Parsing with Context Embeddings
العنوان: | Parsing with Context Embeddings |
---|---|
المؤلفون: | Berkay Furkan Önder, Deniz Yuret, Ömer Kırnap |
المساهمون: | Yüret, Deniz (ORCID 0000-0002-7039-0046 & YÖK ID 179996), Önder, Berkay Furkan, Kırnap, Ömer, College of Engineering, Graduate School of Sciences and Engineering, Department of Computer Engineering |
المصدر: | CoNLL Shared Task (2) Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies |
بيانات النشر: | Association for Computational Linguistics, 2017. |
سنة النشر: | 2017 |
مصطلحات موضوعية: | Parsing, Plain text, business.industry, Computer science, Context (language use), computer.file_format, Top-down parsing, computer.software_genre, Parser combinator, Computer engineering, Embeddings, Long short-term memory, Natural language processing systems, Decision modeling, Language model, Multi layer perceptron, Treebanks, Computational linguistics, S-attributed grammar, Artificial intelligence, business, computer, Natural language processing, Bottom-up parsing |
الوصف: | We introduce context embeddings, dense vectors derived from a language model that represent the left/right context of a word instance, and demonstrate that context embeddings significantly improve the accuracy of our transition based parser. Our model consists of a bidirectional LSTM (BiLSTM) based language model that is pre-trained to predict words in plain text, and a multi-layer perceptron (MLP) decision model that uses features from the language model to predict the correct actions for an ArcHybrid transition based parser. We participated in the CoNLL 2017 UD Shared Task as the “Koç University” team and our system was ranked 7th out of 33 systems that parsed 81 treebanks in 49 languages. Scientific and Technological Research Council of Turkey (TÜBİTAK) |
وصف الملف: | |
الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9aa9077cbfdf59c0bc3223858ed69440Test https://doi.org/10.18653/v1/k17-3008Test |
حقوق: | OPEN |
رقم الانضمام: | edsair.doi.dedup.....9aa9077cbfdf59c0bc3223858ed69440 |
قاعدة البيانات: | OpenAIRE |
الوصف غير متاح. |