mlsanityData to 7 Oct 2026

GAE-ISumm: Unsupervised Graph-Based Summarization of Indian Languages

arXiv 2212.12937 ↗First posted 25 Dec 2022cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 48 references that are in the map. First posted on arXiv 25 Dec 2022.

Builds on

24 of 48 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  5. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  6. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  7. 2016Variational Graph Auto-Encoderscited by 1,373
  8. 2015Teaching Machines to Read and Comprehendcited by 1,039
  9. 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
  10. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  11. 2019Text Summarization with Pretrained Encoderscited by 553
  12. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 364
12 more
  1. 2021XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languagescited by 346
  2. 2018Graph Convolutional Networks for Text Classificationcited by 345
  3. 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 245
  4. 2017Encoding Sentences with Graph Convolutional Networks for Semantic Role Labelingcited by 137
  5. 2019Discourse-Aware Neural Extractive Text Summarizationcited by 104
  6. 2017Graph-based Neural Multi-Document Summarizationcited by 54
  7. 2020SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compressioncited by 24
  8. 2020Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networkscited by 22
  9. 2020Unsupervised Extractive Summarization by Pre-training Hierarchical Transformerscited by 16
  10. 2021Unsupervised Abstractive Summarization of Bengali Text Documentscited by 9
  11. 2022Multi-Task Text Classification using Graph Convolutional Networks for Large-Scale Low Resource Languagecited by 3
  12. 2020Selective Attention Encoders by Syntactic Graph Convolutional Networks for Document Summarizationcited by 1

Built on by

Not cited yet.