Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology最新文献_第2页

Morpheus: A Neural Network for Jointly Learning Contextual Lemmatization and Morphological Tagging Morpheus:一个联合学习上下文词形化和词形标注的神经网络

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4205

Eray Yildiz, A. C. Tantuğ

{"title":"Morpheus: A Neural Network for Jointly Learning Contextual Lemmatization and Morphological Tagging","authors":"Eray Yildiz, A. C. Tantuğ","doi":"10.18653/v1/W19-4205","DOIUrl":"https://doi.org/10.18653/v1/W19-4205","url":null,"abstract":"In this study, we present Morpheus, a joint contextual lemmatizer and morphological tagger. Morpheus is based on a neural sequential architecture where inputs are the characters of the surface words in a sentence and the outputs are the minimum edit operations between surface words and their lemmata as well as the morphological tags assigned to the words. The experiments on the datasets in nearly 100 languages provided by SigMorphon 2019 Shared Task 2 organizers show that the performance of Morpheus is comparable to the state-of-the-art system in terms of lemmatization. In morphological tagging, on the other hand, Morpheus significantly outperforms the SigMorphon baseline. In our experiments, we also show that the neural encoder-decoder architecture trained to predict the minimum edit operations can produce considerably better results than the architecture trained to predict the characters in lemmata directly as in previous studies. According to the SigMorphon 2019 Shared Task 2 results, Morpheus has placed 3rd in lemmatization and reached the 9th place in morphological tagging among all participant teams.","PeriodicalId":191536,"journal":{"name":"Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128353308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Convolutional neural networks for low-resource morpheme segmentation: baseline or state-of-the-art? 卷积神经网络用于低资源语素分割:基线还是最新技术?

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4218

A. Sorokin

引用次数: 5

THOMAS: The Hegemonic OSU Morphological Analyzer using Seq2seq 霸权OSU形态分析仪使用Seq2seq

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4210

Byung-Doh Oh, Pranav Maneriker, Nan-Jiang Jiang

引用次数: 4

Cognate Projection for Low-Resource Inflection Generation 低资源屈折生成的同源投影

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4202

B. Hauer, Amir Ahmad Habibi, Yixing Luan, Rashed Rubby Riyadh, Grzegorz Kondrak

引用次数: 7

Encoder-decoder models for latent phonological representations of words 单词潜在语音表征的编码器-解码器模型

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4224

Cassandra L. Jacobs, Frederic Mailhot

引用次数: 2

CBNU System for SIGMORPHON 2019 Shared Task 2: a Pipeline Model 面向SIGMORPHON 2019共享任务2的CBNU系统:一个管道模型

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4204

Uygun Shadikhodjaev, Jae Sung Lee

引用次数: 1

IT–IST at the SIGMORPHON 2019 Shared Task: Sparse Two-headed Models for Inflection IT-IST在SIGMORPHON 2019共享任务:稀疏的双头变形模型

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4207

Ben Peters, André F. T. Martins

引用次数: 14

Unsupervised Morphological Segmentation for Low-Resource Polysynthetic Languages 低资源多合成语言的无监督形态分割

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4222

R. Eskander, Judith L. Klavans, S. Muresan

引用次数: 18

CUNI–Malta system at SIGMORPHON 2019 Shared Task on Morphological Analysis and Lemmatization in context: Operation-based word formation 在SIGMORPHON 2019上，cci - malta系统在上下文中的词法分析和词法化共享任务:基于操作的构词法

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4213

Ronald Cardenas, Claudia Borg, Daniel Zeman

{"title":"CUNI–Malta system at SIGMORPHON 2019 Shared Task on Morphological Analysis and Lemmatization in context: Operation-based word formation","authors":"Ronald Cardenas, Claudia Borg, Daniel Zeman","doi":"10.18653/v1/W19-4213","DOIUrl":"https://doi.org/10.18653/v1/W19-4213","url":null,"abstract":"This paper presents the submission by the Charles University-University of Malta team to the SIGMORPHON 2019 Shared Task on Morphological Analysis and Lemmatization in context. We present a lemmatization model based on previous work on neural transducers (Makarov and Clematide, 2018b; Aharoni and Goldberg, 2016). The key difference is that our model transforms the whole word form in every step, instead of consuming it character by character. We propose a merging strategy inspired by Byte-Pair-Encoding that reduces the space of valid operations by merging frequent adjacent operations. The resulting operations not only encode the actions to be performed but the relative position in the word token and how characters need to be transformed. Our morphological tagger is a vanilla biLSTM tagger that operates over operation representations, encoding operations and words in a hierarchical manner. Even though relative performance according to metrics is below the baseline, experiments show that our models capture important associations between interpretable operation labels and fine-grained morpho-syntax labels.","PeriodicalId":191536,"journal":{"name":"Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology","volume":"2437 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130898642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Cross-Lingual Lemmatization and Morphology Tagging with Two-Stage Multilingual BERT Fine-Tuning 两阶段多语言BERT微调的跨语言词源化和词法标注

Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology Pub Date : 1900-01-01 DOI: 10.18653/v1/W19-4203

D. Kondratyuk

引用次数: 20