Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction

Hu, Xuming; Zhang, Chenwei; Yang, Yawen; Li, Xiaohe; Li, Lin; Wen, Lijie; Yu, Philip S.

doi:10.18653/v1/2021.emnlp-main.216

Cited by 23 publications

(27 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Foreign Affairs (Austria) Figure 1: An example of limitations of existing methods without considering temporal information relation extraction [14][15][16]28]. However, existing KGs are generally highly incomplete [44].…”

Section: G S G Tmentioning

confidence: 99%

Unsupervised Entity Alignment for Temporal Knowledge Graphs

Liu¹,

Wu²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

Entity alignment (EA) is a fundamental data integration task that identifies equivalent entities between different knowledge graphs (KGs). Temporal Knowledge graphs (TKGs) extend traditional knowledge graphs by introducing timestamps, which have received increasing attention. State-of-the-art time-aware EA studies have suggested that the temporal information of TKGs facilitates the performance of EA. However, existing studies have not thoroughly exploited the advantages of temporal information in TKGs. Also, they perform EA by pre-aligning entity pairs, which can be labor-intensive and thus inefficient. In this paper, we present DualMatch that effectively fuses the relational and temporal information for EA. DualMatch transfers EA on TKGs into a weighted graph matching problem. More specifically, DualMatch is equipped with an unsupervised method, which achieves EA without necessitating the seed alignment. DualMatch has two steps: (i) encoding temporal and relational information into embeddings separately using a novel label-free encoder, Dual-Encoder; and (ii) fusing both information and transforming it into alignment using a novel graph-matching-based decoder, GM-Decoder. DualMatch is able to perform EA on TKGs with or without supervision, due to its capability of effectively capturing temporal information. Extensive experiments on three real-world TKG datasets offer the insight that DualMatch significantly outperforms the state-of-the-art methods.

show abstract

Section: G S G Tmentioning

confidence: 99%

Unsupervised Entity Alignment for Temporal Knowledge Graphs

Liu¹,

Wu²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Inspired by the success of contrastive learning in computer vision tasks (He et al, 2020;Li et al, 2021;Caron et al, 2020), instance-wise contrastive learning in information extraction tasks (Peng et al, 2020;Li et al, 2022a), and large pre-trained language models that show great potential to encode meaningful semantics for various downstream tasks (Devlin et al, 2019;Soares et al, 2019;Hu et al, 2021b), we proposed a hierarchical exemplar contrastive learning schema for unsupervised relation extraction. It has the advantages of supervised learning to capture high-level semantics in the relational features instead of exploiting base-level sentence differences to strengthen discriminative power and also keeps the advantage of unsupervised learning to handle the cases where the number of relations is unknown in advance.…”

Section: Related Workmentioning

confidence: 99%

HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction

Li¹,

Zhang²,

Hu³

et al. 2022

Findings of the Association for Computational Linguistics: ACL 2022

View full text Add to dashboard Cite

Unsupervised relation extraction aims to extract the relationship between entities from natural language sentences without prior information on relational scope or distribution. Existing works either utilize self-supervised schemes to refine relational feature signals by iteratively leveraging adaptive clustering and classification that provoke gradual drift problems, or adopt instance-wise contrastive learning which unreasonably pushes apart those sentence pairs that are semantically similar. To overcome these defects, we propose a novel contrastive learning framework named HiURE, which has the capability to derive hierarchical signals from relational feature space using cross hierarchy attention and effectively optimize relation representation of sentences under exemplar-wise contrastive learning. Experimental results on two public datasets demonstrate the advanced effectiveness and robustness of HiURE on unsupervised relation extraction when compared with state-of-the-art models. Source code is available here 1 .

show abstract

“…To address this problem, (Pham et al, 2020;Wang et al, 2021b;Hu et al, 2021a) propose to utilize the performance of the student model on the held out labeled data as a Meta Learning objective to update the teacher model or improve the pseudo-label generation process. (Hu et al, 2021b) leverage the cosine distance between gradients computed on labeled data and pseudolabeled data as feedback to guide the self-training process. (Mehta et al, 2018) propose to inject span constraints from constituency parsing during selftraining of semantic role labeling.…”

Section: Related Workmentioning

confidence: 99%

Improve Event Extraction via Self-Training with Gradient Guidance

Xu¹,

Huang²

2022

Preprint

View full text Add to dashboard Cite

Data scarcity and imbalance have been the main factors that hinder the progress of event extraction (EE). In this work, we propose a self-training with gradient guidance (STGG) framework which consists of (1) a base event extraction model which is firstly trained on existing event annotations and then applied to large-scale unlabeled corpora to predict new event mentions, and (2) a scoring model that takes in each predicted event trigger and argument as well as their path in the Abstract Meaning Representation (AMR) graph to estimate a probability score indicating the correctness of the event prediction. The new event predictions along with their correctness scores are then used as pseudo labeled examples to improve the base event extraction model while the magnitude and direction of its gradients are guided by the correctness scores. Experimental results on three benchmark datasets, including ACE05-E, ACE05-E + , and ERE, demonstrate the effectiveness of the STGG framework on event extraction task with up to 1.9 Fscore improvement over the base event extraction models. Our experimental analysis further shows that STGG is a general framework as it can be applied to any base event extraction models and improve their performance by leveraging broad unlabeled data, even when the high-quality AMR graph annotations are not available.

show abstract

Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction

Cited by 23 publications

References 67 publications

Unsupervised Entity Alignment for Temporal Knowledge Graphs

Unsupervised Entity Alignment for Temporal Knowledge Graphs

HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction

Improve Event Extraction via Self-Training with Gradient Guidance

Contact Info

Product

Resources

About