GAE-ISumm: Unsupervised Graph-Based Summarization of Indian Languages
It addresses the lack of effective summarization models for Indian languages, which are limited by morphological and semantic differences, though it is incremental as it adapts existing graph autoencoder methods to a new domain.
The paper tackles document summarization for low-resource Indian languages by proposing GAE-ISumm, an unsupervised graph-based model, which achieves competitive or better than state-of-the-art results on seven languages and reports benchmark results on a new Telugu dataset.
Document summarization aims to create a precise and coherent summary of a text document. Many deep learning summarization models are developed mainly for English, often requiring a large training corpus and efficient pre-trained language models and tools. However, English summarization models for low-resource Indian languages are often limited by rich morphological variation, syntax, and semantic differences. In this paper, we propose GAE-ISumm, an unsupervised Indic summarization model that extracts summaries from text documents. In particular, our proposed model, GAE-ISumm uses Graph Autoencoder (GAE) to learn text representations and a document summary jointly. We also provide a manually-annotated Telugu summarization dataset TELSUM, to experiment with our model GAE-ISumm. Further, we experiment with the most publicly available Indian language summarization datasets to investigate the effectiveness of GAE-ISumm on other Indian languages. Our experiments of GAE-ISumm in seven languages make the following observations: (i) it is competitive or better than state-of-the-art results on all datasets, (ii) it reports benchmark results on TELSUM, and (iii) the inclusion of positional and cluster information in the proposed model improved the performance of summaries.