English-Bhojpuri SMT System: Insights from the Karaka Model
arXiv:1905.02239
Abstract
This thesis has been divided into six chapters namely: Introduction, Karaka Model and it impacts on Dependency Parsing, LT Resources for Bhojpuri, English-Bhojpuri SMT System: Experiment, Evaluation of EB-SMT System, and Conclusion. Chapter one introduces this PhD research by detailing the motivation of the study, the methodology used for the study and the literature review of the existing MT related work in Indian Languages. Chapter two talks of the theoretical background of Karaka and Karaka model. Along with this, it talks about previous related work. It also discusses the impacts of the Karaka model in NLP and dependency parsing. It compares Karaka dependency and Universal Dependency. It also presents a brief idea of the implementation of these models in the SMT system for English-Bhojpuri language pair.
arXiv comment211 pages and Submitted at JNU New Delhi
References in corpus (7)
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Recurrent Convolutional Neural Networks for Discourse Compositionality
- Automatic Identification of Closely-related Indian Languages: Resources and Experiments
- Reordering rules for English-Hindi SMT
- Nematus: a Toolkit for Neural Machine Translation
- Demo of Sanskrit-Hindi SMT System
- The RGNLP Machine Translation Systems for WAT 2018