pith. sign in

arxiv: 2606.28044 · v1 · pith:5QMC7AYRnew · submitted 2026-06-26 · 💻 cs.CL

A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs

Aniket Deroy , Kripabandhu Ghosh , Saptarshi Ghosh This is my paper

Pith reviewed 2026-06-29 04:17 UTC · model grok-4.3

classification 💻 cs.CL
keywords legal case summarizationextractive-abstractive summarizationtree-of-thoughtslarge language modelshybrid promptingDeepSeekLlamajudgement summarization
0
0 comments X

The pith

A tree-of-thoughts inspired extractive-abstractive prompt produces better legal case summaries than pure extractive or abstractive LLM prompts.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a hybrid summarization method for legal judgements that first extracts key segments and then rewrites them abstractively, structured via tree-of-thoughts style reasoning. Experiments compare this approach against standalone extractive and abstractive prompts using the DeepSeek and Llama models. The hybrid prompt is reported to yield superior summaries. A sympathetic reader would care because legal judgements are typically long and dense, so more effective summarization could reduce the time required to extract relevant information. The work positions the hybrid technique as a practical improvement for this domain-specific task.

Core claim

The authors propose a novel tree-of-thoughts inspired extractive-abstractive summarization approach for legal judgement summarization. They conduct experiments using two popular LLMs, DeepSeek and Llama, and compare among extractive, abstractive and extractive-abstractive summarization. Their experiments show that the proposed extractive-abstractive prompt provides better summaries compared to other types of LLM prompts.

What carries the argument

The tree-of-thoughts inspired extractive-abstractive prompt, which directs the LLM to extract important elements from the case and then generate an abstractive summary in a structured reasoning sequence.

If this is right

  • Practitioners can obtain more usable summaries of lengthy legal judgements by switching to hybrid prompts.
  • The same extractive-abstractive structure may improve LLM performance on other long, structured documents.
  • Future prompt engineering for legal tasks should prioritize hybrid modes over single-mode approaches.
  • Model choice between DeepSeek and Llama may matter less than the choice of prompt style for this task.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the hybrid method generalizes, it could reduce the need for separate extractive preprocessing steps in legal NLP pipelines.
  • The approach might be extended by incorporating explicit legal reasoning trees rather than generic thought structures.
  • Testing the method on additional legal datasets with known ground-truth summaries would clarify its robustness.

Load-bearing premise

That the quality judgments used in the experiments reliably reflect legal accuracy and practical usefulness for case summaries.

What would settle it

A follow-up evaluation in which legal experts directly compare the hybrid summaries against extractive and abstractive ones on metrics of factual correctness and completeness, finding no consistent advantage for the hybrid method.

read the original abstract

In recent times, Large Language Models (LLMs) are increasingly being used for legal case judgement summarization. Most prior works have tried traditional extractive and abstractive summarization of case judgements. However, hybrid or extractive-abstractive techniques have not been explored much. In this work, we propose a novel tree-of-thoughts inspired extractive-abstractive summarization approach for legal judgement summarization. We conduct experiments using two popular LLMs, DeepSeek and LLama, and compare among extractive, abstractive and extractive-abstractive summarization. Our experiments show that the proposed extractive-abstractive prompt provides better summaries compared to other types of LLM prompts.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The paper proposes a tree-of-thoughts inspired hybrid extractive-abstractive prompting method for legal case judgment summarization. It compares this approach to pure extractive and abstractive LLM prompts using DeepSeek and Llama models, claiming that the hybrid method produces better summaries based on conducted experiments.

Significance. If the superiority claim is substantiated with proper metrics and protocols, the hybrid ToT-inspired prompting could offer a structured way to combine extractive fidelity with abstractive fluency for legal texts, potentially improving downstream legal applications. The work does not include machine-checked proofs, reproducible code releases, or parameter-free derivations.

major comments (1)
  1. [Experiments / Results] The central claim that 'the proposed extractive-abstractive prompt provides better summaries' (abstract) is load-bearing but unsupported: no dataset (source, size, selection criteria), no automatic metrics (ROUGE, BERTScore or legal-specific), no human evaluation rubric, inter-annotator agreement, or statistical tests are reported anywhere in the manuscript. This prevents verification that observed differences exceed prompt-engineering artifacts.
minor comments (2)
  1. [Abstract] The abstract and introduction use 'better summaries' without defining the quality criteria or evaluation protocol.
  2. [Method] Notation for the tree-of-thoughts structure (e.g., how thoughts are branched and merged in the prompt) is not formalized or illustrated with an example prompt.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for highlighting the critical gaps in experimental reporting. We agree that the current version of the manuscript does not adequately substantiate the central claim and will make substantial revisions to address this.

read point-by-point responses

  1. Referee: [Experiments / Results] The central claim that 'the proposed extractive-abstractive prompt provides better summaries' (abstract) is load-bearing but unsupported: no dataset (source, size, selection criteria), no automatic metrics (ROUGE, BERTScore or legal-specific), no human evaluation rubric, inter-annotator agreement, or statistical tests are reported anywhere in the manuscript. This prevents verification that observed differences exceed prompt-engineering artifacts.

    Authors: We fully acknowledge this limitation. The manuscript as submitted contains only high-level statements about conducting experiments with DeepSeek and Llama but provides none of the required details on data, metrics, or evaluation protocols. In the revised manuscript we will add a complete Experiments section that specifies: (1) the dataset source, size, and selection criteria; (2) the automatic metrics used (ROUGE, BERTScore, and any legal-specific measures); (3) the human evaluation rubric, number of annotators, and inter-annotator agreement; and (4) appropriate statistical tests comparing the three prompting strategies. We will also release the exact prompts and any available code to allow verification that differences are not merely prompt-engineering artifacts. revision: yes

Circularity Check

0 steps flagged

No circularity; empirical prompting comparison is self-contained

full rationale

The paper is an empirical study comparing extractive, abstractive, and hybrid extractive-abstractive LLM prompts for legal summarization, with the central claim resting on experimental outcomes. No equations, fitted parameters, self-definitional reductions, or load-bearing self-citations appear in the provided abstract or description. The derivation chain consists solely of prompt design and result reporting, with no steps that reduce by construction to inputs. This matches the reader's assessment of minimal circularity and qualifies as a normal non-finding under the guidelines.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical model or derivation is present; the work is an empirical prompting study with no free parameters, axioms, or invented entities.

pith-pipeline@v0.9.1-grok · 5652 in / 981 out tokens · 33965 ms · 2026-06-29T04:17:49.891594+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

296 extracted references · 50 canonical work pages

  1. [1]

    2023 , issn =

    Improving colloquial case legal judgment prediction via abstractive text summarization , journal =. 2023 , issn =

    2023

  2. [2]

    Proceedings of the AAAI conference on artificial intelligence , volume=

    Abstractive summarization: A survey of the state of the art , author=. Proceedings of the AAAI conference on artificial intelligence , volume=

  3. [3]

    arXiv preprint arXiv:2303.08774 , year=

    Gpt-4 technical report , author=. arXiv preprint arXiv:2303.08774 , year=

    Pith/arXiv arXiv

  4. [4]

    Proceedings of COLING 2016, the 26th international conference on Computational Linguistics: System Demonstrations , pages=

    Casesummarizer: a system for automated summarization of legal texts , author=. Proceedings of COLING 2016, the 26th international conference on Computational Linguistics: System Demonstrations , pages=

    2016

  5. [5]

    Proceedings of the eighteenth international conference on artificial intelligence and law , pages=

    Incorporating domain knowledge for extractive summarization of legal case documents , author=. Proceedings of the eighteenth international conference on artificial intelligence and law , pages=

  6. [6]

    Journal of King Saud University Computer and Information Sciences , volume=

    LSDK-LegalSum: improving legal judgment summarization using logical structure and domain knowledge , author=. Journal of King Saud University Computer and Information Sciences , volume=. 2025 , publisher=

    2025

  7. [7]

    arXiv preprint arXiv:2501.12948 , year=

    Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning , author=. arXiv preprint arXiv:2501.12948 , year=

    Pith/arXiv arXiv

  8. [8]

    arXiv preprint arXiv:2403.05530 , year=

    Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context , author=. arXiv preprint arXiv:2403.05530 , year=

    Pith/arXiv arXiv

  9. [9]

    arXiv e-prints , pages=

    The llama 3 herd of models , author=. arXiv e-prints , pages=

  10. [10]

    arXiv preprint arXiv:2105.06982 , year=

    Ease: Extractive-abstractive summarization with explanations , author=. arXiv preprint arXiv:2105.06982 , year=

    arXiv

  11. [11]

    2024 , author =

    Low-resource court judgment summarization for common law systems , journal =. 2024 , author =

    2024

  12. [12]

    Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) , pages=

    LongDocFACTScore: Evaluating the Factuality of Long Document Abstractive Summarisation , author=. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) , pages=

    2024

  13. [13]

    L aw B ench: Benchmarking Legal Knowledge of Large Language Models

    Fei, Zhiwei and Shen, Xiaoyu and Zhu, Dawei and Zhou, Fengzhe and Han, Zhuo and Huang, Alan and Zhang, Songyang and Chen, Kai and Yin, Zhixin and Shen, Zongwen and Ge, Jidong and Ng, Vincent. L aw B ench: Benchmarking Legal Knowledge of Large Language Models. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024. doi...

    work page doi:10.18653/v1/2024.emnlp-main.452 2024

  14. [14]

    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

    MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents , author=. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

    2024

  15. [15]

    MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance , author=. Proc. EMNLP-IJCNLP , year=

  16. [16]

    Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation

    Shukla, Abhay and Bhattacharya, Paheli and Poddar, Soham and Mukherjee, Rajdeep and Ghosh, Kripabandhu and Goyal, Pawan and Ghosh, Saptarshi. Legal Case Document Summarization: Extractive and Abstractive Methods and their Evaluation. Proc. AACL-IJCNLP. 2022

    2022

  17. [17]

    extractive summarization: An experimental review , author=

    Abstractive vs. extractive summarization: An experimental review , author=. Applied Sciences , volume=. 2023 , publisher=

    2023

  18. [18]

    Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP) , pages=

    On extractive and abstractive neural document summarization with transformer language models , author=. Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP) , pages=

    2020

  19. [19]

    Proceedings of the ACL 2016 Student Research Workshop , pages=

    From Extractive to Abstractive Summarization: A Journey , author=. Proceedings of the ACL 2016 Student Research Workshop , pages=

    2016

  20. [20]

    Findings of the Association for Computational Linguistics: EMNLP 2022 , pages=

    Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance , author=. Findings of the Association for Computational Linguistics: EMNLP 2022 , pages=

    2022

  21. [21]

    Proceedings of the 3rd International Conference on Information Science and Systems , pages=

    Legal judgement prediction for UK courts , author=. Proceedings of the 3rd International Conference on Information Science and Systems , pages=

  22. [22]

    Themis , pages=

    Characteristic of the Judgement-at-Law , author=. Themis , pages=. 2015 , publisher=

    2015

  23. [23]

    European Journal of Legal Education , volume=

    The Other'LLM': Large Language Models and the Future of Legal Education , author=. European Journal of Legal Education , volume=

  24. [24]

    BERTScore: Evaluating Text Generation with BERT , author=

  25. [25]

    DialDoc 2021 , pages=

    A Template-guided Hybrid Pointer Network for Knowledge-based Task-oriented Dialogue Systems , author=. DialDoc 2021 , pages=

    2021

  26. [26]

    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

    On context utilization in summarization with large language models , author=. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

  27. [27]

    Transactions of the Association for Computational Linguistics , volume=

    Benchmarking large language models for news summarization , author=. Transactions of the Association for Computational Linguistics , volume=. 2024 , publisher=

    2024

  28. [28]

    NPJ digital medicine , volume=

    Evaluating large language models on medical evidence summarization , author=. NPJ digital medicine , volume=. 2023 , publisher=

    2023

  29. [29]

    2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) , pages=

    An unsupervised graph-based hybrid approach for opinion summarization , author=. 2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) , pages=. 2021 , organization=

    2021

  30. [30]

    Journal of AI and Data Mining , volume=

    Graph hybrid summarization , author=. Journal of AI and Data Mining , volume=. 2018 , publisher=

    2018

  31. [31]

    IEEE Access , volume=

    A combined extractive with abstractive model for summarization , author=. IEEE Access , volume=. 2021 , publisher=

    2021

  32. [32]

    Transactions of the Association for Computational Linguistics , volume=

    Template-based abstractive microblog opinion summarization , author=. Transactions of the Association for Computational Linguistics , volume=. 2022 , publisher=

    2022

  33. [33]

    Future Generation Computer Systems , volume=

    Pegasus, a workflow management system for science automation , author=. Future Generation Computer Systems , volume=. 2015 , publisher=

    2015

  34. [34]

    Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop , pages=

    Hie-BART: Document summarization with hierarchical BART , author=. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop , pages=

    2021

  35. [35]

    International Journal of Performability Engineering , volume=

    Fine-tuned t5 for abstractive summarization , author=. International Journal of Performability Engineering , volume=

  36. [36]

    Text Summarization with Pretrained Encoders , author=. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) , pages=. 2019 , organization=

    2019

  37. [37]

    Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

    Get To The Point: Summarization with Pointer-Generator Networks , author=. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

  38. [38]

    International conference on machine learning , pages=

    A convolutional attention network for extreme summarization of source code , author=. International conference on machine learning , pages=. 2016 , organization=

    2016

  39. [39]

    Applied Sciences , volume=

    Abstract text summarization with a convolutional seq2seq model , author=. Applied Sciences , volume=. 2019 , publisher=

    2019

  40. [40]

    Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval , pages=

    Multi-document summarization using cluster-based link analysis , author=. Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval , pages=

  41. [41]

    2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI) , pages=

    Temporal TF-IDF: A high performance approach for event summarization in twitter , author=. 2016 IEEE/WIC/ACM International Conference on Web Intelligence (WI) , pages=. 2016 , organization=

    2016

  42. [42]

    ComTech: Computer, Mathematics and Engineering Applications , volume=

    Single document automatic text summarization using term frequency-inverse document frequency (TF-IDF) , author=. ComTech: Computer, Mathematics and Engineering Applications , volume=

  43. [43]

    2009 2nd IEEE international conference on computer science and information technology , pages=

    Automatic text summarization based on sentences clustering and extraction , author=. 2009 2nd IEEE international conference on computer science and information technology , pages=. 2009 , organization=

    2009

  44. [44]

    Transactions of the Association for Computational Linguistics , volume=

    SummaC: Re-visiting NLI-based models for inconsistency detection in summarization , author=. Transactions of the Association for Computational Linguistics , volume=. 2022 , publisher=

    2022

  45. [45]

    METEOR: An automatic metric for MT evaluation with improved correlation with human judgments , author=. Proc. ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization , pages=

  46. [46]

    Text summarization branches out , pages=

    Rouge: A package for automatic evaluation of summaries , author=. Text summarization branches out , pages=

  47. [47]

    2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021 , pages=

    Efficient Attentions for Long Document Summarization , author=. 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021 , pages=. 2021 , organization=

    2021

  48. [48]

    Advances in Information Retrieval: 41st European Conference on IR Research, ECIR 2019, Cologne, Germany, April 14--18, 2019, Proceedings, Part I 41 , pages=

    A comparative study of summarization algorithms applied to legal case judgments , author=. Advances in Information Retrieval: 41st European Conference on IR Research, ECIR 2019, Cologne, Germany, April 14--18, 2019, Proceedings, Part I 41 , pages=. 2019 , organization=

    2019

  49. [49]

    2024 IEEE International Symposium on Systems Engineering (ISSE) , pages=

    Design, Validation, and Risk Assessment of LLM-Based Generative AI Systems Operating in the Legal Sector , author=. 2024 IEEE International Symposium on Systems Engineering (ISSE) , pages=. 2024 , organization=

    2024

  50. [50]

    The 2024 ACM Conference on Fairness, Accountability, and Transparency , pages=

    (A) I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice , author=. The 2024 ACM Conference on Fairness, Accountability, and Transparency , pages=

    2024

  51. [51]

    Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=

    Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration , author=. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=

    2023

  52. [52]

    Artificial Intelligence and Law , volume=

    Recognizing cited facts and principles in legal judgements , author=. Artificial Intelligence and Law , volume=. 2017 , publisher=

    2017

  53. [53]

    Proceedings of the Natural Legal Language Processing Workshop 2021 , pages=

    jurBERT: A Romanian BERT model for legal judgement prediction , author=. Proceedings of the Natural Legal Language Processing Workshop 2021 , pages=

    2021

  54. [54]

    Critical Realism , pages=

    The praxiology of legal judgement , author=. Critical Realism , pages=. 2013 , publisher=

    2013

  55. [55]

    Proceedings of the Natural Legal Language Processing Workshop 2024 , pages=

    Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models , author=. Proceedings of the Natural Legal Language Processing Workshop 2024 , pages=

    2024

  56. [56]

    How Ready are Pre-trained Abstractive Models and LLMs for Legal Case Judgement Summarization? , author=. Proc. International Workshop on Artificial Intelligence and Intelligent Assistance for Legal Professionals in the Digital Workplace , year=

  57. [57]

    Journal of Management Analytics , volume=

    Fuzzy AHP approach for legal judgement summarization , author=. Journal of Management Analytics , volume=. 2019 , publisher=

    2019

  58. [58]

    Computer Science Review , volume=

    Summarization of legal documents: Where are we now and the way forward , author=. Computer Science Review , volume=. 2021 , publisher=

    2021

  59. [59]

    Applied Soft Computing , volume=

    An approach for extractive text summarization using fuzzy evolutionary and clustering algorithms , author=. Applied Soft Computing , volume=. 2022 , publisher=

    2022

  60. [60]

    Proceedings of 8th International PhD Workshop on Systems and Control , volume=

    Lsa-based multi-document summarization , author=. Proceedings of 8th International PhD Workshop on Systems and Control , volume=. 2007 , organization=

    2007

  61. [61]

    Interactive learning environments , volume=

    Developing summarization skills through the use of LSA-based feedback , author=. Interactive learning environments , volume=. 2000 , publisher=

    2000

  62. [62]

    Journal of artificial intelligence research , volume=

    Lexrank: Graph-based lexical centrality as salience in text summarization , author=. Journal of artificial intelligence research , volume=

  63. [63]

    Proceedings of the 2004 conference on empirical methods in natural language processing , pages=

    Textrank: Bringing order into text , author=. Proceedings of the 2004 conference on empirical methods in natural language processing , pages=

    2004

  64. [64]

    What writing does and how it does it , pages=

    Linguistic discourse analysis: How the language in texts works , author=. What writing does and how it does it , pages=. 2003 , publisher=

    2003

  65. [65]

    2002 , school=

    Automated question answering: template-based approach , author=. 2002 , school=

    2002

  66. [66]

    Proceedings of the 2nd Workshop on Representation Learning for NLP , year=

    NewsQA: A Machine Comprehension Dataset , author=. Proceedings of the 2nd Workshop on Representation Learning for NLP , year=

  67. [67]

    Proceedings of the 2015 conference on empirical methods in natural language processing , pages=

    Wikiqa: A challenge dataset for open-domain question answering , author=. Proceedings of the 2015 conference on empirical methods in natural language processing , pages=

    2015

  68. [68]

    arXiv preprint arXiv:1611.09268 , year=

    Ms marco: A human generated machine reading comprehension dataset , author=. arXiv preprint arXiv:1611.09268 , year=

    Pith/arXiv arXiv

  69. [69]

    Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing , pages=

    QuAC: Question Answering in Context , author=. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing , pages=

    2018

  70. [70]

    Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) , pages=

    Know What You Don’t Know: Unanswerable Questions for SQuAD , author=. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) , pages=

  71. [71]

    Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers , pages=

    Generating natural language question-answer pairs from a knowledge graph using a RNN based question generation model , author=. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers , pages=

  72. [72]

    Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=

    Not all quantifiers are equal: Probing transformer-based language models’ understanding of generalised quantifiers , author=. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing , pages=

    2023

  73. [73]

    Simplifying paragraph-level question generation via transformer language models , author=. PRICAI 2021: Trends in Artificial Intelligence: 18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021, Hanoi, Vietnam, November 8--12, 2021, Proceedings, Part II 18 , pages=. 2021 , organization=

    2021

  74. [74]

    Proceedings of the 2020 5th International Conference on Mathematics and Artificial Intelligence , pages=

    Neural question generation based on Seq2Seq , author=. Proceedings of the 2020 5th International Conference on Mathematics and Artificial Intelligence , pages=

    2020

  75. [75]

    Proceedings of The Web Conference 2020 , pages=

    Asking questions the human way: Scalable question-answer generation from text corpus , author=. Proceedings of The Web Conference 2020 , pages=

    2020

  76. [76]

    , author=

    Pattern Discovery using QG for Question-Answering Pairs. , author=. International Journal on Electrical Engineering & Informatics , volume=

  77. [77]

    A novel belief rule base representation, generation and its inference methodology , journal =

    Jun Liu and Luis Martinez and Alberto Calzada and Hui Wang , keywords =. A novel belief rule base representation, generation and its inference methodology , journal =. 2013 , issn =. doi:https://doi.org/10.1016/j.knosys.2013.08.019 , url =

    work page doi:10.1016/j.knosys.2013.08.019 2013

  78. [78]

    Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 , pages=

    Improving unsupervised extractive summarization with facet-aware modeling , author=. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 , pages=

    2021

  79. [79]

    IEEE/ACM Transactions on Audio, Speech, and Language Processing , volume=

    A Divide-and-Conquer Approach to the Summarization of Long Documents , author=. IEEE/ACM Transactions on Audio, Speech, and Language Processing , volume=. 2020 , publisher=

    2020

  80. [80]

    26th European Conference on Artificial Intelligence , volume=

    Graph-Based Abstractive Summarization of Extracted Essential Knowledge for Low-Resource Scenarios , author=. 26th European Conference on Artificial Intelligence , volume=

Showing first 80 references.