grisp: a massive multilingual terminological database for scientific and technical domains

20
GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains Patrice Lopez and Laurent Romary INRIA & HUB – IDSL [email protected] laurent.romary@inria. fr

Upload: sera

Post on 23-Feb-2016

43 views

Category:

Documents


0 download

DESCRIPTION

GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains. Patrice Lopez and Laurent Romary INRIA & HUB – IDSL [email protected] [email protected]. Overview. GRISP ( G eneric R esearch I nsight in S cientific and technical P ublications ) - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

GRISP: A Massive Multilingual Terminological Database

for Scientific and Technical Domains

Patrice Lopez and Laurent RomaryINRIA & HUB – IDSL

[email protected] [email protected]

Page 2: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Overview• GRISP (Generic Research Insight in Scientific and technical Publications)

– Multiple scientific and technical fields– Multilingual (en, fr, de)– Built from the compilation of open resources

• Sound conceptual model• Mapping across a variety of domains• Use of structural constraints• Machine learning techniques for controlling the fusion process

– Our sources: MeSH, UMLS, Specialist Lexicon, Gene Ontology, ChEBI, WordNet, WOLF, SUMO, IPC, Wikipedia

– Result: several millions terms, concepts, semantic relations and definitions.

Page 3: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Why are we doing all this?• Terminology is the main vehicle by which technical and scientific units

of knowledge are represented and conveyed (30-80%; Ahmad, 1996)• Application to a large collection of multilingual and multi-domain

patent documents• Two underlying considerations:

– Cost of manually maintained terminological resources• Cf. Biosis, IATE, TermScience

– Khayari et al., 2006: Modeling the heterogeneity of resources

– A lot of available resources online, based on heterogeneous organizational principles

• Underlying vision: Integrating knowledge engineering into current state of the art information retrieval and classification systems

Page 4: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Merging terminological resources• Related to the fusion of ontologies

– Ontologies are usually relatively small in size• Semi-automatic methods: McGuinness et al., 2000• Fully automatic method

– Madhavan et al., 2001: exploit structural and linguistic matching– Doan et al., 2001: Machine learning techniques (concepts and properties)– Gal et al., 2005: fuzzy logic methods

• Existing work on merging classification systems– Wang et al., 2008: Merging of subject headers in Digital Libraries

• Automatic merging techniques for heterogeneous terminologies has not been yet investigated– Much richer linguistic content– No formal organization of concepts

• Do not model facts or assertions

Page 5: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

A quick reminder• Terminological resources

– Approximation of lexical semantics in specialized fields– Based on a concept to term (onomasiological) model– Naturally multilingual (term grouping according to

languages)– Existing standards

• ISO 704: editorial principles for building up a terminological resource

• ISO 16642: Abstract model for representing terminological databases– Romary, 2001

• ISO 30042: A concrete XML syntax (TBX)– Note: terminology standards do not standardize

terminologies!

Page 6: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Target terminological model• Multiple languages• Multiple terms

– Variants, abbreviation, inflexions• Multiple descriptions

– E.g. multiple definitions, complementing each other– Additional information: illustrations, formulae, etc.

• Basic conceptual relations• Local metadata

– Provides management information attached to the various terminological description levels (e.g. origin, validation level, register)

– Allows the creation of views (e.g. all MeSH entries; cf. Khayari et al., 2006)

• And yes, ISO 16642 (TMF) can all this!– Main issue: identifying the relevant data category in the various

source terminologies

Page 7: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Merging terminologies,merging models

TMF model 1

TMF model 2

TMF model 2

TMF model 2

Target model

Page 8: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

TMF in a nutshell

Terminological Data Collection (TDC)Terminological Data Collection (TDC)

Terminological EntryTerminological Entry

Language Language SectionSection

Term Section Term Section Term Section Term Section

Language Language SectionSection

Term Section Term Section Term Section Term Section

Terminological EntryTerminological Entry

Language Language SectionSection

Term Section Term Section Term Section Term Section

Language Language SectionSection

Term Section Term Section Term Section Term Section

Terminological EntryTerminological Entry

Language Language SectionSection

Term Section Term Section Term Section Term Section

Language Language SectionSection

Term Section Term Section Term Section Term Section

Terminological EntryTerminological Entry

Language Language SectionSection

Term Section Term Section Term Section Term Section

Language Language SectionSection

Term Section Term Section Term Section Term Section

Metadata (sources,

revisions)

Ontological relations,

definition

Dialectal information,

definitionGrammatical

information, register, …

definition

+ any kind of local metadata (origin, certainty, accessibility)+ any kind of local metadata (origin, certainty, accessibility)

Page 9: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Merging terminologies,merging models

TMF model 1

TMF model 2

TMF model 2

TMF model 2

Target model

Data category mapping

/definition/

/definition/

Page 10: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Identifying domains• Theoretical background

– Non-ambiguity of a term within a domain– E.g. 129 domains in MESH

• GRISP– Set of 76 reference domains (see table 1)

• Scientific and technical domains of Wordnet Domains (Magnini and Cavaglià, 2000)

• Organised as a hierarchy– Manual mapping from resource specific domains to our

reference set

Page 11: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Merging concepts• Identification of common concepts across

terminological sources – core principles– Baseline: same term + same domain = same concept– Difficulties: Conflicting domain mapping, high polysemy of

term variants and incorrectly positioned concepts (e.g. Wikipedia)• Wrongly merged concepts• Lost in precision for concept description

– Revised: same preferred term + same domain = same concept

– Source conformance rule: separated concepts in a given source cannot be further merged (by transitivity)• Not applied to Wordnet, IPC and Wikipedia

– Smoothing down the rules: using machine learning techniques

Page 12: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Concept merging as a machine learning process

Concept pool

ConceptConceptConceptConcept

ConceptConcept

ConceptConcept

ConceptConceptConceptConcept

ConceptConcept

ConceptConcept

ConceptConcept

ConceptConcept

ConceptConcept

Features Merging decision

SVM (Support Vector Machine) and MLP (Multi-Layer Perceptron) binary classification models

ConceptConcept

Page 13: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Training process• Training features

• (f1-2) sources (e.g. S1=“MeSH”, S2=“Wikipedia”)• (f3) Number of common domains between the two concepts• (f4) Number of same source-specific categorizations• (f5) Boolean indicating if both preferred terms are identical• (f6) Boolean indicating if both preferred terms are identical after stemming• (f7) Ratio of identical terms given all terms• (f8) Similarity measure of the definition texts, after stemming and based on

negative KL divergence• (f9) Number of domains of the merged concept• (f10) Number of words of the longest common terms

• Training data– Wikipedia – MeSH mapping– Pascal database (INIST)

Page 14: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Result overviewMerger Concepts Terms Sem.

Rel.Aggregation 1,503,818 3,140,726 970,864Merg. Rule 1 1,457,538 3,157,179 1,022,303Merg. Rule 2 1,476,508 3,114,711 971,218SVM 1,450,688 3,195,118 1,088,446MLP 1,451,710 3,192,325 1,081,955

• Observations:– Small number of actual merges (cf. product names,

chemical and medical entities)– Merging relevant for frequently used concepts

Overall content:• 596,865 definitions• 1,321,988 source specific

categorizations of concepts• 20,000 acronyms• 14,268 chemical formulas

and• 12,375 chemical structure

identifiers.

Page 15: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

EvaluationMerger Wiki/MeSH PASCAL

Merging Rule 1 cov. 0.6464acc. 0.9497

cov. 0.5358acc. 0.9371

Merging Rule 2 cov. 0.3607acc. 0.9949

cov. 0.2735acc. 0.9916

SVM cov. 0.8642acc. 0.9698

cov. 0.6203acc. 0.9522

MLP cov. 0.8607acc. 0.9748

cov. 0.6178acc. 0.9515

• Random subset of 10% of the merging examples extracted from Wikipedia/MeSH mappings and from the PASCAL terminology

• Merging Rule 2 produces almost perfect merging but with a very low coverage• Rule 1 extends the coverage at the price of a relatively high rate of merging error• Machine Learning approaches further extend the coverage while maintaining a

high precision

Page 16: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

16

renderingrenderingrendering

GRISP browser: radial engine

Page 17: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

17

Page 18: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Application: Patatras• PATATRAS (PATent and Article Tracking, Retrieval

and AnalysiS)• Context: CLEF-IP competition

– Prior art search task (EPO documents)– 1,9 million documents in English, French and German (more

than 3 billion words)– Ranked first for all subtasks of the evaluation track among 14

participants (Roda et al., 2009)• Conceptual indexing of the CLEF-IP corpus

– Development of a term annotator based on GRISP• Term variant matching after POS + lemmatization• Concept disambiguation based on IPC classes of the documents• 1.1 million different terms identified• 176 million annotations

Page 19: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

19

Results: Patatras• Significant accuracy improvements for CLEF-IP

– Combination of a word-based and concept-based ranked results with a regression model

Based on 10,000 queries

Page 20: GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains

Epilogue• Online tool– Contact: [email protected]

• Free resource– Based on the freely available subset of resources

• Constant evolution– Maintenance according to evolution of our

sources– Addition of further sources