SwePub
Sök i LIBRIS databas

  Extended search

onr:"swepub:oai:DiVA.org:uu-394133"
 

Search: onr:"swepub:oai:DiVA.org:uu-394133" > Linguistically Info...

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist
LIBRIS Formathandbok  (Information om MARC21)
FältnamnIndikatorerMetadata
00004012nam a2200409 4500
001oai:DiVA.org:uu-394133
003SwePub
008191003s2019 | |||||||||||000 ||eng|
020 a 9789151307671q print
024a https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-3941332 URI
040 a (SwePub)uu
041 a engb eng
042 9 SwePub
072 7a vet2 swepub-contenttype
072 7a dok2 swepub-publicationtype
100a de Lhoneux, Miryam,d 1990-u Uppsala universitet,Institutionen för lingvistik och filologi,Computational Linguistics4 aut0 (Swepub:uu)mirde471
2451 0a Linguistically Informed Neural Dependency Parsing for Typologically Diverse Languages
264 1a Uppsala :b Acta Universitatis Upsaliensis,c 2019
300 a 178 s.
338 a electronic2 rdacarrier
490a Studia Linguistica Upsaliensia,x 1652-1366 ;v 24
520 a This thesis presents several studies in neural dependency parsing for typologically diverse languages, using treebanks from Universal Dependencies (UD). The focus is on informing models with linguistic knowledge. We first extend a parser to work well on typologically diverse languages, including morphologically complex languages and languages whose treebanks have a high ratio of non-projective sentences, a notorious difficulty in dependency parsing. We propose a general methodology where we sample a representative subset of UD treebanks for parser development and evaluation. Our parser uses recurrent neural networks which construct information sequentially, and we study the incorporation of a recursive neural network layer in our parser. This follows the intuition that language is hierarchical. This layer turns out to be superfluous in our parser and we study its interaction with other parts of the network. We subsequently study transitivity and agreement information learned by our parser for auxiliary verb constructions (AVCs). We suggest that a parser should learn similar information about AVCs as it learns for finite main verbs. This is motivated by work in theoretical dependency grammar. Our parser learns different information about these two if we do not augment it with a recursive layer, but similar information if we do, indicating that there may be benefits from using that layer and we may not yet have found the best way to incorporate it in our parser. We finally investigate polyglot parsing. Training one model for multiple related languages leads to substantial improvements in parsing accuracy over a monolingual baseline. We also study different parameter sharing strategies for related and unrelated languages. Sharing parameters that partially abstract away from word order appears to be beneficial in both cases but sharing parameters that represent words and characters is more beneficial for related than unrelated languages.
650 7a HUMANIORAx Språk och litteraturx Jämförande språkvetenskap och allmän lingvistik0 (SwePub)602012 hsv//swe
650 7a HUMANITIESx Languages and Literaturex General Language Studies and Linguistics0 (SwePub)602012 hsv//eng
653 a Dependency parsing
653 a multilingual NLP
653 a Universal Dependencies
653 a Linguistically informed NLP
653 a Computational Linguistics
653 a Datorlingvistik
700a Nivre, Joakimu Uppsala universitet,Institutionen för lingvistik och filologi4 ths0 (Swepub:uu)joani384
700a Stymne, Sarau Uppsala universitet,Institutionen för lingvistik och filologi4 ths
700a Bender, Emily,c Professoru University of Washington, Department of Linguistics4 opn
710a Uppsala universitetb Institutionen för lingvistik och filologi4 org
856u https://uu.diva-portal.org/smash/get/diva2:1357373/FULLTEXT01.pdfx primaryx Raw objecty fulltext
856u https://uu.diva-portal.org/smash/get/diva2:1357373/PREVIEW01.jpgx Previewy preview image
8564 8u https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-394133

Find in a library

To the university's database

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist

Search outside SwePub

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.

 
pil uppåt Close

Copy and save the link in order to return to this view