CPTuning: Contrastive Prompt Tuning for Generative Relation Extraction

• URL: http://arxiv.org/abs/2501.02196v1
• Date: Sat, 04 Jan 2025 05:17:34 GMT
• Title: CPTuning: Contrastive Prompt Tuning for Generative Relation Extraction
• Authors: Jiaxin Duan, Fengyu Lu, Junfei Liu,
• Abstract summary: Generative relation extraction (RE) commonly involves first reformulating RE as a linguistic modeling problem easily tackled with pre-trained language models (PLM) We introduce a novel contrastive prompt tuning method for RE, CPTuning, which learns to associate a candidate relation between two in-context entities. CTPuning also organizes RE as a verbalized relation generation task and uses Trie-constrained decoding to ensure a model generates valid relations.
• Score: 2.883903547507341
• License:
• Abstract: Generative relation extraction (RE) commonly involves first reformulating RE as a linguistic modeling problem easily tackled with pre-trained language models (PLM) and then fine-tuning a PLM with supervised cross-entropy loss. Although having achieved promising performance, existing approaches assume only one deterministic relation between each pair of entities without considering real scenarios where multiple relations may be valid, i.e., entity pair overlap, causing their limited applications. To address this problem, we introduce a novel contrastive prompt tuning method for RE, CPTuning, which learns to associate a candidate relation between two in-context entities with a probability mass above or below a threshold, corresponding to whether the relation exists. Beyond learning schema, CPTuning also organizes RE as a verbalized relation generation task and uses Trie-constrained decoding to ensure a model generates valid relations. It adaptively picks out the generated candidate relations with a high estimated likelihood in inference, thereby achieving multi-relation extraction. We conduct extensive experiments on four widely used datasets to validate our method. Results show that T5-large fine-tuned with CPTuning significantly outperforms previous methods, regardless of single or multiple relations extraction.

Related papers

• Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction [19.019881161010474]
  Relation extraction is essentially a text classification problem, which can be tackled by fine-tuning a pre-trained language model (LM) Existing approaches therefore solve the problem in an indirect way: they fine-tune an LM to learn embeddings of the head and tail entities, and then predict the relationship from these entity embeddings. Our hypothesis in this paper is that relation extraction models can be improved by capturing relationships in a more direct way.
  arXiv  Detail & Related papers  (2023-12-18T09:58:19Z)
• More than Classification: A Unified Framework for Event Temporal Relation Extraction [61.44799147458621]
  Event temporal relation extraction(ETRE) is usually formulated as a multi-label classification task. We observe that all relations can be interpreted using the start and end time points of events. We propose a unified event temporal relation extraction framework, which transforms temporal relations into logical expressions of time points.
  arXiv  Detail & Related papers  (2023-05-28T02:09:08Z)
• PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extraction [0.0]
  Unsupervised Relation Extraction (RE) aims to identify relations between entities in text, without having access to labeled data during training. We propose PromptORE, a ''Prompt-based Open Relation Extraction'' model. We adapt the novel prompt-tuning paradigm to work in an unsupervised setting, and use it to embed sentences expressing a relation. We show that PromptORE consistently outperforms state-of-the-art models with a relative gain of more than 40% in B 3, V-measure and ARI.
  arXiv  Detail & Related papers  (2023-03-24T12:55:35Z)
• PCRED: Zero-shot Relation Triplet Extraction with Potential Candidate Relation Selection and Entity Boundary Detection [11.274924966891842]
  Zero-shot relation triplet extraction (ZeroRTE) aims to extract relation triplets from unstructured texts. Previous state-of-the-art method handles this challenging task by leveraging pretrained language models to generate data as additional training samples. We tackle this task from a new perspective and propose a novel method named PCRED for ZeroRTE with Potential Candidate Relation selection and Entity boundary Detection.
  arXiv  Detail & Related papers  (2022-11-26T04:27:31Z)
• SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction [51.27558374091491]
  We propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for relation extraction. Based on a broad spectrum of carefully designed tasks, our proposed SAIS method not only extracts relations of better quality due to more effective supervision, but also retrieves the corresponding supporting evidence more accurately.
  arXiv  Detail & Related papers  (2021-09-24T17:37:35Z)
• D-REX: Dialogue Relation Extraction with Explanations [65.3862263565638]
  This work focuses on extracting explanations that indicate that a relation exists while using only partially labeled data. We propose our model-agnostic framework, D-REX, a policy-guided semi-supervised algorithm that explains and ranks relations. We find that about 90% of the time, human annotators prefer D-REX's explanations over a strong BERT-based joint relation extraction and explanation model.
  arXiv  Detail & Related papers  (2021-09-10T22:30:48Z)
• Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction [84.64435075778988]
  We propose a general approach to learn relation prototypes from unlabeled texts. We learn relation prototypes as an implicit factor between entities. We conduct experiments on two publicly available datasets: New York Times and Google Distant Supervision.
  arXiv  Detail & Related papers  (2020-11-27T06:21:12Z)
• Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction [40.00702385889112]
  We propose a novel multi-prototype embedding network model to jointly extract the composition of relational triples. We design a hybrid learning mechanism that bridges text and knowledge concerning both entities and relations. Experimental results demonstrate that the proposed method can improve the performance of the few-shot triple extraction.
  arXiv  Detail & Related papers  (2020-10-30T04:18:39Z)
• Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training [49.9995628166064]
  We propose CTEG, a model equipped with two mechanisms to learn to decouple easily-confused relations. On the one hand, an EGA mechanism is introduced to guide the attention to filter out information causing confusion. On the other hand, a Confusion-Aware Training (CAT) method is proposed to explicitly learn to distinguish relations.
  arXiv  Detail & Related papers  (2020-10-21T11:07:53Z)
• Relation of the Relations: A New Paradigm of the Relation Extraction Problem [52.21210549224131]
  We propose a new paradigm of Relation Extraction (RE) that considers as a whole the predictions of all relations in the same context. We develop a data-driven approach that does not require hand-crafted rules but learns by itself the relation of relations (RoR) using Graph Neural Networks and a relation matrix transformer. Experiments show that our model outperforms the state-of-the-art approaches by +1.12% on the ACE05 dataset and +2.55% on SemEval 2018 Task 7.2.
  arXiv  Detail & Related papers  (2020-06-05T22:25:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.