SMT vs NMT: A Comparison over Hindi and Bengali Simple Sentences

In the present article, we identified the qualitative differences between Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) outputs. We have tried to answer two important questions: 1. Does NMT perform equivalently well with respect to SMT and 2. Does it add extra flavor in improving the quality of MT output by employing simple sentences as training units. In order to obtain insights, we have developed three core models viz., SMT model based on Moses toolkit, followed by character and word level NMT models. All of the systems use English-Hindi and English-Bengali language pairs containing simple sentences as well as sentences of other complexity. In order to preserve the translations semantics with respect to the target words of a sentence, we have employed soft-attention into our word level NMT model. We have further evaluated all the systems with respect to the scenarios where they succeed and fail. Finally, the quality of translation has been validated using BLEU and TER metrics along with manual parameters like fluency, adequacy etc. We observed that NMT outperforms SMT in case of simple sentences whereas SMT outperforms in case of all types of sentence.

• Publication year

  2018

• Venue

  ICON

• Publication date

  2018-12-12

• Fields of study

  Linguistics, Computer Science

• Identifiers
  arXiv 1812.04898
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation

  2019cited by this paper
• Attention is All you Need

  2017cited by this paper
• BUCC2017: A Hybrid Approach for Identifying Parallel Sentences in Comparable Corpora

  2017cited by this paper
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

  2016cited by this paper
• A Character-level Decoder without Explicit Segmentation for Neural Machine Translation

  2016cited by this paper
• WMT2016: A Hybrid Approach to Bilingual Document Alignment

  2016cited by this paper
• Improved Neural Machine Translation with SMT Features

  2016cited by this paper
• Effective Approaches to Attention-based Neural Machine Translation

  2015cited by this paper
• Statistical Machine Translation

  2014cited by this paper
• A Recursive Recurrent Neural Network for Statistical Machine Translation

  2014cited by this paper
• Addressing the Rare Word Problem in Neural Machine Translation

  2014cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

  2014cited by this paper
• The Stanford CoreNLP Natural Language Processing Toolkit

  2014cited by this paper
• Recurrent Continuous Translation Models

  2013cited by this paper
• Decoding with Large-Scale Neural Language Models Improves Translation

  2013cited by this paper
• KenLM: Faster and Smaller Language Model Queries

  2011cited by this paper
• Eye tracking as an MT evaluation technique

  2010cited by this paper
• Large-Scale Machine Learning with Stochastic Gradient Descent

  2010cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• A Study of Translation Edit Rate with Targeted Human Annotation

  2006cited by this paper
• A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION

  2005cited by this paper
• tRuEcasIng

  2003cited by this paper
• A Systematic Comparison of Various Statistical Alignment Models

  2003cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• Long Short-Term Memory

  1997influential reference
• Machine translation of languages

  1956cited by this paper
• Translation

  1873cited by this paper

• An empirical investigation of the neural base approaches based on the sentence length using low-resource language: English-to-Nyishi

  2025cites this paper
• Comparative analysis of machine translation for Hindi-Dogri text using rule-based, statistical, and neural approaches

  2025cites this paper
• Comparative study of low resource Digaru language using SMT and NMT

  2024cites this paper
• An empirical analysis on statistical and neural machine translation system for English to Mizo language

  2023cites this paper
• Statistical Machine Translation for Indic Languages

  2023cites this paper
• Simplification of English and Bengali Sentences for Improving Quality of Machine Translation

  2022cites this paper
• Bilingual Parallel Corpora: A Major Resource for Developing Computational Tools for Automatic Processing of Hindi-Dogri Language Pair

  2022cites this paper
• Pseudocode Generation from Source Code Using the BART Model

  2022cites this paper
• Source Code Generation-based on NLP and Ontology

  2022cites this paper
• Investigating the roles of sentiment in machine translation

  2021cites this paper
• SMT Versus NMT: An Experiment with Punjabi–English

  2021cites this paper
• An Improved English-to-Mizo Neural Machine Translation

  2021cites this paper
• Preparation of Sentiment tagged Parallel Corpus and Testing its effect on Machine Translation

  2020cites this paper
• Data Augmentation and Terminology Integration for Domain-Specific Sinhala-English-Tamil Statistical Machine Translation

  2020cites this paper
• The Roles of Language Models and Hierarchical Models in Neural Sequence-to-Sequence Prediction

  2020cites this paper
• Code-Mixed to Monolingual Translation Framework

  2019cites this paper
• JUMT at WMT2019 News Translation Task: A Hybrid Approach to Machine Translation for Lithuanian to English

  2019cites this paper
• Pinyin as a Feature of Neural Machine Translation for Chinese Speech Recognition Error Correction

  2019cites this paper
• Sentence Simplification using Syntactic Parse trees

  2019cites this paper
• Neural Machine Translation: A Review

  2019cites this paper