Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction (2310.03414v1)

Published 5 Oct 2023 in cs.CL

Abstract: Multi-document summarization is a challenging task due to its inherent subjective bias, highlighted by the low inter-annotator ROUGE-1 score of 0.4 among DUC-2004 reference summaries. In this work, we aim to enhance the objectivity of news summarization by focusing on the main event of a group of related news documents and presenting it coherently with sufficient context. Our primary objective is to succinctly report the main event, ensuring that the summary remains objective and informative. To achieve this, we employ an extract-rewrite approach that incorporates a main-event biased monotone-submodular function for content selection. This enables us to extract the most crucial information related to the main event from the document cluster. To ensure coherence, we utilize a fine-tuned LLM for rewriting the extracted content into a coherent text. The evaluation using objective metrics and human evaluators confirms the effectiveness of our approach, as it surpasses potential baselines, demonstrating excellence in both content coverage, coherence, and informativeness.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Evaluating topic coherence using distributional semantics. In Proceedings of the 10th international conference on computational semantics (IWCS 2013)–Long Papers, 13–22.
  2. Fast and Robust Compressive Summarization with Dual Decomposition and Multi-Task Learning. In ACL (1), 196–206.
  3. The internal state of an llm knows when its lying. arXiv preprint arXiv:2304.13734.
  4. Aggregation via set partitioning for natural language generation. In Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, 359–366. Citeseer.
  5. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150.
  6. Extending context window of large language models via positional interpolation. arXiv preprint arXiv:2306.15595.
  7. Abstractive sentence summarization with attentive recurrent neural networks. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 93–98.
  8. Discourse as a function of event: Profiling discourse structure in news articles around the main event. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.
  9. Towards coherent multi-document summarization. In Proceedings of the 2013 conference of the North American chapter of the association for computational linguistics: Human language technologies, 1163–1173.
  10. Global inference for sentence compression: An integer linear programming approach. Journal of Artificial Intelligence Research, 31: 399–429.
  11. Dueck, D. 2009. Affinity propagation: clustering data by passing messages. University of Toronto Toronto, ON, Canada.
  12. Neural Natural Language Generation: A Survey on Multilinguality, Multimodality, Controllability and Learning. Journal of Artificial Intelligence Research, 73: 1131–1207.
  13. Ontology Graph Embeddings and ILP for Financial Forecasting. In Inductive Logic Programming, Proceedings of the 30th International Conference:. Springer.
  14. Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model. arXiv preprint arXiv:1906.01749.
  15. A large-scale multi-document summarization dataset from the Wikipedia current events portal. arXiv preprint arXiv:2005.10070.
  16. Globalizing BERT-based transformer architectures for long document summarization. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, 1792–1810.
  17. Overview and importance of data quality for machine learning tasks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, 3561–3562.
  18. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461.
  19. Li, Y. 2023. Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering. arXiv preprint arXiv:2304.12102.
  20. Lin, C.-Y. 2003. Improving summarization performance by sentence compression: a pilot study. In Proceedings of the sixth international workshop on Information retrieval with Asian languages-Volume 11, 1–8. Association for Computational Linguistics.
  21. A class of submodular functions for document summarization. In Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, 510–520.
  22. Liu, Y. 2019. Fine-tune BERT for extractive summarization. arXiv preprint arXiv:1903.10318.
  23. Text summarization with pretrained encoders. arXiv preprint arXiv:1908.08345.
  24. Subtree Extractive Summarization via Submodular Maximization. In ACL (1), 1023–1032. Citeseer.
  25. Sentence-t5: Scalable sentence encoders from pre-trained text-to-text models. arXiv preprint arXiv:2108.08877.
  26. The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116.
  27. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084.
  28. A neural attention model for abstractive sentence summarization. arXiv preprint arXiv:1509.00685.
  29. Get to the point: Summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368.
  30. A graph-to-sequence model for AMR-to-text generation. arXiv preprint arXiv:1805.02473.
  31. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  32. Van Dijk, T. A. 2013. News as discourse. Routledge.
  33. Multi-document summarization via sentence-level semantic analysis and symmetric matrix factorization. In Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, 307–314. ACM.
  34. Learning deep transformer models for machine translation. arXiv preprint arXiv:1906.01787.
  35. Learning Neural Templates for Text Generation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 3174–3187.
  36. How” Multi” is Multi-Document Summarization? arXiv preprint arXiv:2210.12688.
  37. PRIMERA: Pyramid-based masked sentence pre-training for multi-document summarization. arXiv preprint arXiv:2110.08499.
  38. A cross-domain transferable neural coherence model. arXiv preprint arXiv:1905.11912.
  39. Sentence compression as a component of a multi-document summarization system. In Proceedings of the 2006 Document Understanding Workshop, New York.
  40. Pegasus: Pre-training with extracted gap-sentences for abstractive summarization. In International Conference on Machine Learning, 11328–11339. PMLR.
  41. When radiology report generation meets knowledge graph. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, 12910–12917.
  42. Extractive Summarization as Text Matching. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 6197–6208.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Litton J Kurisinkel (4 papers)
  2. Nancy F. Chen (97 papers)
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now