2000 character limit reached
AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction
Published 3 Sep 2024 in cs.CL | (2409.01854v1)
Abstract: The relation extraction (RE) in complex scenarios faces challenges such as diverse relation types and ambiguous relations between entities within a single sentence, leading to the poor performance of pure "text-in, text-out" LMs. To address these challenges, in this paper, we propose an agent-based RE framework, namely AgentRE, which fully leverages the potential of LLMs including memory, retrieval and reflection, to achieve RE in complex scenarios. Specifically, three major modules are built in AgentRE serving as the tools to help the agent acquire and process various useful information, thereby obtaining improved RE performance. Our extensive experimental results upon two datasets in English and Chinese demonstrate our AgentRE's superior performance, especially in low-resource scenarios. Additionally, the trajectories generated by AgentRE can be refined to construct a high-quality training dataset incorporating different reasoning methods, which can be used to fine-tune smaller models. Code is available at https://github.com/Lightblues/AgentRE.
- Joint entity recognition and relation extraction as a multi-head selection problem. Expert Systems with Applications 114 (2018), 34–45.
- CodeKGC: Code Language Model for Generative Knowledge Graph Construction. In ACM Transactions on Asian and Low-Resource Language Information Processing, Vol. abs/2304.09048.
- RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation. https://api.semanticscholar.org/CorpusID:259203978
- FireAct: Toward Language Agent Fine-tuning. ArXiv abs/2310.05915 (2023).
- Scaling Instruction-Finetuned Language Models. ArXiv abs/2210.11416 (2022).
- SimCSE: Simple Contrastive Learning of Sentence Embeddings. In Conference on Empirical Methods in Natural Language Processing.
- DeepSeek-Coder: When the Large Language Model Meets Programming – The Rise of Code Intelligence. arXiv abs/2401.14196 (2024).
- Retrieval-Augmented Code Generation for Universal Information Extraction. ArXiv abs/2311.02962 (2023).
- LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations (ICLR).
- CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors. ArXiv abs/2305.05711 (2023).
- DuIE: A Large-Scale Chinese Dataset for Information Extraction. In Natural Language Processing and Chinese Computing.
- Entity-Relation Extraction as Multi-Turn Question Answering. ArXiv abs/1905.05529 (2019).
- Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019).
- Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. In International Conference on Learning Representations.
- Universal Information Extraction as Unified Semantic Matching. Proceedings of the AAAI Conference on Artificial Intelligence 37, 11 (2023), 13318–13326.
- Unified structure generation for universal information extraction. arXiv preprint arXiv:2203.12277 (2022).
- Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction. In Conference on Empirical Methods in Natural Language Processing.
- AUTOACT: Automatic Agent Learning from Scratch via Self-Planning. ArXiv abs/2401.05268 (2024). https://api.semanticscholar.org/CorpusID:266902590
- Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research 21, 1 (2020), 5485–5551.
- Juan Enrique Ramos. 2003. Using TF-IDF to Determine Word Relevance in Document Queries.
- Stephen E. Robertson and Hugo Zaragoza. 2009. The Probabilistic Relevance Framework: BM25 and Beyond. Found. Trends Inf. Retr. 3 (2009), 333–389.
- Cognitive architectures for language agents. arXiv abs/2309.02427 (2023).
- Llama 2: Open Foundation and Fine-Tuned Chat Models. ArXiv abs/2307.09288 (2023).
- Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk. ArXiv abs/2401.05033 (2024). https://api.semanticscholar.org/CorpusID:266902624
- GPT-RE: In-context Learning for Relation Extraction using Large Language Models. ArXiv abs/2305.02105 (2023).
- A Survey on Large Language Model based Autonomous Agents. arXiv abs/2308.11432 (2023).
- InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction. CoRR abs/2304.08085 (2023).
- TPLinker: Single-stage joint extraction of entities and relations through token pair linking. arXiv preprint arXiv:2010.13415 (2020).
- Zero-Shot Information Extraction via Chatting with ChatGPT. arXiv abs/2302.10205 (2023).
- A Survey on Large Language Models for Recommendation. CoRR abs/2305.19860 (2023).
- C-Pack: Packaged Resources To Advance General Chinese Embedding. ArXiv abs/2309.07597 (2023).
- Large Language Models for Generative Information Extraction: A Survey. arXiv abs/2312.17617 (2023).
- ReAct: Synergizing Reasoning and Acting in Language Models. In NeurIPS 2022 Foundation Models for Decision Making Workshop.
- Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction. ArXiv abs/2312.03022 (2023). https://api.semanticscholar.org/CorpusID:265696391
- Joint extraction of entities and relations based on a novel decomposition strategy. arXiv preprint arXiv:1909.04273 (2019).
- Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors. In Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, 794–812.
- A Survey of Large Language Models. ArXiv abs/2303.18223 (2023).
- A Survey on Neural Open Information Extraction: Current Status and Future Directions. ArXiv abs/2205.11725 (2022).
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition. In The Twelfth International Conference on Learning Representations, Vol. abs/2308.03279.
- ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification. ArXiv abs/2203.02225 (2022).
- KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents. ArXiv abs/2403.03101 (2024). https://api.semanticscholar.org/CorpusID:268248897
- LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities. ArXiv abs/2305.13168 (2023).
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
