同源反射预测的变压器体系结构

Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP Pub Date : 1900-01-01 DOI:10.18653/v1/2022.sigtyp-1.10

G. Celano

{"title":"同源反射预测的变压器体系结构","authors":"G. Celano","doi":"10.18653/v1/2022.sigtyp-1.10","DOIUrl":null,"url":null,"abstract":"This paper presents the transformer model built to participate in the SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes. It consists of an encoder-decoder architecture with multi-head attention mechanism. Its output is concatenated with the one hot encoding of the language label of an input character sequence to predict a target character sequence. The results show that the transformer outperforms the baseline rule-based system only partially.","PeriodicalId":255232,"journal":{"name":"Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"A Transformer Architecture for the Prediction of Cognate Reflexes\",\"authors\":\"G. Celano\",\"doi\":\"10.18653/v1/2022.sigtyp-1.10\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents the transformer model built to participate in the SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes. It consists of an encoder-decoder architecture with multi-head attention mechanism. Its output is concatenated with the one hot encoding of the language label of an input character sequence to predict a target character sequence. The results show that the transformer outperforms the baseline rule-based system only partially.\",\"PeriodicalId\":255232,\"journal\":{\"name\":\"Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP\",\"volume\":\"45 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.18653/v1/2022.sigtyp-1.10\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18653/v1/2022.sigtyp-1.10","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

本文提出了参与同族反射预测SIGTYP 2022共享任务的变压器模型。它由一个具有多头注意机制的编码器-解码器结构组成。它的输出与输入字符序列的语言标签的唯一编码相连接，以预测目标字符序列。结果表明，该变压器仅部分优于基于规则的基准系统。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A Transformer Architecture for the Prediction of Cognate Reflexes

This paper presents the transformer model built to participate in the SIGTYP 2022 Shared Task on the Prediction of Cognate Reflexes. It consists of an encoder-decoder architecture with multi-head attention mechanism. Its output is concatenated with the one hot encoding of the language label of an input character sequence to predict a target character sequence. The results show that the transformer outperforms the baseline rule-based system only partially.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Proceedings of the 4th Workshop on Research in Computational Linguistic Typology and Multilingual NLP

自引率

0.00%

发文量