2000 character limit reached
Prompting for Numerical Sequences: A Case Study on Market Comment Generation (2404.02466v1)
Published 3 Apr 2024 in cs.CL, cs.AI, and cs.CE
Abstract: LLMs have been applied to a wide range of data-to-text generation tasks, including tables, graphs, and time-series numerical data-to-text settings. While research on generating prompts for structured data such as tables and graphs is gaining momentum, in-depth investigations into prompting for time-series numerical data are lacking. Therefore, this study explores various input representations, including sequences of tokens and structured formats such as HTML, LaTeX, and Python-style codes. In our experiments, we focus on the task of Market Comment Generation, which involves taking a numerical sequence of stock prices as input and generating a corresponding market comment. Contrary to our expectations, the results show that prompts resembling programming languages yield better outcomes, whereas those similar to natural languages and longer formats, such as HTML and LaTeX, are less effective. Our findings offer insights into creating effective prompts for tasks that generate text from numerical sequences.
- In-context examples selection for machine translation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8857–8873, Toronto, Canada. Association for Computational Linguistics.
- Generating market comments referring to external resources. In Proceedings of the 11th International Conference on Natural Language Generation, pages 135–139, Tilburg University, The Netherlands. Association for Computational Linguistics.
- Agnes Axelsson and Gabriel Skantze. 2023. Using large language models for zero-shot natural language generation from knowledge graphs. In Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023), pages 39–54, Prague, Czech Republic. Association for Computational Linguistics.
- Graph pre-training for AMR parsing and generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6001–6015, Dublin, Ireland. Association for Computational Linguistics.
- Language models are few-shot learners. In Advances in Neural Information Processing Systems, volume 33, pages 1877–1901. Curran Associates, Inc.
- Logic-guided message generation from raw real-time sensor data. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6899–6908, Marseille, France. European Language Resources Association.
- The WebNLG challenge: Generating text from RDF data. In Proceedings of the 10th International Conference on Natural Language Generation, pages 124–133, Santiago de Compostela, Spain. Association for Computational Linguistics.
- Unpredictable attributes in market comment generation. In Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation, pages 217–226, Shanghai, China. Association for Computational Lingustics.
- Generating racing game commentary from vision, language, and structured data. In Proceedings of the 14th International Conference on Natural Language Generation, pages 103–113, Aberdeen, Scotland, UK. Association for Computational Linguistics.
- StructGPT: A general framework for large language model to reason over structured data. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9237–9251, Singapore. Association for Computational Linguistics.
- InstructoR: Instructing unsupervised conversational dense retrieval with large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6649–6675, Singapore. Association for Computational Linguistics.
- Chart-to-text: A large-scale benchmark for chart summarization. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4005–4023, Dublin, Ireland. Association for Computational Linguistics.
- Marzena Karpinska and Mohit Iyyer. 2023. Large language models effectively leverage document-level context for literary translation, but critical errors persist. In Proceedings of the Eighth Conference on Machine Translation, pages 419–451, Singapore. Association for Computational Linguistics.
- Neural AMR: Sequence-to-sequence models for parsing and generation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 146–157, Vancouver, Canada. Association for Computational Linguistics.
- Neural text generation from structured data with application to the biography domain. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1203–1213, Austin, Texas. Association for Computational Linguistics.
- BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7871–7880, Online. Association for Computational Linguistics.
- AutoConv: Automatically generating information-seeking conversations with large language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1751–1762, Toronto, Canada. Association for Computational Linguistics.
- Michela Lorandi and Anya Belz. 2023. Data-to-text generation for severely under-resourced languages with GPT-3.5: A bit of help needed from Google Translate (WebNLG 2023). In Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023), pages 80–86, Prague, Czech Republic. Association for Computational Linguistics.
- Learning to generate market comments from stock prices. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1374–1384, Vancouver, Canada. Association for Computational Linguistics.
- Select, prompt, filter: Distilling large language models for summarizing conversations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12257–12265, Singapore. Association for Computational Linguistics.
- Data-to-text generation with content selection and planning. In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, AAAI’19/IAAI’19/EAAI’19. AAAI Press.
- Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140):1–67.
- MURMUR: Modular multi-step reasoning for semi-structured data-to-text generation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11069–11090, Toronto, Canada. Association for Computational Linguistics.
- Prompting palm for translation: Assessing strategies and performance.
- Document-level machine translation with large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16646–16661, Singapore. Association for Computational Linguistics.
- Element-aware summarization with large language models: Expert-aligned evaluation and chain-of-thought method. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8640–8665, Toronto, Canada. Association for Computational Linguistics.
- MOBA-E2C: Generating MOBA game commentaries via capturing highlight events from the meta-data. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4545–4556, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- SummIt: Iterative text summarization via ChatGPT. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10644–10657, Singapore. Association for Computational Linguistics.
- Investigating table-to-text generation capabilities of large language models in real-world information seeking scenarios. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 160–175, Singapore. Association for Computational Linguistics.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.