Multi-Task Sequence Labeling Under Adverse Conditions

Søgeresultater

• 2021

  Challenges in Annotating and Parsing Spoken, Code-switched, Frisian-Dutch Data

  Braggaar, A. & van der Goot, R., apr. 2021, Proceedings of the Second Workshop on Domain Adaptation for NLP. Association for Computational Linguistics, s. 50-58

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Dutch 100%
  • Parsing 100%
  • Treebank 100%
  • Code-switching 100%
  • Language Resource 100%

• CL-MoNoise: Cross-lingual Lexical Normalization

  van der Goot, R., okt. 2021, Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021). Association for Computational Linguistics, s. 510 4 s.

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Cross-lingual 100%
  • Lexical Normalization 100%
  • Starting Point 100%
  • Natural Language Processing 100%
  • Capitalization 66%

• Creating a Universal Dependencies Treebank of Spoken Frisian-Dutch Code-switched Data

  Braggaar, A. & van der Goot, R., 25 sep. 2021.

  Publikation: Konferencebidrag - EJ publiceret i proceeding eller tidsskrift › Konferenceabstrakt til konference › Forskning › peer review

  Åben adgang

  • Dutch 100%
  • Universal Dependencies 100%
  • Dependency Treebank 100%
  • Utterance 100%
  • Code-switching 100%

• Cross-lingual Multi-task Transfer for Zero-shot Task-oriented Dialog

  van der Goot, R., Stepanovic, M., Ramponi, A., Sharaf, I., Üstün, A., Imankulova, A., Khairunnisa, S. O., Komachi, M. & Plank, B., 25 sep. 2021.

  Publikation: Konferencebidrag - EJ publiceret i proceeding eller tidsskrift › Konferenceabstrakt til konference › Forskning › peer review

  Åben adgang

  • Multitask Learning 100%
  • Annotation 100%
  • Machine Translation 100%
  • Zero-shot 100%
  • Digital Assistant 100%

• From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding

  van der Goot, R., Sharaf, I., Imankulova, A., Üstün, A., Stepanovic, M., Ramponi, A., Khairunnisa, S. O., Komachi, M. & Plank, B., 2021, Proceedings of NAACL. Association for Computational Linguistics

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Non-English 100%
  • Auxiliary Task 100%
  • Masked Language Model 100%
  • Language Understanding 100%
  • Spoken Language 100%

• Genre as Weak Supervision for Cross-lingual Dependency Parsing

  Müller-Eberstein, M., van der Goot, R. & Plank, B., nov. 2021, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Online and Punta Cana, Dominican Republic: Association for Computational Linguistics, s. 4786-4802

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Cross-lingual 100%
  • Dependency Parsing 100%
  • Unsupervised Learning 100%
  • Data Selection 100%
  • dependency parse 100%

• How Universal is Genre in Universal Dependencies?

  Müller-Eberstein, M., van der Goot, R. & Plank, B., dec. 2021, Proceedings of the 20th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2021). Sofia, Bulgaria: Association for Computational Linguistics, s. 69-85

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Universal Dependencies 100%
  • Instance Level 100%
  • Treebank 80%
  • Annotation 50%
  • Varying Degree 50%

• Lexical Normalization for Code-switched Data and its Effect on POS Tagging

  van der Goot, R. & Çetinoğlu, Ö., apr. 2021, Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. Association for Computational Linguistics, s. 2352-2365 13 s.

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • POS Tagging 100%
  • Lexical Normalization 100%
  • Code-switching 100%
  • Natural Language Processing 100%
  • Multiple Language 100%

• Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLP

  van der Goot, R., Üstün, A., Ramponi, A., Sharaf, I. & Plank, B., 2021, Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics, s. 176-197

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Natural Language Processing 100%
  • Multi-task Learning 100%
  • Contextual Embeddings 100%
  • NLP. 100%
  • Multitask Learning 100%

• Much Gracias: Semi-supervised Code-switch Detection for Spanish-English: How far can we get?

  Iliescu, D.-M., Grand, R., van der Goot, R. & Qirko, S., jun. 2021, Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching. Association for Computational Linguistics, s. 65 6 s. (Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching).

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Code-switching 100%
  • Spanish-English Bilinguals 100%
  • Training Data 100%
  • N-gram 66%
  • Natural Language Processing 50%

• MultiLexNorm: A Shared Task on Multilingual Lexical Normalization

  van der Goot, R., Ramponi, A., Zubiaga, A., Plank, B., Muller, B., San Vicente Roncal, I., Ljubešic´, N., Çetinoğlu, Ö., Mahendra, R., Çolakoglu, T., Baldwin, T., Caselli, T. & Sidorenko, W., nov. 2021, Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021). Association for Computational Linguistics, s. 493–509 16 s.

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Shared Task 100%
  • Lexical Normalization 100%
  • Parts Of Speech Tagging 100%
  • Parsing 100%
  • Part-of 50%

• On the Effectiveness of Dataset Embeddings in Mono-lingual, Multi-lingual and Zero-shot Conditions

  van der Goot, R., Üstün, A. & Plank, B., apr. 2021, Proceedings of the Second Workshop on Domain Adaptation for NLP: EACL 2021 workshop. Association for Computational Linguistics, s. 183–194

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Performance Increase 100%
  • Parsing 100%
  • Lemmatization 100%
  • Data Source 100%
  • Heterogeneous Data Sources 33%

• We Need to Talk About train-dev-test Splits

  van der Goot, R., okt. 2021, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, s. 4485 9 s.

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  • Natural Language Processing 100%
  • Development Data 100%
  • Neural Network 100%
  • Model Selection 50%
  • Overfitting 50%

• 2020

  Biomedical Event Extraction as Sequence Labeling

  Ramponi, A., van der Goot, R., Lombardo, R. & Plank, B., nov. 2020, Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Sequence Labeling 100%
  • Biomedical Event Extraction 100%
  • Event Extraction 100%
  • Multi-task Learning 16%
  • Viable Approach 16%

• DAN+: Danish Nested Named Entities and Lexical Normalization

  Plank, B., Jensen, K. N. & van der Goot, R., dec. 2020, The 28th International Conference on Computational Linguistics. Association for Computational Linguistics, s. 6649–6662

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Lexical Normalization 100%
  • Named Entity Normalization 100%
  • Nested Entities 100%
  • Named Entity Recognition 100%
  • Bidirectional Encoder Representations From Transformers 100%

• NLP North at WNUT-2020 Task 2: Pre-training versus Ensembling for Detection of Informative COVID-19 English Tweets

  Møller, A. G., van der Goot, R. & Plank, B., nov. 2020, Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020). Association for Computational Linguistics, s. 331-336

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Tweets 100%
  • COVID-19 100%
  • BERT Model 100%
  • NLP. 100%
  • Bidirectional Encoder Representations From Transformers 100%

• Norm It! Lexical Normalization for Italian and Its Downstream Effects forDependency Parsing

  van der Goot, R., Ramponi, A., Caselli, T., Cafagna, M. & De Mattei, L., maj 2020, Proceedings of the Twelfth International Conference on Language Resources and Evaluation (LREC 2020). France: European Language Resources Association, s. 6272–6278

  Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

  Åben adgang

  Fil

  • Parsing 100%
  • Lexical Normalization 100%
  • Downstream Effects 100%
  • Social Medium Data 100%
  • Italian 100%