Skip to main content
Erschienen in: KI - Künstliche Intelligenz 4/2018

10.09.2018 | Dissertation and Habilitation Abstracts

Multitask and Multilingual Modelling for Lexical Analysis

verfasst von: Johannes Bjerva

Erschienen in: KI - Künstliche Intelligenz | Ausgabe 4/2018

Einloggen

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

In Natural Language Processing (NLP), one traditionally considers a single task (e.g. part-of-speech tagging) for a single language (e.g. English) at a time. However, recent work has shown that it can be beneficial to take advantage of relatedness between tasks, as well as between languages. In this work I examine the concept of relatedness and explore how it can be utilised to build NLP models that require less manually annotated data. A large selection of NLP tasks is investigated for a substantial language sample comprising 60 languages. The results show potential for joint multitask and multilingual modelling, and hints at linguistic insights which can be gained from such models.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

KI - Künstliche Intelligenz

The Scientific journal "KI – Künstliche Intelligenz" is the official journal of the division for artificial intelligence within the "Gesellschaft für Informatik e.V." (GI) – the German Informatics Society - with constributions from troughout the field of artificial intelligence.

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Weitere Produktempfehlungen anzeigen
Fußnoten
1
In NLP words are commonly represented by embedding them in a vector space, typically with 64–256 dimensions. These representations are learnt by predicting contexts in large text corpora, such that words occurring in similar contexts are close to one another, which is useful since such words tend to have similar meanings (i.e. distributional semantics).
 
2
SemTags: [1, 9]. POS: UD1.3 (universaldependencies.org).
 
3
This can be done by learning multilingual word embeddings, in which, e.g., the words dialects and Dialekten are close to one another.
 
4
Bi-directional RNNs are frequently used in NLP. One advantage of this is that one can use both the preceding and succeeding contexts of a word when predicting its tag.
 
5
Evaluation of a model trained on one language on a test instance for an unobserved language.
 
Literatur
1.
Zurück zum Zitat Abzianidze L, Bjerva J, Evang K, Haagsma H, van Noord R, Ludmann P, Nguyen DD, Bos J (2017) The parallel meaning bank: towards a multilingual corpus of translations annotated with compositional meaning representations. In: EACL, pp 242–247 Abzianidze L, Bjerva J, Evang K, Haagsma H, van Noord R, Ludmann P, Nguyen DD, Bos J (2017) The parallel meaning bank: towards a multilingual corpus of translations annotated with compositional meaning representations. In: EACL, pp 242–247
2.
Zurück zum Zitat Bjerva J (2016) Byte-based language identification with deep convolutional networks. In: VarDial3, pp 119–125 Bjerva J (2016) Byte-based language identification with deep convolutional networks. In: VarDial3, pp 119–125
4.
Zurück zum Zitat Bjerva J (2017) Will my auxiliary tagging task help? Estimating auxiliary tasks effectivity in multi-task learning. In: NoDaLiDa, pp 216–220 Bjerva J (2017) Will my auxiliary tagging task help? Estimating auxiliary tasks effectivity in multi-task learning. In: NoDaLiDa, pp 216–220
5.
Zurück zum Zitat Bjerva J, Augenstein I (2018) From phonology to syntax: unsupervised linguistic typology at different levels with language embeddings. In: NAACL-HLT Bjerva J, Augenstein I (2018) From phonology to syntax: unsupervised linguistic typology at different levels with language embeddings. In: NAACL-HLT
6.
Zurück zum Zitat Bjerva J, Augenstein I (2018) Tracking typological features of uralic languages in distributed language representations. In: IWCLUL Bjerva J, Augenstein I (2018) Tracking typological features of uralic languages in distributed language representations. In: IWCLUL
7.
Zurück zum Zitat Bjerva J, Bos J, Van der Goot R, Nissim M (2014) The meaning factory: Formal semantics for recognizing textual entailment and determining semantic similarity. In: SemEval 2014, pp 642–646 Bjerva J, Bos J, Van der Goot R, Nissim M (2014) The meaning factory: Formal semantics for recognizing textual entailment and determining semantic similarity. In: SemEval 2014, pp 642–646
8.
Zurück zum Zitat Bjerva J, Östling R (2017) Cross-lingual learning of semantic textual similarity with multilingual word representations. In: NoDaLiDa, pp 211–215 Bjerva J, Östling R (2017) Cross-lingual learning of semantic textual similarity with multilingual word representations. In: NoDaLiDa, pp 211–215
9.
Zurück zum Zitat Bjerva J, Plank B, Bos J (2016) Semantic tagging with deep residual networks. In: COLING, pp 3531–3541 Bjerva J, Plank B, Bos J (2016) Semantic tagging with deep residual networks. In: COLING, pp 3531–3541
10.
Zurück zum Zitat Bos J, Basile V, Evang K, Venhuizen NJ, Bjerva J (2017) The Groningen meaning bank. Springer, Dordrecht, pp 463–496 Bos J, Basile V, Evang K, Venhuizen NJ, Bjerva J (2017) The Groningen meaning bank. Springer, Dordrecht, pp 463–496
12.
Zurück zum Zitat de Lhoneux M, Bjerva J, Augenstein I, Søgaard A (2018) Parameter sharing between dependency parsers for related languages. In: EMNLP de Lhoneux M, Bjerva J, Augenstein I, Søgaard A (2018) Parameter sharing between dependency parsers for related languages. In: EMNLP
Metadaten
Titel
Multitask and Multilingual Modelling for Lexical Analysis
verfasst von
Johannes Bjerva
Publikationsdatum
10.09.2018
Verlag
Springer Berlin Heidelberg
Erschienen in
KI - Künstliche Intelligenz / Ausgabe 4/2018
Print ISSN: 0933-1875
Elektronische ISSN: 1610-1987
DOI
https://doi.org/10.1007/s13218-018-0557-5

Weitere Artikel der Ausgabe 4/2018

KI - Künstliche Intelligenz 4/2018 Zur Ausgabe

News

News