請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94174完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 盧信銘 | zh_TW |
| dc.contributor.advisor | Hsin-Min Lu | en |
| dc.contributor.author | 沈冠伶 | zh_TW |
| dc.contributor.author | Kuan-Ling Shen | en |
| dc.date.accessioned | 2024-08-14T17:04:58Z | - |
| dc.date.available | 2024-08-15 | - |
| dc.date.copyright | 2024-08-14 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-07-30 | - |
| dc.identifier.citation | Aghajanyan, A., Gupta, A., Shrivastava, A., Chen, X., Zettlemoyer, L., & Gupta, S. (2021, November). Muppet: Massive Multi-task Representations with Pre-Finetuning. In M.-F. Moens, X. Huang, L. Specia, & S. W.-t. Yih, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing Online and Punta Cana, Dominican Republic.
Chen, C.-C., Huang, H.-H., & Chen, H.-H. (2021a). Nquad: 70,000+ questions for machine comprehension of the numerals in text. Proceedings of the 30th ACM International Conference on Information & Knowledge Management, Chen, C.-C., Huang, H.-H., Takamura, H., & Chen, H.-H. (2019, July). Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments. In A. Korhonen, D. Traum, & L. Màrquez, Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics Florence, Italy. Chen, C.-C., Takamura, H., Kobayashi, I., & Miyao, Y. (2023, May). Improving Numeracy by Input Reframing and Quantitative Pre-Finetuning Task. In A. Vlachos & I. Augenstein, Findings of the Association for Computational Linguistics: EACL 2023 Dubrovnik, Croatia. Chen, J., Tang, J., Qin, J., Liang, X., Liu, L., Xing, E. P., & Lin, L. (2021b). GeoQA: A geometric question answering benchmark towards multimodal numerical reasoning. arXiv preprint arXiv:2105.14517. Chen, Z., Chen, W., Smiley, C., Shah, S., Borova, I., Langdon, D., Moussa, R., Beane, M., Huang, T.-H., Routledge, B., & et al. (2021c). Finqa: A dataset of numerical reasoning over financial data. arXiv preprint arXiv:2109.00122. Chen, Z., Li, S., Smiley, C., Ma, Z., Shah, S., & Wang, W. Y. (2022). Convfinqa: Exploring the chain of numerical reasoning in conversational finance question answering. arXiv preprint arXiv:2210.03849. Chopra, S., Auli, M., & Rush, A. M. (2016, June). Abstractive Sentence Summarization with Attentive Recurrent Neural Networks. In K. Knight, A. Nenkova, & O. Rambow, Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies San Diego, California. Christiano, P. F., Leike, J., Brown, T., Martic, M., Legg, S., & Amodei, D. (2017). Deep reinforcement learning from human preferences. Advances in Neural Information Processing Systems, 30. Chu, J., Chen, C.-C., Huang, H.-H., & Chen, H.-H. (2020). Learning to Generate Correct Numeric Values in News Headlines Companion Proceedings of the Web Conference 2020, Taipei, Taiwan. https://doi.org/10.1145/3366424.3382676 Crum, H., & Bethard, S. (2024, June). hinoki at SemEval-2024 Task 7: Numeral-Aware Headline Generation (English). In A. K. Ojha, A. S. Doğruöz, H. Tayyar Madabushi, G. Da San Martino, S. Rosenthal, & A. Rosá, Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024) Mexico City, Mexico. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019, June). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In J. Burstein, C. Doran, & T. Solorio, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) Minneapolis, Minnesota. Dou, Z.-Y., Liu, P., Hayashi, H., Jiang, Z., & Neubig, G. (2021, June). GSum: A General Framework for Guided Neural Abstractive Summarization. In K. Toutanova, A. Rumshisky, L. Zettlemoyer, D. Hakkani-Tur, I. Beltagy, S. Bethard, R. Cotterell, T. Chakraborty, & Y. Zhou, Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Online. Dua, D., Wang, Y., Dasigi, P., Stanovsky, G., Singh, S., & Gardner, M. (2019, June). DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs. In J. Burstein, C. Doran, & T. Solorio, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) Minneapolis, Minnesota. Feng, F., Rui, X., Wang, W., Cao, Y., & Chua, T.-S. (2022). Pre-training and evaluation of numeracy-oriented language model Proceedings of the Second ACM International Conference on AI in Finance, Virtual Event. https://doi.org/10.1145/3490354.3494412 Filippova, K., Alfonseca, E., Colmenares, C. A., Kaiser, L., & Vinyals, O. (2015, September). Sentence Compression by Deletion with LSTMs. In L. Màrquez, C. Callison-Burch, & J. Su, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing Lisbon, Portugal. Geva, M., Gupta, A., & Berant, J. (2020, July). Injecting Numerical Reasoning Skills into Language Models. In D. Jurafsky, J. Chai, N. Schluter, & J. Tetreault, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Online. Gu, J., Lu, Z., Li, H., & Li, V. O. K. (2016, August). Incorporating Copying Mechanism in Sequence-to-Sequence Learning. In K. Erk & N. A. Smith, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Berlin, Germany. Huang, J.-T., Chen, C.-C., Huang, H.-H., & Chen, H.-H. (2024, May). NumHG: A Dataset for Number-Focused Headline Generation. In N. Calzolari, M.-Y. Kan, V. Hoste, A. Lenci, S. Sakti, & N. Xue, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) Torino, Italia. Jin, D., Jin, Z., Zhou, J. T., Orii, L., & Szolovits, P. (2020, July). Hooks in the Headline: Learning to Generate Headlines with Controlled Styles. In D. Jurafsky, J. Chai, N. Schluter, & J. Tetreault, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Online. Jin, Z., Jiang, X., Wang, X., Liu, Q., Wang, Y., Ren, X., & Qu, H. (2021). NumGPT: Improving Numeracy Ability of Generative Pre-trained Models. arXiv:2109.03137. Retrieved September 01, 2021, from https://ui.adsabs.harvard.edu/abs/2021arXiv210903137J Jing, H., & McKeown, K. R. (2000). Cut and Paste Based Text Summarization.1st Meeting of the North American Chapter of the Association for Computational Linguistics Knight, K., & Marcu, D. (2000). Statistics-based summarization-step one: Sentence compression. AAAI/IAAI, 2000, 703-710. Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020, July). BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In D. Jurafsky, J. Chai, N. Schluter, & J. Tetreault, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Online. Lin, B. Y., Lee, S., Khanna, R., & Ren, X. (2020, November). Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-Trained Language Models. In B. Webber, T. Cohn, Y. He, & Y. Liu, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) Online. Liu, Y., & Lapata, M. (2019, November). Text Summarization with Pretrained Encoders. In K. Inui, J. Jiang, V. Ng, & X. Wan, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) Hong Kong, China. Liu, Y., Liu, P., Radev, D., & Neubig, G. (2022, May). BRIO: Bringing Order to Abstractive Summarization. In S. Muresan, P. Nakov, & A. Villavicencio, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Dublin, Ireland. Lu, P., Qiu, L., Yu, W., Welleck, S., & Chang, K.-W. (2023, July). A Survey of Deep Learning for Mathematical Reasoning. In A. Rogers, J. Boyd-Graber, & N. Okazaki, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Toronto, Canada. Matsumaru, K., Takase, S., & Okazaki, N. (2020, July). Improving Truthfulness of Headline Generation. In D. Jurafsky, J. Chai, N. Schluter, & J. Tetreault, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Online. Miao, S.-y., Liang, C.-C., & Su, K.-Y. (2020, July). A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers. In D. Jurafsky, J. Chai, N. Schluter, & J. Tetreault, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Online. Nallapati, R., Zhou, B., dos Santos, C., Gu̇lçehre, Ç., & Xiang, B. (2016, August). Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond. In S. Riezler & Y. Goldberg, Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning Berlin, Germany. Narayan, S., Cohen, S. B., & Lapata, M. (2018, oct nov). Don’t Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization. In E. Riloff, D. Chiang, J. Hockenmaier, & J. i. Tsujii, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Brussels, Belgium. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., & Ray, A. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730-27744. Rafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., & Finn, C. (2024). Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems, 36. Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21(1), Article 140. Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016, November). SQuAD: 100,000+ Questions for Machine Comprehension of Text. In J. Su, K. Duh, & X. Carreras, Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing Austin, Texas. Ravichander, A., Naik, A., Rose, C., & Hovy, E. (2019, November). EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference. In M. Bansal & A. Villavicencio, Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL) Hong Kong, China. Roit, P., Ferret, J., Shani, L., Aharoni, R., Cideron, G., Dadashi, R., Geist, M., Girgin, S., Hussenot, L., Keller, O., Momchev, N., Ramos Garea, S., Stanczyk, P., Vieillard, N., Bachem, O., Elidan, G., Hassidim, A., Pietquin, O., & Szpektor, I. (2023, July). Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback. In A. Rogers, J. Boyd-Graber, & N. Okazaki, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Toronto, Canada. Rush, A. M., Chopra, S., & Weston, J. (2015, September). A Neural Attention Model for Abstractive Sentence Summarization. In L. Màrquez, C. Callison-Burch, & J. Su, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing Lisbon, Portugal. Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. See, A., Liu, P. J., & Manning, C. D. (2017). Get To The Point: Summarization with Pointer-Generator Networks. arXiv:1704.04368. Retrieved April 01, 2017, from https://ui.adsabs.harvard.edu/abs/2017arXiv170404368S Spithourakis, G., & Riedel, S. (2018, July). Numeracy for Language Models: Evaluating and Improving their Ability to Predict Numbers. In I. Gurevych & Y. Miyao, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Melbourne, Australia. Stiennon, N., Ouyang, L., Wu, J., Ziegler, D., Lowe, R., Voss, C., Radford, A., Amodei, D., & Christiano, P. F. (2020). Learning to summarize with human feedback. Advances in Neural Information Processing Systems, 33, 3008-3021. Suadaa, L. H., Kamigaito, H., Funakoshi, K., Okumura, M., & Takamura, H. (2021, August). Towards Table-to-Text Generation with Numerical Reasoning. In C. Zong, F. Xia, W. Li, & R. Navigli, Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) Online. Wallace, E., Wang, Y., Li, S., Singh, S., & Gardner, M. (2019, November). Do NLP Models Know Numbers? Probing Numeracy in Embeddings. In K. Inui, J. Jiang, V. Ng, & X. Wan, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) Hong Kong, China. Wang, F., Song, K., Zhang, H., Jin, L., Cho, S., Yao, W., Wang, X., Chen, M., & Yu, D. (2022, December). Salience Allocation as Guidance for Abstractive Summarization. In Y. Goldberg, Z. Kozareva, & Y. Zhang, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Abu Dhabi, United Arab Emirates. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824-24837. Xu, J., Zhou, M., He, X., Han, S., & Zhang, D. (2022, December). Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems. In Y. Goldberg, Z. Kozareva, & Y. Zhang, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Abu Dhabi, United Arab Emirates. Xu, P., Wu, C.-S., Madotto, A., & Fung, P. (2019, November). Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning. In K. Inui, J. Jiang, V. Ng, & X. Wan, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) Hong Kong, China. Zhang, J., Zhao, Y., Saleh, M., & Liu, P. J. (2020). PEGASUS: pre-training with extracted gap-sentences for abstractive summarization Proceedings of the 37th International Conference on Machine Learning, Zhang, L., Negrinho, R., Ghosh, A., Jagannathan, V., Hassanzadeh, H. R., Schaaf, T., & Gormley, M. R. (2021, November). Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations. In M.-F. Moens, X. Huang, L. Specia, & S. W.-t. Yih, Findings of the Association for Computational Linguistics: EMNLP 2021 Punta Cana, Dominican Republic. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94174 | - |
| dc.description.abstract | 現代人每天透過新聞標題快速獲取大量資訊，並用標題來決定是否進一步閱讀新聞內文，因此標題的重要性不言而喻。標題生成仰賴從內文中萃取出精華資訊，並用一句話濃縮、概括整篇文章，可以視為摘要任務的一環。另一方面，標題中的數字也扮演了相當重要的角色，具備文字所不能傳達的精確性特性，不僅影響讀者的看法與價值觀，財經新聞標題中的數字對於投資人的投資決策更有不容忽視的影響力。若語言模型能幫助新聞業者實現自動生成標題，並且在標題中包含編輯者視為重要的數字，則能夠節省大量時間與人力成本。
過往在摘要任務上的研究已行之有年，然而當中有結合數字的研究卻寥寥無幾。此外，儘管在機器數字理解領域上累積了不少研究，但這些研究大多在提升模型數字推理方面的能力，對於我們任務的幫助有限。 因此，本研究提出了基於摘要模型 Bringing Order to Abstractive Summarization (BRIO) 上的方法，定義兩個品質指標，分別代表數字描述對象的語意相似度分數以及整個標題的語意相似度分數，並透過對比學習鼓勵模型給予高品質摘要較高的預測機率值、低品質摘要較低的預測機率值，從而引導模型生成高品質且包含數字的標題。我們的實驗結果表明，這兩個方法在數字準確率方面個別提升了4和2個百分點；在三個摘要指標（ROUGE、BERTScore和MoverScore）上皆個別提升了0到1分，證實我們的方法既能維持一定程度的摘要品質，還能有效協助模型生成符合編輯者偏好的數字。此外，第一種方法在摘要能力上甚至超越了所有基準的表現。 | zh_TW |
| dc.description.abstract | Modern individuals rapidly obtain vast amounts of information through news headlines and use them to decide whether to read the full article. Therefore, the importance of headlines is undeniable. Headline generation relies on extracting essential information from the content and condensing it into a single sentence, thus making it an integral part of the summarization task. Furthermore, numerical values in headlines play a significant role by providing precision that words alone cannot convey, influencing readers' perceptions and values. In financial news, the numbers in headlines have a substantial impact on investors' decision-making. If language models can assist news editors in automatically generating headlines that include numbers deemed important by editors, it would save significant time and labor costs.
Although research on summarization tasks has been extensive, there is a scarcity of studies incorporating numerical values. Despite the accumulated research in the domain of numerical reasoning, most of it focuses on enhancing models' numeracy for solving machine reading comprehension (MRC) tasks, offering limited assistance for our task. Therefore, this study proposes methods based on the summarization model Bringing Order to Abstractive Summarization (BRIO), defining two quality metrics representing the semantic similarity scores of numerical entities and the overall headline. Through contrastive learning, the model is encouraged to assign higher estimated probabilities to high-quality summaries and lower probabilities to low-quality ones, thereby guiding the generation of high-quality headlines that include numerical values. Our experimental results show that the two methods individually improve numeral accuracy by 4- and 2-percentage-point, respectively. In terms of summarization metrics, each method enhances the three metrics (ROUGE, BERTScore, and MoverScore) by 0 to 1 point, respectively, confirming that our approach not only maintains a certain level of summary quality but also effectively helps the model generate numerical values aligned with editors' preferences. Additionally, the first method surpasses all baselines in summarization capability. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-14T17:04:58Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-08-14T17:04:58Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝 i
中文摘要 ii ABSTRACT iii TABLE OF CONTENTS v LIST OF TABLES vii Chapter 1 Introduction 1 Chapter 2 Literature Review 3 2.1 Headline Generation 3 2.1.1 Text Summarization 3 2.1.2 Neural Model 4 2.1.2.1 Out-of-vocabulary (OOV) Issue 4 2.1.3 Pretrained Language Model 4 2.1.4 Output Control 6 2.1.4.1 Faithfulness 6 2.1.4.2 Styles 7 2.1.4.3 Human Preferences Alignment 7 2.2 Numerical Reasoning 8 2.2.1 Pretrained Language Model 9 2.2.2 Numeracy Injection 10 2.2.2.1 Input Reframing 10 2.2.2.2 Pre-finetuning 11 2.2.2.3 Fine-tuning 11 2.2.2.4 Other Methods 12 2.3 Number-Focused Headline Generation 12 2.4 Research Gaps and Questions 13 Research Questions 14 Chapter 3 System Design 15 3.1 BRIO 17 3.2 BRIO-NumEntity 19 3.3 BRIO-BERTScore 22 Chapter 4 Experimental Design 23 4.1 Dataset 23 4.2 Baselines 25 4.3 Evaluation Metrics 25 4.4 Implementation Details 26 Chapter 5 Experimental Results 28 Chapter 6 Analysis 30 6.1 The Number of Generated Numerical Values 30 6.2 Case Study 31 Chapter 7 Conclusion 34 REFERENCE 35 | - |
| dc.language.iso | en | - |
| dc.title | 基於品質排名訊號之新聞標題數值生成 | zh_TW |
| dc.title | Generating Number-Rich News Headlines Guided by Rank-based Quality Signals | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 陳建錦;林怡伶 | zh_TW |
| dc.contributor.oralexamcommittee | Chien-Chin Chen;Yi-Ling Lin | en |
| dc.subject.keyword | 標題生成,數字,對比學習,數字描述對象資訊,語意相似度,自然語言處理, | zh_TW |
| dc.subject.keyword | headline generation,numerical value,contrastive learning,numeral entity,semantic similarity,natural language processing, | en |
| dc.relation.page | 43 | - |
| dc.identifier.doi | 10.6342/NTU202402437 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2024-08-01 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| dc.date.embargo-lift | 2029-07-27 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 目前未授權公開取用 | 1.13 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。