Abstractive Text Summarization for Sanskrit Prose: A Study of Methods and Approaches
The authors present a work-in-progress in the field of Abstractive Text Summarization (ATS) for Sanskrit Prose {--} a first attempt at ATS for Sanskrit (SATS). We will evaluate recent approaches and methods used for ATS and argue for the ones to be adopted for Sanskrit prose considering the unique properties of the language. There are three goals of SATS - to make manuscript summaries, to enrich the semantic processing of Sanskrit, and to improve the information retrieval systems in the language. While Extractive Text Summarization (ETS) is an important method, the summaries it generates are not always coherent. For qualitative coherent summaries, ATS is considered a better option by scholars. This paper reviews various ATS/ETS approaches for Sanskrit and other Indian Languages done till date. In the preliminary overview, authors conclude that of the two available approaches - structure-based and semantic-based - the latter would be viable owing to the rich morphology of Sanskrit. Moreover, a graph-based method may also be suitable. The second suggested method is the supervised-learning method. The authors also suggest attempting cross-lingual summarization as an extension to this work in future.
Code (0)
등록된 구현이 없습니다.
Tasks
Abstractive Text SummarizationExtractive Text SummarizationInformation RetrievalRetrievalText SummarizationSimilar Papers 제목 키워드 기반
Abstractive Text Summarization for Contemporary Sanskrit Prose: Issues and Challenges
This thesis presents Abstractive Text Summarization models for contemporary Sanskrit prose. The first chapter, titled Introduction, presents the motivation behind this work, the research questions, and the conceptual fra…
Abstractive Text SummarizationLanguage ModelingLanguage ModellingText SummarizationSāmayik: A Benchmark and Dataset for English-Sanskrit Translation
We release S\={a}mayik, a dataset of around 53,000 parallel English-Sanskrit sentences, written in contemporary prose. Sanskrit is a classical language still in sustenance and has a rich documented heritage. However, due…
Machine TranslationTranslationStill Not There: Can LLMs Outperform Smaller Task-Specific Seq2Seq Models on the Poetry-to-Prose Conversion Task?
Large Language Models (LLMs) are increasingly treated as universal, general-purpose solutions across NLP tasks, particularly in English. But does this assumption hold for low-resource, morphologically rich languages such…
Poetry to Prose Conversion in Sanskrit as a Linearisation Task: A Case for Low-Resource Languages
The word ordering in a Sanskrit verse is often not aligned with its corresponding prose order. Conversion of the verse to its corresponding prose helps in better comprehension of the construction. Owing to the resource c…
San-BERT: Extractive Summarization for Sanskrit Documents using BERT and it's variants
In this work, we develop language models for the Sanskrit language, namely Bidirectional Encoder Representations from Transformers (BERT) and its variants: A Lite BERT (ALBERT), and Robustly Optimized BERT (RoBERTa) usin…
ClusteringExtractive SummarizationExtractive Text SummarizationText Summarization