Sökning: WFRF:(de Lhoneux Miryam 1990 ) > Linguistically Info...
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 04012nam a2200409 4500 | |
001 | oai:DiVA.org:uu-394133 | |
003 | SwePub | |
008 | 191003s2019 | |||||||||||000 ||eng| | |
020 | a 9789151307671q print | |
024 | 7 | a 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 | 7 | a vet2 swepub-contenttype |
072 | 7 | a dok2 swepub-publicationtype |
100 | 1 | a de Lhoneux, Miryam,d 1990-u Uppsala universitet,Institutionen för lingvistik och filologi,Computational Linguistics4 aut0 (Swepub:uu)mirde471 |
245 | 1 0 | a Linguistically Informed Neural Dependency Parsing for Typologically Diverse Languages |
264 | 1 | a Uppsala :b Acta Universitatis Upsaliensis,c 2019 |
300 | a 178 s. | |
338 | a electronic2 rdacarrier | |
490 | 0 | a 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 | 7 | a HUMANIORAx Språk och litteraturx Jämförande språkvetenskap och allmän lingvistik0 (SwePub)602012 hsv//swe |
650 | 7 | a 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 | |
700 | 1 | a Nivre, Joakimu Uppsala universitet,Institutionen för lingvistik och filologi4 ths0 (Swepub:uu)joani384 |
700 | 1 | a Stymne, Sarau Uppsala universitet,Institutionen för lingvistik och filologi4 ths |
700 | 1 | a Bender, Emily,c Professoru University of Washington, Department of Linguistics4 opn |
710 | 2 | a Uppsala universitetb Institutionen för lingvistik och filologi4 org |
856 | 4 | u https://uu.diva-portal.org/smash/get/diva2:1357373/FULLTEXT01.pdfx primaryx Raw objecty fulltext |
856 | 4 | u https://uu.diva-portal.org/smash/get/diva2:1357373/PREVIEW01.jpgx Previewy preview image |
856 | 4 8 | u https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-394133 |
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.
Kopiera och spara länken för att återkomma till aktuell vy