← Back to papers
2022 NAACL NAACL 2022

A Transformer Architecture for the Prediction of Cognate Reflexes

Abstract

AbstractThis 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.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning
🧭 Keyword Pioneer — character sequence prediction
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Giuseppe G. A. Celano

Topics

Machine Learning > Core Methods > Classification Deep Learning > Architectures > Transformers

Keywords

transformer architecture multi-head attention encoder-decoder model character sequence prediction cognate reflex
Download PDF

Related papers

EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification 2022
Generating Complement Data for Aspect Term Extraction with GPT-2 2022
Regularized Training of Nearest Neighbor Language Models 2022
Systematicity Emerges in Transformers when Abstract Grammatical Roles Guide Attention 2022
Neural Retriever and Go Beyond: A Thesis Proposal 2022