SLIDE 1
Workshop on Social Media and the Web of Linked Data at EUROLAN 2015 - - PowerPoint PPT Presentation
Workshop on Social Media and the Web of Linked Data at EUROLAN 2015 - - PowerPoint PPT Presentation
Workshop on Social Media and the Web of Linked Data at EUROLAN 2015 Summer School on Linguistic Linked Open Data 18 July 2015 | Sibiu, Romania This work continues the research began in 2013, having the main scope of building a corpus of
SLIDE 2
SLIDE 3
This work continues the research began in 2013, having the main scope of building a corpus
- f
annotated entities and semantic
- relations. The used text is the Romanian version
- f the novel
novel novel novel “Quo Quo Quo Quo Vadis Vadis Vadis Vadis”, authored by the Nobel laureate Henryk Henryk Henryk Henryk Sienkiewicz Sienkiewicz Sienkiewicz Sienkiewicz. The corpus is manually annotated with 12 types
- f anaphoric relations (e.g. coref, member-of,
part-of, has-as-part) and almost 30 types of non-anaphoric relations (e.g. parent-of, child-
- f, love, friendship, hate, superior-of, inferior-
- f, colleague-of ).
SLIDE 4
Entities are realized in texts as noun noun noun noun phrases phrases phrases phrases (NP NP NP NP) whose heads are nouns or pronouns.
SLIDE 5
Entities in QuoVadis corpus represent descriptions of persons, gods and any grouping of them.
SLIDE 6
Anaphoric (noted REFERENTIAL) relations:
coreferential, isa, class-of, member-of, has-as-member, part-of, has-as-part, etc.
Affectional (noted AFFECT) relations: friend-of,
fear-of, love, loved-by, hate, hated-by, worship, worshiped-by, etc.
Kinship (noted KINSHIP) relations: parent-of,
child-of, sibling-of, spouse-of, unknown, etc.
Social (noted SOCIAL) relations: superior-of,
inferior-of, colleague-of, in- competition-with, etc.
SLIDE 7
Figure taken from A.-D. Bibiri, M. Colhon, P. Diac, D. Cristea (2014). Statistics Over A Corpus Of Semantic Links: “QuoVadis”. In M. Colhon, A. Iftene, V. Barbu Mititelu, D. Cristea, D. Tufiş (eds.) Proceedings of the 10th International Conference "Linguistic Resources And Tools For Processing The Romanian Language”, „Alexandru Ioan Cuza” University Publishing House, pag. 33-44
SLIDE 8
Figure taken from M. Colhon, P. Diac, C. Mărănduc, A. Perez, "QuoVadis" Research Areas – Text
- Analysis. In M. Colhon, A. Iftene, V. Barbu Mititelu, D. Cristea, D. Tufiş (eds.) Proceedings of the
10th International Conference "Linguistic Resources And Tools For Processing The Romanian Language”, „Alexandru Ioan Cuza” University Publishing House, pag. 45-56
The colours code: colleague-of in-cooperation- with in-competition- with
- pposite-to
inferior-of superior-of
SLIDE 9
copii mame cu [ ] in brate [un grup de [ ]] children mothers with [ ] in their arms [a group of [ ]]
HEAD HEAD HEAD KINSHIP.parent-of REFERENTIAL.part-of
Properties: Properties: Properties: Properties:
- Imbricated entities have always separate heads.
- There are not entities that intersect and which are non-imbricated.
- The direction of the relation is from the larger entity (FROM entity)
to the nested entity (TO entity)
SLIDE 10
Manual annotations include:
the relation’s span the relation type the two entities the trigger
iubită este Ligia de familia lui Plautius dear Ligia was to Plautius
relation’s span
< < < < < < < < > > > > > > > > 1:[ 1:[ 1:[ 1:[ 1:[ 1:[ 1:[ 1:[ ] ] ] ] ] ] ] ] 2:[ 2:[ 2:[ 2:[ 2:[ 2:[ 2:[ 2:[ ] ] ] ] ] ] ] ]
Relation type Relation type Relation type Relation type: AFFECT.love FROM entity FROM entity FROM entity FROM entity: 1:[Ligia] TO entity TO entity TO entity TO entity: 2:[familia lui Plautius] Trigger Trigger Trigger Trigger: <iubită>
SLIDE 11
Our study:
addresses only to
imbricated entities
uses lexical and
syntactical patterns
SLIDE 12
no lexical information is considered here the main scope is to generalize the syntactic
patterns found in the training corpus under the same relation realization
applied on the following relations:
- REFERENTIAL.has-as-member
- REFERENTIAL.has-as-part
- REFERENTIAL.has-as-subgroup
SLIDE 13
1:[ 2:[împăratul însui], i 3:[preoii], i 4:[vestalele], i 5:[senatorii], i 6:[cavalerii], i 7:[poporul]] 1:[ 2:[Caesar himself], 3:[priests], 4:[vestals], 5:[senators], 6:[knights], 7:[the populace]] 1:[ 2:[împăratul însui], , , , i i i i 3:[preoii], i i i i 4:[vestalele], , , , i i i i 5:[senatorii], , , , i i i i 6:[cavalerii], , , , i i i i 7:[poporul]] 1:[ 2:[Caesar himself] , , , ,3:[priests] , , , , 4:[vestals] , , , , 5:[senators] , , , , 6:[knights] , , , , 7:[the populace]] 1:[2:[Ncmsry Dh3ms] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 3:[Ncmpry] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 4:[Ncfpry] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 5:[Ncmpry] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 6:[Ncmpry] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 7:[Ncmsry]] 1:[2:[ENTITY] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 3:[ENTITY] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 4:[ENTITY] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 5:[ENTITY] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 6:[ENTITY] COMMA Cc COMMA Cc COMMA Cc COMMA Cc 7:[ENTITY]] REFERENTIAL.has-as-member
SLIDE 14
1:[furtunos <urma> 2:[al consulilor]] 1:[mad <descendant> 2:[of consuls]]
dependency tree of the inner entity dependency tree
- f the outer entity
Relation type: KINSHIP.unknown triggered by <urma>
SLIDE 15
Relation type # test relations # correct Precision Recall F- measure AFFECT 3 3 1.0 1.0 1.0 KINSHIP 16 16 1.0 1.0 1.0 SOCIAL 20 15 1.0 0.75 0.86 REFERENTIAL 85 78 0.96 0.92 0.94 TOTAL 124 112 0.97 0.90 0.93
SLIDE 16
SLIDE 17