{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neural-morphological-tagging-from-characters","title":"Neural Morphological Tagging from Characters for Morphologically Rich Languages","arxiv_id":"1606.06640","date":"2016-06-21","proceeding":null,"authors":["Georg Heigold","Guenter Neumann","Josef van Genabith"],"abstract":"This paper investigates neural character-based morphological tagging for\nlanguages with complex morphology and large tag sets. We systematically explore\na variety of neural architectures (DNN, CNN, CNNHighway, LSTM, BLSTM) to obtain\ncharacter-based word vectors combined with bidirectional LSTMs to model\nacross-word context in an end-to-end setting. We explore supplementary use of\nword-based vectors trained on large amounts of unlabeled data. Our experiments\nfor morphological tagging suggest that for \"simple\" model configurations, the\nchoice of the network architecture (CNN vs. CNNHighway vs. LSTM vs. BLSTM) or\nthe augmentation with pre-trained word embeddings can be important and clearly\nimpact the accuracy. Increasing the model capacity by adding depth, for\nexample, and carefully optimizing the neural networks can lead to substantial\nimprovements, and the differences in accuracy (but not training time) become\nmuch smaller or even negligible. Overall, our best morphological taggers for\nGerman and Czech outperform the best results reported in the literature by a\nlarge margin.","url_abs":"http://arxiv.org/abs/1606.06640v1","url_pdf":"http://arxiv.org/pdf/1606.06640v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-morphological-tagging-from-characters","repo_url":"https://github.com/ziegler-ingo/cleavage_prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"morphological-tagging","task_name":"Morphological Tagging"},{"task_slug":"tag","task_name":"TAG"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.06640","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}