Uncertainty Detection as Approximate Max-Margin Sequence Labelling

Täckström, Oscar (author): RISE,Uppsala universitet,Institutionen för lingvistik och filologi,Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Languages, Department of Linguistics and Philology.(Datorlingvistik),SICS

Velupillai, Sumithra Ulrika (author): tockholms universitet, Institutionen för data- och systemvetenskap,Institutionen för data- och systemvetenskap, Informationssystem

Hassel, Martin (author): tockholms universitet, Institutionen för data- och systemvetenskap

Dalianis, Hercules (author): Stockholms universitet,Institutionen för data- och systemvetenskap,tockholms universitet, Institutionen för data- och systemvetenskap

Duneld, Martin (author): Stockholms universitet,Institutionen för data- och systemvetenskap

(creator_code:org_t)

Association for Computational Linguistics, 2010
2010
English.
In: CoNLL 2010. - : Association for Computational Linguistics. ; , s. 84-91

Related links:: http://soda.swedish-...; show more...; https://uu.diva-port... (primary) (Raw object); http://www.aclweb.or...; https://su.diva-port... (primary) (Raw object); https://ri.diva-port... (primary) (Raw object); https://urn.kb.se/re...; https://urn.kb.se/re...; https://urn.kb.se/re...; show less...

Abstract Subject headings

This paper reports experiments for the CoNLL 2010 shared task on learning to detect hedges and their scope in natural language text. We have addressed the experimental tasks as supervised linear maximum margin prediction problems. For sentence level hedge detection in the biological domain we use an L1-regularised binary support vector machine, while for sentence level weasel detection in the Wikipedia domain, we use an L2-regularised approach. We model the in-sentence uncertainty cue and scope detection task as an L2-regularised approximate maximum margin sequence labelling problem, using the BIO-encoding. In addition to surface level features, we use a variety of linguistic features based on a functional dependency analysis. A greedy forward selection strategy is used in exploring the large set of potential features. Our official results for Task 1 for the biological domain are 85.2 F1-score, for the Wikipedia set 55.4 F1-score. For Task 2, our official results are 2.1 for the entire task with a score of 62.5 for cue detection. After resolving errors and final bugs, our final results are for Task 1, biological: 86.0, Wikipedia: 58.2; Task 2, scopes: 39.6 and cues: 78.5.

NATURVETENSKAP -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
NATURAL SCIENCES -- Computer and Information Sciences -- Language Technology (hsv//eng)
NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)

By the author/editor: Täckström, Oscar; Velupillai, Sumi ...; Hassel, Martin; Eriksson, Gunnar; Dalianis, Hercul ...; Karlgren, Jussi; show more...; Duneld, Martin; show less...

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Language Technol ...

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Science ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.