3 Hits in 2.5 sec

LemmaTag: Jointly Tagging and Lemmatizing for Morphologically-Rich Languages with BRNNs [article]

Daniel Kondratyuk, Tomáš Gavenčiak, Milan Straka, Jan Hajič
2018 arXiv   pre-print
We present LemmaTag, a featureless neural network architecture that jointly generates part-of-speech tags and lemmas for sentences by using bidirectional RNNs with character-level and word-level embeddings  ...  We evaluate our model across several languages with complex morphology, which surpasses state-of-the-art accuracy in both part-of-speech tagging and lemmatization in Czech, German, and Arabic.  ...  CZ.07.1.02/0.0/0.0/16 023/0000108 and it has been using language resources developed by the LINDAT/CLARIN project of the Ministry of Education, Youth and Sports of the Czech Republic (project LM2015071  ... 
arXiv:1808.03703v2 fatcat:ujvw6dc7zbdw7p7kcypanmrja4

75 Languages, 1 Model: Parsing Universal Dependencies Universally

Dan Kondratyuk, Milan Straka
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
We present UDify, a multilingual multi-task model capable of accurately predicting universal part-of-speech, morphological features, lemmas, and dependency trees simultaneously for all 124 Universal Dependencies  ...  We also evaluate for zero-shot learning, with results suggesting that multilingual training provides strong UD predictions even for languages that neither UDify nor BERT have ever been trained on.  ...  Daniel Kondratyuk, Tomáš Gavenčiak, Milan Straka, and Jan Hajič. 2018. Lemmatag: Jointly tagging and lemmatizing for morphologically rich languages with brnns.  ... 
doi:10.18653/v1/d19-1279 dblp:conf/emnlp/KondratyukS19 fatcat:fl7dibtopjamvk4j6molkilfxu

Multi-Team: A Multi-attention, Multi-decoder Approach to Morphological Analysis

Ahmet Üstün, Rob van der Goot, Gosse Bouma, Gertjan van Noord
2019 Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology   unpublished
Our model is a multi-task sequence to sequence neural network, which jointly learns morphological tagging and lemmatization.  ...  This paper describes our submission to SIG-MORPHON 2019 Task 2: Morphological analysis and lemmatization in context.  ...  Furthermore, we would like to thank the Center for Information Technology of the University of Groningen for their support and for providing access to the Peregrine high performance computing cluster.  ... 
doi:10.18653/v1/w19-4206 fatcat:g37ndtu5x5hfjdr3eofzjc5awy