# Neural Machine Translation for Malayalam Paraphrase Generation

arXiv: https://arxiv.org/abs/2401.17827 · HTML: https://mlsanity.com/paper/2401.17827/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 31 Jan 2024.

## Builds on (most cited first, 8 of 8)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages](https://mlsanity.com/paper/2104.05596/) (2021)
- [Neural Question Generation from Text: A Preliminary Study](https://mlsanity.com/paper/1704.01792/) (2017)
- [Paraphrase Generation with Deep Reinforcement Learning](https://mlsanity.com/paper/1711.00279/) (2017)
- [A Deep Generative Framework for Paraphrase Generation](https://mlsanity.com/paper/1709.05074/) (2017)
- [Style-transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metric](https://mlsanity.com/paper/2004.05001/) (2020)

## Abstract (arXiv)

This study explores four methods of generating paraphrases in Malayalam, utilizing resources available for English paraphrasing and pre-trained Neural Machine Translation (NMT) models. We evaluate the resulting paraphrases using both automated metrics, such as BLEU, METEOR, and cosine similarity, as well as human annotation. Our findings suggest that automated evaluation measures may not be fully appropriate for Malayalam, as they do not consistently align with human judgment. This discrepancy underscores the need for more nuanced paraphrase evaluation approaches especially for highly agglutinative languages.