Span-based single-stage joint entity-relation extraction model
TL;DR: Wang et al. as mentioned in this paper proposed a joint entity relation extraction model (SMHS) based on a span-level multi-head selection mechanism, which transforms relation extraction into a spanlevel multihead selection problem.
read more
Abstract: Extracting entities and relations from the unstructured text has attracted increasing attention in recent years. The existing work has achieved considerable results, yet it is difficult to solve entity overlap and exposure bias. To address cascading errors, exposure bias, and entity overlap in existing entity relation extraction approaches, we propose a joint entity relation extraction model (SMHS) based on a span-level multi-head selection mechanism, transforming entity relation extraction into a span-level multi-head selection problem. Our model uses span-tagger and span-embedding to construct span semantic vectors, utilizes LSTM and multi-head self-attention mechanism for span feature extraction, multi-head selection mechanism for span-level relation decoding, and introduces span classification task for multi-task learning to decode out the relation triad in a single-stage. Experiments on the classic English dataset NYT and the publicly available Chinese relationship extraction dataset DuIE 2.0 show that this method achieves better results than the baseline method, which verifies the effectiveness of this method. Source code and data are published here(https://github.com/Beno-waxgourd/NLP.git).
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
The Entity Relationship Extraction Method Using Improved RoBERTa and Multi-Task Learning
C. Simon Fan
TL;DR: The proposed method for entity relationship extraction using RoBERTa and multi-task learning achieves high accuracy and significantly improves the effectiveness of model interaction.
Research on joint model relation extraction method based on entity mapping
Hongmei Tang,Dixiongxiao Zhu,Shuai Wang,Yanyang Wang,Lihong Wang +4 more
TL;DR: Experiments indicate the superiority of the CasRelBLCF model and the enhancement on model’s performance of the noise reduction method and the superiority on model’s performance of the noise reduction method.
2
Research on the construction and application of problem-method-oriented academic graph empowered by LLM
Qigang Liu,Yinfan Wang,Lifeng Mu,Jun Li +3 more
TL;DR: Researchers propose a novel problem-method-oriented academic graph empowered by Large Language Models (LLM) to facilitate efficient literature management and content-level review, achieving 8.01-8.65% improvement over state-of-the-art models in entity identification and relation classification.
A joint extraction method for fault text entity relationships in smart grid considering nested entities and complex semantics
Lei Wang,Fei Wu,Xiaoqing Liu,Yunlong Wang,Wanxin Wang,Mingshi Cui,Zhaoyang Qu +6 more
TL;DR: A joint extraction method for fault text entity relationships in smart grid considering nested entities and complex semantics accurately extracts information from complex semantic fault texts by incorporating RoFormer, orthogonalized Biaffine attention mechanism, stacked pointers and hidden layers.
References
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
99K
•Posted Content
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
81.7K
End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
Makoto Miwa,Mohit Bansal +1 more
- 05 Jan 2016
TL;DR: A novel end-to-end neural model to extract entities and relations between them and compares favorably to the state-of-the-art CNN based model (in F1-score) on nominal relation classification (SemEval-2010 Task 8).
Pre-Training with Whole Word Masking for Chinese BERT
TL;DR: The whole word masking (wwm) strategy for Chinese BERT is introduced, along with a series of Chinese pre-trained language models, and a simple but effective model called MacBERT is proposed, which improves upon RoBERTa in several ways.
943