2000 character limit reached
Grammatical gender in Swedish is predictable using recurrent neural networks (2306.10869v1)
Published 19 Jun 2023 in cs.CL and cs.LG
Abstract: The grammatical gender of Swedish nouns is a mystery. While there are few rules that can indicate the gender with some certainty, it does in general not depend on either meaning or the structure of the word. In this paper we demonstrate the surprising fact that grammatical gender for Swedish nouns can be predicted with high accuracy using a recurrent neural network (RNN) working on the raw character sequence of the word, without using any contextual information.
- Ali Basirat and Marc Tang. 2018. Linguistic information in word embeddings. In International Conference on Agents and Artificial Intelligence, pages 492–513. Springer.
- Learning long-term dependencies with gradient descent is difficult. Neural Networks, IEEE Transactions on, 5(2):157–166.
- SALDO: a touch of yin to WordNet’s yang. Language Resources and Evaluation, 47(4):1191–1211.
- Learning phrase representations using rnn encoder-decoder for statistical machine translation. In EMNLP, pages 1724–1734. ACL.
- The SIGMORPHON 2016 shared task – morphological reinflection. In Proceedings of the 14th Annual SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 10–22.
- Silviu Cucerzan and David Yarowsky. 2003. Minimally supervised induction of grammatical gender. In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1, pages 40–47. Association for Computational Linguistics.
- Staged approach for grammatical gender identification of nouns using association rule mining and classification. Research in Computing Science, 90:359–371.
- The romanian neuter examined through a two-gender n-gram classification system. In LREC, pages 907–910.
- Institutet för språk och folkminnen. 2019. Språkrådgivning.
- Sepp Hochreiter. 1998. The vanishing gradient problem during learning recurrent neural nets and problem solutions. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 6(02):107–116.
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780.
- Katharina Kann and Hinrich Schütze. 2016. MED: The LMU system for the SIGMORPHON 2016 shared task on morphological reinflection. In Proceedings of the 14th Annual SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 62–70.
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
- Olof Mogren and Richard Johansson. 2017. Character-based recurrent neural networks for morphological relational reasoning. In Proceedings of the First Workshop on Subword and Character Level Models in NLP, pages 57–63.
- Vivi Nastase and Marius Popescu. 2009. What’s in a name?: in some languages, grammatical gender. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 3-Volume 3, pages 1368–1377. Association for Computational Linguistics.
- Rebbe-Gullberg-Ivan. 1954. Svensk språklära. Svenska Bokförlaget.
- Svenska akademiens grammatik. Svenska akademien.