Evaluating LSTM models for grammatical function labelling
To improve grammatical function labelling for German, we augment the labelling component of a neural dependency parser with a decision history. We present different ways to encode the history, using different LSTM architectures, and show that our models yield significant improvements, resulting in a...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Kapitel/Artikel Konferenzschrift |
| Sprache: | Englisch |
| Veröffentlicht: |
September 2017
|
| In: |
15th International Conference on Parsing Technologies - proceedings of the conference
Year: 2017, Pages: 128-133 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://aclanthology.org/W17-6318 |
| Verfasserangaben: | Bich-Ngoc Do, Ines Rehbein |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1870904826 | ||
| 003 | DE-627 | ||
| 005 | 20240311111216.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231122s2017 xx |||||o 00| ||eng c | ||
| 035 | |a (DE-627)1870904826 | ||
| 035 | |a (DE-599)KXP1870904826 | ||
| 035 | |a (OCoLC)1425869777 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 28 |2 sdnb | ||
| 100 | 1 | |a Do, Bich-Ngoc |d 1989- |e VerfasserIn |0 (DE-588)1208354051 |0 (DE-627)1694619745 |4 aut | |
| 245 | 1 | 0 | |a Evaluating LSTM models for grammatical function labelling |c Bich-Ngoc Do, Ines Rehbein |
| 264 | 1 | |c September 2017 | |
| 300 | |a 6 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 22.11.2023 | ||
| 520 | |a To improve grammatical function labelling for German, we augment the labelling component of a neural dependency parser with a decision history. We present different ways to encode the history, using different LSTM architectures, and show that our models yield significant improvements, resulting in a LAS for German that is close to the best result from the SPMRL 2014 shared task (without the reranker). | ||
| 700 | 1 | |a Rehbein, Ines |e VerfasserIn |0 (DE-588)1207353833 |0 (DE-627)1693632373 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |a International Conference on Parsing Technologies (15. : 2017 : Pisa) |t 15th International Conference on Parsing Technologies - proceedings of the conference |d Stroudsburg, PA : Association for Computational Linguistics (ACL), 2017 |g (2017), Seite 128-133 |h 1 Online-Ressource (xvii, 135 Seiten, 3,69 MB) |w (DE-627)1002174716 |z 9781945626739 |7 nnam |
| 773 | 1 | 8 | |g year:2017 |g pages:128-133 |g extent:6 |a Evaluating LSTM models for grammatical function labelling |
| 787 | 0 | 8 | |i Forschungsdaten |a Do, Bich-Ngoc, 1989 - |t Head selection parsers and LSTM labelers |d Heidelberg : Universität, 2023 |h 1 Online-Ressource (19 Files) |w (DE-627)1870904370 |
| 856 | 4 | 0 | |u https://aclanthology.org/W17-6318 |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20231122 | ||
| 993 | |a ConferencePaper | ||
| 994 | |a 2017 | ||
| 998 | |g 1207353833 |a Rehbein, Ines |m 1207353833:Rehbein, Ines |d 90000 |e 90000PR1207353833 |k 0/90000/ |p 2 |y j | ||
| 998 | |g 1208354051 |a Do, Bich-Ngoc |m 1208354051:Do, Bich-Ngoc |d 90000 |d 90500 |e 90000PD1208354051 |e 90500PD1208354051 |k 0/90000/ |k 1/90000/90500/ |p 1 |x j | ||
| 999 | |a KXP-PPN1870904826 |e 4415913814 | ||
| BIB | |a Y | ||
| JSO | |a {"title":[{"title_sort":"Evaluating LSTM models for grammatical function labelling","title":"Evaluating LSTM models for grammatical function labelling"}],"person":[{"display":"Do, Bich-Ngoc","roleDisplay":"VerfasserIn","role":"aut","family":"Do","given":"Bich-Ngoc"},{"role":"aut","display":"Rehbein, Ines","roleDisplay":"VerfasserIn","given":"Ines","family":"Rehbein"}],"type":{"media":"Online-Ressource","bibl":"chapter"},"note":["Gesehen am 22.11.2023"],"language":["eng"],"recId":"1870904826","origin":[{"dateIssuedDisp":"September 2017","dateIssuedKey":"2017"}],"id":{"eki":["1870904826"]},"name":{"displayForm":["Bich-Ngoc Do, Ines Rehbein"]},"physDesc":[{"extent":"6 S."}],"relHost":[{"physDesc":[{"extent":"1 Online-Ressource (xvii, 135 Seiten, 3,69 MB)","noteIll":"Illustrationen"}],"id":{"isbn":["9781945626739"],"eki":["1002174716"]},"origin":[{"dateIssuedKey":"2017","publisher":"Association for Computational Linguistics (ACL)","dateIssuedDisp":"[2017]","publisherPlace":"Stroudsburg, PA"}],"language":["eng"],"corporate":[{"role":"aut","display":"International Conference on Parsing Technologies (15., 2017, Pisa)","roleDisplay":"VerfasserIn"},{"roleDisplay":"Herausgebendes Organ","display":"Association for Computational Linguistics","role":"isb"},{"role":"orm","roleDisplay":"VeranstalterIn","display":"Association for Computational Linguistics"}],"recId":"1002174716","type":{"media":"Online-Ressource","bibl":"book"},"disp":"International Conference on Parsing Technologies (15. : 2017 : Pisa)15th International Conference on Parsing Technologies - proceedings of the conference","note":["\"IWPT 2017 continues the tradition of biennial conferences organized by SIGPARSE, the Special Interest Group on Natural Language Parsing of the Association for Computational Linguistics (ACL) ... This year, for the first time, IWPT is co-located with the International Conference on Dependency Linguistics (DepLing)\" - Vorwort","\"Editors: Yusuke Miyao, Kenji Sagae\" - Startseite der Ressource","Literaturangaben"],"titleAlt":[{"title":"Proceedings of the 15th International Conference on Parsing Technologies"}],"part":{"text":"(2017), Seite 128-133","extent":"6","year":"2017","pages":"128-133"},"person":[{"given":"Yusuke","family":"Miyao","role":"edt","roleDisplay":"HerausgeberIn","display":"Miyao, Yusuke"},{"roleDisplay":"HerausgeberIn","display":"Sagae, Kenji","role":"edt","family":"Sagae","given":"Kenji"}],"title":[{"title_sort":"15th International Conference on Parsing Technologies - proceedings of the conference","subtitle":"September 20-22, 2017, Pisa, Italy : IWPT 2017","title":"15th International Conference on Parsing Technologies - proceedings of the conference"}]}]} | ||
| SRT | |a DOBICHNGOCEVALUATING2017 | ||