens) Give me a list of all Dutch data that contain children 2-7 years old as speaker Give me a list of all Dutch data containing any of the words heel, zeer, erg Not even in most individual data centres (TST-Centrale, ELRA, LDC, ..) Find Data

  18. CLARIN Provides a flexible framework incl. tools for making descriptions of LRs (‘metadata’) CMDI Supports (assistance, execution, funding) the creation of metadata for LRs Supports making these metadata (and the actual data) visible and accessible via CLARIN portals Find Data

  19. CLARIN Provides facilities for semantic interoperability ISOCAT, Relation Registry (coming soon) browsing, searching and querying facilities for the metadata Initial prototype: Virtual Language Observatory Will enable you to collect the data that are relevant to you in a virtual collection This will save the researcher a lot of time It will enlarge the empirical basis for the research Find Data

  20. Find words that are closely related Adverbs that function as an intensifier (‘booster’) Are (near-)synonymous, hyponyms, or co-hyponyms Also (near-)antonyms are relevant In order to determine their properties and potential further generalizations Closely Related Words

  21. Using e.g. Synonym information in traditional dictionaries Dutch EuroWordnet (currently via ELRAM0016) Or Cornetto (via the Dutch HLT-Agency) Currently searchable only via a plug-in in an old version (3.5) of Firefox. or In programs via a python module A CLARIN-NL project to improve this Closely Related Words

  22. Found via synonym dictionaries: abnormaal afschuwelijk akelig bijster bijzonder bovenmatig buitengemeen buitensporig danig donders eminent enorm exceptioneel extra extraordinair extreem fabelachtig fenomenaal geweldig gigantisch intens kolossaal merkwaardig mirakels onbeschrijfelijk ongelofelijk ongehoord ongekend ongemeen onmenselijk onmetelijk ontzettend onwijs speciaal uitermate uiterst uitzonderlijk verdraaid verduiveld verrekte verschrikkelijk vet zeldzaam ….. Closely Related Words

  23. zeer:adverb:3 / heel:adverb:5 (from Cornetto) zeer:3/d_r-343077, allemachtig:2/d_r-9922, beestachtig:2/d_r-23835, bijzonder:4/c_546765, bliksems:2/d_r-32612, bloedig:2/d_r-32881, bovenmate:1/d_r-36728, buitengewoon:2/d_r-39235, buitenmate:1/d_r-39294, buitensporig:2/d_r-401837, crimineel:4/d_a-53026, deerlijk:2/d_r-57321, deksels:2/d_r-57728, donders:2/d_r-62605, drommels:2/d_r-65820, eindeloos:3/c_546740, enorm:2/d_r-74285, erbarmelijk:2/d_r-74877, fantastisch:6/d_r-79264, formidabel:2/d_r-82704, geweldig:4/d_r-92392, goddeloos:2/d_r-94633, godsjammerlijk:2/d_r-94798, grenzeloos:2/d_r-96846, grotelijks:1/d_r-98244, heel:5/d_r-106880, ijselijk:2/d_r-118854, ijzig:4/c_546756, intens:2/d_r-123517, krankzinnig:3/d_r-142403, machtig:4/d_r-165866, mirakels:1/d_r-173095, onsterachtig:2/d_r-175264, moorddadig:4/d_r-175475, oneindig:2/d_r-193740, onnoemelijk:2/d_r-194761, ontiegelijk:2/d_r-415154, ontstellend:2/d_r-415165, ontzaglijk:2/d_r-415176, ontzettend:3/d_r-196906, onuitsprekelijk:2/d_r-415180, onvoorstelbaar:2/d_r-415191, onwezenlijk:2/d_r-197464, onwijs:4/d_r-197468, overweldigend:2/d_r-205004, peilloos:2/d_r-213144, reusachtig:3/d_r-239357, reuze:2/d_r-239379, schrikkelijk:2/d_r-256144, sterk:7/d_r-272639, uiterst:4/d_r-300933, verdomd:2/d_r-308293, verdraaid:4/c_546761, verduiveld:2/d_r-308522, verduveld:2/d_r-308569, verrekt:3/d_r-418644, verrot:3/d_r-418648, verschrikkelijk:3/d_r-312634, vervloekt:2/d_r-314372, vreselijk:5/d_r-323099, waanzinnig:2/d_r-329061, zeldzaam:2/d_r-419882, zwaar:10/d_r-347153 Closely Related Words

  24. Check the basic facts Check against occurrences in corpora Problem: each of the 3 words is ambiguous! Erg (4x)= noun(de) ‘erg’; noun(het)’evil’, adj+adv ‘unpleasant’, adv ’very’ Zeer (3x)= noun ‘pain’; adj ‘painful’; adv ‘very’ Heel (3x) = adj ‘whole’; verbform ‘heal’; adv ‘very’ PoS-tagged corpus will help somewhat But most corpora do not distinguish adj from adv by category! (searching for PoS bigrams will help slightly) A fully-parsed corpus would be ideal Basic Facts: Correct?

  25. LASSY Small: 1M manually verified parsed corpus Interface to LASSY Small Requires knowledge of XPATH/XQUERY Very Simple Interface to LASSY Small limitedoptions but simple commands Example-based interface GrETEL (CLARIN- Flanders) Greedy Extraction of Trees for Empirical Linguistics Generates XPATH/XQUERY expression on the basis of an example sentence plus markings of what is relevant in it Basic Facts: Correct?

  26. Queries: erg::mod:; zeer::mod: ; heel::mod: Extract from Statistics: Query: heel::mod:ww Basic Facts: Correct?

  27. Analysis 8 examples are forms that are ambiguous between adjectival and verbal participle, All are examples of adjectival participles but LASSY represents all participles as verbal In 1 example heel modifies the adj open from the expression open staan voor, but wrongly analyzed as modifying the verb staan CLARIN will offer facilities to make annotations to such corpora Same queries could be done for the other related words on LASSY Large Corpus (2.4 billion words, automatically parsed) In the CGN corpus (but it uses a different interface) But this will require facilities for ‘batch jobs’ or more complicated queries (maybe via web services) Basic Facts: Correct?

  28. E.g. data in the CHILDES system (part of TalkBank 7 corpora for Dutch But with their own data formats (CHAT) and tools (CLAN) However, also mirrored at MPI and accessible via (ANNEX/)TROVA (again another interface) Acquisition Corpora: Search

  29. Give records for utterances containing erg with Corpus (e.g. Van Kampen Corpus) File: (e.g. laura74.cha) Line: (e.g. 139) Part Role: (e.g. Child) Child Gdr: (e.g. female) Age: (e.g. 5;6.12) UTT (e.g. “ja , die s erg moeilijk .”) Maybe also some preceding/following context Map attribute names and values to ISOCAT Acquisition Corpora: Search

  30. Corpus: Van Kampen File: sarah21.cha Line: 630 Speaker: Child Child Gender: Female Age: 2;7.16 UTT: “prinses e(r)g groot !” Acquisition Corpora: Search

  31. For each child, give list of pairs session + age of the child For child and each session, give #occurrences of zeer, heel, erg etc, etc. Such queries (Some example attempts ) Mixed metadata/content search Over multiple resources Specific output formats are not so easy with the current interfaces!! Acquisition Corpora: Search

  32. Heel is found 153 times in Van Kampen corpus Erg is found 77 times in Van Kampen corpus But many are an irrelevant use of erg PoS-tagging the corpus might be useful Search for POS-bigrams (e.g. erg/adj */adj) Add lemma’s Or even full parsing, at least of the adult speech Acquisition corpora: Search

  33. CLARIN-NL Web services are being developed For PoS-tagging text For full parsing of text (and many more) To be usable by humanities researchers in a user-friendly way in work flow systems Usefulness depends on Size of the data (effort to select manually) Quality of the web services Acquisition corpora: Parse

  34. The found and newly created data should be stored in a supported format With automatically generated metadata With automatically generated provenance data Using data categories mapped to or from ISOCAT For which PIDs are provided Stored on a server of a CLARIN-centre So that they can become proper resources on their own Are visible, accessible and interpretable as part of enriched publications Store the found data

  35. Search in CGN / SONAR • To assess level of formality • Give absolute and relative frequencies of heel/hele/erg/erge/zeer as adj by text genre, and speaker/participants education level • In CGN (spoken corpus) • In SONAR (written corpus) • Idem but for the word + the following Pos-tag • Idem but in the fully parsed part of CGN and in LASSY + the PoS tag of the modifiee head

  36. Interpret the data • Interpret the data in function of the hypotheses being investigated • Apply analytical / statistical tools to the data • CLARIN should support formats of frequently used statistical packages such as SPSS, R, etc. • The research will surely lead to new questions, so to new queries • Reach conclusions and publish an open access enriched publication

  37. Broaden the scope • Do the same for worden/raken (‘become’/ ‘get’) • NP, PP and AP can be predicate complements • Worden and raken take predicate complements • They are (almost) synonymous • worden: takes only NP or AP • raken: takes only AP or PP

  38. Broaden the scope • AP: Zij werd / raakte zwanger • PP: Zij *werd / raakte in verwachting • NP: Zij werd / *raakte burgemeester And repeat the process Exercise

  39. Conclusions • There is no adequate infrastructure for linguistic research • There are bits and pieces, but • Finding LRs is not easy • LRs have their own formats, data categories, user / search interfaces • Limited formal and no semantic interoperability • Search in combined LRs very difficult if not impossible • full research potential is not exploited • CLARIN(-NL) attempts to remedy this

  40. Thanks for your attention! http://www.clarin.nl/ CLARIN-NL

  41. No Entry!

  42. De omgang met de buren gebeurt op een heel ontspannen manier en de vrouw van de dominee heeft zelfs al Wolderse vlaai leren bakken . (parse) heel:ADJ:mod:WW:ontspannen De verschijnselen zijn heel verschillend . (parse) heel:ADJ:mod:WW:verschillend ,, Op het voorterrein ging het nog heel overtuigend . (parse) heel:ADJ:mod:WW:overtuigend Ze hebben heel gericht en planmatig volkscafés bezocht om daar hun gif te spuien . (parse) heel:ADJ:mod:WW:gericht Ze is zelfs met een ' meester ' getrouwd : Marc Dassesse _ mevrouw Spiritus-Dassesse zet heel geëmanicipeerd haar meisjesnaam voorop _ is nu een gerenomeerd fiscaal adviseur en hoogleraar aan de ULB . (parse) heel:ADJ:mod:WW:geëmanicipeerd Gelukkig krijg ik nog heel geregeld te horen : ' Gerard jongen , dat doe je gewoon foùt ' . (parse) heel:ADJ:mod:WW:geregeld Dat is een heel verrassend resultaat en het stemt tot optimisme . (parse) heel:ADJ:mod:WW:verrassend De biermarkt is heel versnipperd en wordt overspoeld door nieuwe productlanceringen . (parse) heel:ADJ:mod:WW:versnipperd Toch staan we hier heel open voor voorstellen . (parse) heel:ADJ:mod:WW:staan Basic Facts: Correct?

  43. Metadata search CGN+CHILDESDutch && 2<age<7

  44. Regexp content searchheel|zeer|erg|erge|hele

  45. Resultset export to file

  46. CGNregexp ^heel$|^erg$|…

  47. CGNregexp op WORDS tier + POS

  48. Exercise • ‘Worden takes APs not PPs as predc’ • Use the LASSY-Small Very Simple Interface • Give me all sentences in which the word “worden” takes a predicative (predc) PP complement: • rel='predc' and hlemma='worden‘ and postag='vz' • Do you find examples with this query? • How do you interpret this?

More Related