Isabelle Augenstein

Publikation

Publikationer pr. år 2017 2018 2018

• 11 Konferencebidrag i proceedings
• 2 Tidsskriftartikel

Publikationer pr. år

Publikationer pr. år

Søgeresultater

• 2018

  A strong baseline for question relevancy ranking

  Gonzalez, A. V., Augenstein, I. & Søgaard, A., 2018, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, s. 4810–4815

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

• Character-level Supervision for Low-resource POS Tagging

  Kann, K., Bjerva, J., Augenstein, I., Plank, B. & Søgaard, A., 2018, Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP. Association for Computational Linguistics, s. 1–11

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

• Copenhagen at CoNLL–SIGMORPHON 2018: Multilingual Inflection in Context with Explicit Morphosyntactic Decoding

  Kementchedjhieva, Y. R., Bjerva, J. & Augenstein, I., 2018, Proceedings of the CoNLL SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection . Association for Computational Linguistics, s. 93–98

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

  • Multi-task learning 100%
  • Decoding 63%
  2 Citationer (Scopus)

• Discourse-aware rumour stance classification in social media using sequential classifiers

  Zubiaga, A., Kochkina, E., Liakata, M., Procter, R., Lukasik, M., Bontcheva, K., Cohn, T. & Augenstein, I., mar. 2018, I: Information Processing & Management. 54, 2, s. 273-290

  Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review

  • Rumor 100%
  • rumor 96%
  • Classifier 91%
  • Social Media 64%
  • social media 60%
  37 Citationer (Scopus)

• From Phonology to Syntax: Unsupervised Linguistic Typology at Different Levels with Language Embeddings

  Bjerva, J. & Augenstein, I., 2018, Proceedings, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies : (Long Papers). Association for Computational Linguistics, Bind 1. s. 907-916 10 s.

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

  • phonology 100%
  • syntax 89%
  • typology 73%
  • linguistics 56%
  • spoken language 8%
  7 Citationer (Scopus)

  33 Downloads (Pure)

• Jack the Reader – A Machine Reading Framework

  Weissenborn, D., Minervini, P., Dettmers, T., Augenstein, I., Welbl, J., Rocktäschel, T., Bošnjak, M., Mitchell, J., Demeester, T., Stenetorp, P. & Riedel, S., 2018, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics-System Demonstrations. Association for Computational Linguistics, s. 25–30

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

• Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces

  Augenstein, I., Ruder, S. & Søgaard, A., 2018, Proceedings, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies : (Long Papers). Association for Computational Linguistics, Bind 1. s. 1896–1906 11 s.

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

  • Multi-task learning 100%
  • Labels 63%
  • Semi-supervised learning 30%
  • Sentiment analysis 27%
  • Transfer functions 22%
  21 Citationer (Scopus)

  72 Downloads (Pure)

• Nightmare at test time: How punctuation prevents parsers from generalizing

  Søgaard, A., Lhoneux, M. D. & Augenstein, I., 2018, Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP . Association for Computational Linguistics, s. 25–29

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

• Parameter sharing between dependency parsers for related languages

  Lhoneux, M. D., Bjerva, J., Augenstein, I. & Søgaard, A., 2018, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing . Association for Computational Linguistics

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

  • Classifiers 100%

• Proceedings of The Third Workshop on Representation Learning for NLP

  Augenstein, I. (red.), Cao, K. (red.), He, H. (red.), Hill, F. (red.), Gella, S. (red.), Kiros, J. (red.), Mei, H. (red.) & Misra, D., 2018, Proceedings of the Third Workshop: Representation Learning for NLP. Association for Computational Linguistics, 224 s.

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

• Tracking Typological Traits of Uralic Languages in Distributed Language Representations

  Bjerva, J. & Augenstein, I., 2018, Proceedings, Fourth International Workshop on Computational Linguistics for Uralic Languages. Association for Computational Linguistics, s. 78-88

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

  • popularity 100%
  • typology 96%
  • linguistics 74%
  • history 61%
  26 Downloads (Pure)
• 2017

  Learning what to share between loosely related tasks

  Ruder, S., Bingel, J., Augenstein, I. & Søgaard, A., 23 maj 2017, I: arXiv.

  Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning

  • Multi-task learning 100%
  • Deep neural networks 24%
  • Profitability 22%
  • Labels 21%
  • Entropy 20%
  17 Downloads (Pure)

• Multi-Task Learning of Keyphrase Boundary Classification

  Augenstein, I. & Søgaard, A., 2017, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics : (Short Papers). Barzilay, R. & Kan, M-Y. (red.). Association for Computational Linguistics, Bind 2. s. 341-346 6 s.

  Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

  • Multi-task learning 100%
  • Labeled data 43%
  • Recurrent neural networks 38%
  • Labeling 36%
  • Deep neural networks 36%
  20 Citationer (Scopus)