Viktor Hangya

Ludwig-Maximilians-Universität München

I am working in Prof. Dr. Alexander M. Fraser’s group at the Center for Information and Language Processing (CIS) at LMU Munich, Germany. My research focuses on cross-lingual tasks and machine translation in low resource setups. Previously, I worked on various sentiment analysis tasks in the Natural Language Processing Group at the University of Szeged, Hungary.

Contact Information

Ludwig-Maximilians-Universität München
Centrum für Informations- und Sprachverarbeitung
Viktor Hangya
Oettingenstraße 67
D-80538 München

Room: 126
E-mail: hangyav [-at-] cis.uni-muenchen.de

Publications

  1. Irina Bigoulaeva, Viktor Hangya, Iryna Gurevych, and Alexander Fraser. 2023. Label modification and bootstrapping for zero-shot cross-lingual hate speech detection. Language Resources and Evaluation:1–32. Link
  2. Viktor Hangya and Alexander Fraser. 2023. How to Solve Few-Shot Abusive Content Detection Using the Data We Actually Have. arXiv preprint arXiv:2305.14081. Link
  3. Viktor Hangya and Alexander Fraser. 2023. LMU at HaSpeeDe3: Multi-Dataset Training for Cross-Domain Hate Speech Detection. In The Eighth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2023). EVALITA. Link
  4. Wen Lai, Viktor Hangya, and Alexander Fraser. 2023. Extending Multilingual Machine Translation through Imitation Learning. arXiv preprint arXiv:2311.08538. Link
  5. Viktor Hangya, Silvia Severini, Radoslav Ralev, Alexander Fraser, and Hinrich Schütze. 2023. Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages. In Proceedings of the 3rd Workshop on Multi-lingual Representation Learning (MRL), pages 95–105. Link
  6. Silvia Severini, Viktor Hangya, Masoud Jalili Sabet, Alexander Fraser, and Hinrich Schütze. 2022. Don’t Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings. In Proceedings of the 15th Workshop on Building and Using Comparable Corpora, pages 15–22. Link
  7. Hossain Shaikh Saadi, Viktor Hangya, Tobias Eder, and Alexander Fraser. 2022. Comparative Analysis of Cross-lingual Contextualized Word Embeddings. In Proceedings of the The 2nd Workshop on Multi-lingual Representation Learning, pages 64–75. Association for Computational Linguistics. Link
  8. Viktor Hangya, Hossain Shaikh Saadi, and Alexander Fraser. 2022. Improving Low-Resource Languages in Pre-Trained Multilingual Language Models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11993–12006. Link
  9. Tobias Eder, Viktor Hangya, and Alexander Fraser. 2021. Anchor-based Bilingual Word Embeddings for Low-Resource Languages. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 227–232. Link
  10. Irina Bigoulaeva, Viktor Hangya, and Alexander Fraser. 2021. Cross-Lingual Transfer Learning for Hate Speech Detection. In Proceedings of the First Workshop on Language Technology for Equality, Diversity and Inclusion, pages 15–25. Link
  11. Lisa Woller, Viktor Hangya, and Alexander Fraser. 2021. Do not neglect related languages: The case of low-resource Occitan cross-lingual word embeddings. In Proceedings of the 1st Workshop on Multilingual Representation Learning, pages 41–50. Link
  12. Denis Peskov, Viktor Hangya, Jordan Boyd-Graber, and Alexander Fraser. 2021. Adapting Entities across Languages and Cultures. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3725–3750. Link
  13. Viktor Hangya, Qianchu Liu, Dario Stojanovski, Alexander Fraser, and Anna Korhonen. 2021. Improving Machine Translation of Rare and Unseen Word Senses. In Proceedings of the Sixth Conference on Machine Translation, pages 614–624. Link
  14. Leah Michel, Viktor Hangya, and Alexander Fraser. 2020. Exploring Bilingual Word Embeddings for Hiligaynon, a Low-Resource Language. In Proceedings of The 12th Language Resources and Evaluation Conference, pages 2566–2573. Link
  15. Viktor Hangya and Alexander Fraser. 2020. Towards Handling Compositionality in Low-Resource Bilingual Word Induction. In Proceedings of the 14th Conference of the Association for Machine Translation in the Americas, pages 89–101. Link
  16. Viktor Hangya. 2020. Target-Level Sentiment Analysis on Various Genres. Szte. PhD Thesis. Link
  17. Jindrich Libovicky, Viktor Hangya, Helmut Schmid, and Alexander Fraser. 2020. The LMU Munich System for the WMT20 Very Low Resource Supervised MT Task. In Proceedings ofthe 5th Conference on Machine Translation, pages 1102–1109. Link
  18. Silvia Severini, Viktor Hangya, Alexander Fraser, and Hinrich Schütze. 2020. LMU Bilingual Dictionary Induction System with Word Surface Similarity Scores for BUCC 2020. In Proceedings ofthe 13th Workshop on Building and Using Comparable Corpora, pages 49–55. Link
  19. Silvia Severini, Viktor Hangya, Alexander Fraser, and Hinrich Schütze. 2020. Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6044–6055. Link
  20. Dario Stojanovski, Viktor Hangya, Matthias Huck, and Alexander Fraser. 2019. The LMU Munich Unsupervised Machine Translation System for WMT19. In Proceedings of the ACL 2019 Forth Conference on Machine Translation (WMT), pages 592–598. Link
  21. Matthias Huck, Viktor Hangya, and Alexander Fraser. 2019. Better OOV Translation with Bilingual Terminology Mining. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5809–5815. Link
  22. Viktor Hangya and Alexander Fraser. 2019. Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1224–1234. Link
  23. Dario Stojanovski, Viktor Hangya, Matthias Huck, and Alexander Fraser. 2018. The LMU Munich Unsupervised Machine Translation Systems. In Proceedings of the EMNLP 2018 Third Conference on Machine Translation (WMT), pages 513–521.
  24. Viktor Hangya and Alexander Fraser. 2018. An Unsupervised System for Parallel Corpus Filtering. In Proceedings of the EMNLP 2018 Third Conference on Machine Translation (WMT), pages 882–887.
  25. Fabienne Braune, Viktor Hangya, Tobias Eder, and Alexander Fraser. 2018. Evaluating bilingual word embeddings on the long tail. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 188–193. Link
  26. Viktor Hangya, Fabienne Braune, Alexander Fraser, and Hinrich Schütze. 2018. Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 810–820. Link
  27. Viktor Hangya, Fabienne Braune, Yuliya Kalasouskaya, and Alexander Fraser. 2018. Unsupervised Parallel Sentence Extraction from Comparable Corpora. In Proceedings of the 15th International Workshop on Spoken Language Translation (IWSLT), pages 7–13.
  28. Matthias Huck, Dario Stojanovski, Viktor Hangya, and Alexander Fraser. 2018. LMU Munich’s Neural Machine Translation Systems at WMT 2018. In Proceedings of the EMNLP 2018 Third Conference on Machine Translation (WMT), volume 2, pages 648–654.
  29. Viktor Hangya and Richárd Farkas. 2017. A comparative empirical study on social media sentiment analysis over various genres and languages. Artificial Intelligence Review, 47(4):485–505. Link
  30. Viktor Hangya, Zsolt Szántó, and Richárd Farkas. 2017. Latent Syntactic Structure-Based Sentiment Analysis. In Proceeding of the 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA 2017), pages 248–254. Link
  31. Martina Katalin Szabó, Veronika Vincze, Katalin Simkó, Viktor Varga, and Viktor Hangya. 2016. A Hungarian sentiment corpus manually annotated at aspect level. In Proceedings of the 10th International Conference on Language Resources and Evaluation, LREC 2016, pages 2873–2878.
  32. Viktor Hangya. 2015. Automatic Construction of Domain Specific Sentiment Lexicons for Hungarian. In Proceedings of the 18th International Conference on Text, Speech and Dialogue (TSD 2015), pages 201–208. Link
  33. Viktor Hangya, Gábor Berend, István Varga, and Richárd Farkas. 2014. SZTE-NLP: Aspect level opinion mining exploiting syntactic cues. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 610–614. Link
  34. Viktor Hangya and Richárd Farkas. 2013. Filtering and Polarity Detection for Reputation Management on Tweets. In Proceedings of the 4th Conference and Labs of the Evaluation Forum: Working Notes. Link
  35. Viktor Hangya and Richárd Farkas. 2013. Target-oriented opinion mining from tweets. In 4th IEEE International Conference on Cognitive Infocommunications (CogInfoCom 2013), pages 251–254. IEEE. Link
  36. Viktor Hangya, Gábor Berend, and Richárd Farkas. 2013. SZTE-NLP: Sentiment Detection on Twitter Messages. In Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013), pages 549–553. Link