Open AccessPosted Content
A Question-answering Based Framework for Relation Extraction Validation.
TL;DR: This paper proposed a question-answering based framework to validate the results of relation extraction models, which can be easily applied to existing relation classifiers without any additional information, and observe consistent improvements over five strong baselines.
read more
Abstract: Relation extraction is an important task in knowledge acquisition and text understanding. Existing works mainly focus on improving relation extraction by extracting effective features or designing reasonable model structures. However, few works have focused on how to validate and correct the results generated by the existing relation extraction models. We argue that validation is an important and promising direction to further improve the performance of relation extraction. In this paper, we explore the possibility of using question answering as validation. Specifically, we propose a novel question-answering based framework to validate the results from relation extraction models. Our proposed framework can be easily applied to existing relation classifiers without any additional information. We conduct extensive experiments on the popular NYT dataset to evaluate the proposed framework, and observe consistent improvements over five strong baselines.
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
Weakly-Supervised Questions for Zero-Shot Relation Extraction
Saeed Najafi,Alona Fyshe +1 more
- 01 Jan 2023
TL;DR: ZRE task involves extracting relations between entities without shared relation types. This paper proposes a novel approach that eliminates the need for manually creating gold question templates. The model generates questions for unseen relations and leverages them to extract tail entities, outperforming previous state-of-the-art by a significant margin.
StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding
Cheng Ji,Lin Qiu,Tsz Ho Chan,Tianqing Fang,Weiqi Wang,Chunkit Chan,Dongyu Ru,Qinglan Guo,Hongming Zhang,Yangqiu Song,Yue Zhang,Qi Zhang +11 more
- 01 Jan 2023
TL;DR: The paper proposes a novel approach to derive story-level analogies from large language models, unlocking analogical understanding.
MCPG: A Flexible Multi-Level Controllable Framework for Unsupervised Paraphrase Generation
Yi Chen,Haiyun Jiang,Lemao Liu,Qianqian Wang,Shuming Shi,Ruifeng Xu +5 more
- 01 Jan 2022
TL;DR: MCPG is a flexible multi-level controllabe framework for unsupervised paraphrase generation that is simple, effective, and domain-adaptable.
A Hybrid of Rule-based and Transformer-based Approaches for Relation Extraction in Biodiversity Literature
Roselyn Gabud,Portia Lapitan,Vladimir Mariano,Eduardo Mendoza,Nelson Pampolina,Maria Art Antonette Clariño,Riza Theresa Batista-Navarro +6 more
TL;DR: This paper takes advantage of the zero-shot (i.e., not requiring any labeled data) capability of pattern-based methods for RE using a rule-based approach, combined with templates for natural language inference (NLI) transformer models to present a hybrid method for RE that exploits the advantages of both methods.
References
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Jacob Devlin,Ming-Wei Chang,Kenton Lee,Kristina Toutanova +3 more
- 11 Oct 2018
TL;DR: BERT as mentioned in this paper pre-trains 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.
24.6K
•Proceedings Article
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Zhenzhong Lan,Mingda Chen,Sebastian Goodman,Kevin Gimpel,Piyush Sharma,Radu Soricut +5 more
- 30 Apr 2020
TL;DR: This work presents two parameter-reduction techniques to lower memory consumption and increase the training speed of BERT, and uses a self-supervised loss that focuses on modeling inter-sentence coherence.
•Proceedings Article
Knowledge graph embedding by translating on hyperplanes
Zhen Wang,Jianwen Zhang,Jianlin Feng,Zheng Chen +3 more
- 27 Jul 2014
TL;DR: This paper proposes TransH which models a relation as a hyperplane together with a translation operation on it and can well preserve the above mapping properties of relations with almost the same model complexity of TransE.
Know What You Don't Know: Unanswerable Questions for SQuAD
Pranav Rajpurkar,Robin Jia,Percy Liang +2 more
- 11 Jun 2018
TL;DR: SQuADRUn as discussed by the authors is a new dataset that combines the existing Stanford Question Answering Dataset with over 50,000 unanswerable questions written adversarially by crowdworkers to look similar to answerable ones.
2.3K
•Proceedings Article
Relation Classification via Convolutional Deep Neural Network
Daojian Zeng,Kang Liu,Siwei Lai,Guangyou Zhou,Jun Zhao +4 more
- 01 Aug 2014
TL;DR: This paper exploits a convolutional deep neural network (DNN) to extract lexical and sentence level features from the output of pre-existing natural language processing systems and significantly outperforms the state-of-the-art methods.