Reinforcement Learning-Based Dialogue Guided Event Extraction to Exploit Argument Relations

Li, Qian; Peng, Hao; Li, Jianxin; Wu, Jia; Ning, Yuanxing; Wang, Lihong; Yu, Philip S.; Wang, Zheng

doi:10.1109/taslp.2021.3138670

Cited by 22 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we aim to find a solution that can adaptively control learning rates while speeding up the convergence process. We proposed a Learning rate Learning (LRL) mechanism to learn the two learning rates (𝑙𝑟 𝑠 and 𝑙𝑟 𝑞 ) adaptively according to the current state of the encoder in a reinforcement learning approach [14,20,43]. In our reinforcement learning setting, we propose to use a function F to generate the state 𝑠 𝑡 which encodes the observation of the training process (the inputs 𝑋 and the parameters 𝜃 𝑡 ) at the time step 𝑡: The action 𝑎 𝑡 is defined as the learned learning rate based on the state 𝑠 𝑡 and 𝑎 𝑡 ∈ R is a continuous value.…”

Section: Learning Rate Learning (Lrl)mentioning

confidence: 99%

Unbiased and Efficient Self-Supervised Incremental Contrastive Learning

Cheng¹,

Li²,

Peng³

et al. 2023

Preprint

View full text Add to dashboard Cite

Contrastive Learning (CL) has been proved to be a powerful selfsupervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been studied, which brings the limitation in applying it to real-world applications. Contrastive learning identifies the samples with the negative ones from the noise distribution that changes in the incremental scenarios. Therefore, only fitting the change of data without noise distribution causes bias, and directly retraining results in low efficiency. To bridge this research gap, we propose a self-supervised Incremental Contrastive Learning (ICL) framework consisting of (i) a novel Incremental InfoNCE (NCE-II) loss function by estimating the change of noise distribution for old data to guarantee no bias with respect to the retraining, (ii) a meta-optimization with deep reinforced Learning Rate Learning (LRL) mechanism which can adaptively learn the learning rate according to the status of the training processes and achieve fast convergence which is critical for incremental learning. Theoretically, the proposed ICL is equivalent to retraining, which is based on solid mathematical derivation. In practice, extensive experiments in different domains demonstrate that, without retraining a new model, ICL achieves up to 16.7× training speedup and 16.8× faster convergence with competitive results.

show abstract

Section: Learning Rate Learning (Lrl)mentioning

confidence: 99%

Unbiased and Efficient Self-Supervised Incremental Contrastive Learning

Cheng¹,

Li²,

Peng³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…As shown in Figure 1(a), only a short video segment semantically matches the query, while most of the video contents are queryirrelevant. Clearly, TSG tries to break through the barrier between computer vision and natural language processing techniques for more challenging cross-modal grounding (Li et al, ,a, 2022Wang and Shi, 2023;Wang et al, 2021aWang et al, , 2020c.…”

Section: Introductionmentioning

confidence: 99%

Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding

Fang,

Liu,

Fang

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

This paper addresses the task of temporal sentence grounding (TSG). Although many respectable works have made decent achievements in this important topic, they severely rely on massive expensive video-query paired annotations, which require a tremendous amount of human effort to collect in real-world applications. To this end, in this paper, we target a more practical but challenging TSG setting: unsupervised temporal sentence grounding, where both paired video-query and segment boundary annotations are unavailable during the network training. Considering that some other cross-modal tasks provide many easily available yet cheap labels, we tend to collect and transfer their simple cross-modal alignment knowledge into our complex scenarios: 1) We first explore the entity-aware objectguided appearance knowledge from the paired Image-Noun task, and adapt them into each independent video frame; 2) Then, we extract the event-aware action representation from the paired Video-Verb task, and further refine the action representation into more practical but complicated real-world cases by a newly proposed copy-paste approach; 3) By modulating and transferring both appearance and action knowledge into our challenging unsupervised task, our model can directly utilize this general knowledge to correlate videos and queries, and accurately retrieve the relevant segment without training. Extensive experiments on two challenging datasets (ActivityNet Captions and Charades-STA) show our effectiveness, outperforming existing unsupervised methods and even competitively beating supervised works.

show abstract

“…Social event detection, which aims to extract and reorganize the media texts into different types of events, can thus benefit greatly in fields like recommendation [1], disaster risk management [2], public opinion analysis [3] and so on. Due to its wide applications, social event detection has been the research hot spot since the last decade [4], [5].…”

Section: Introductionmentioning

confidence: 99%

Evidential Temporal-aware Graph-based Social Event Detection via Dempster-Shafer Theory

Ren¹,

Jiang²,

Peng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The rising popularity of online social network services has attracted lots of research on mining social media data, especially on mining social events. Social event detection, due to its wide applications, has now become a trivial task. State-ofthe-art approaches exploiting Graph Neural Networks (GNNs) usually follow a two-step strategy: 1) constructing text graphs based on various views (co-user, co-entities and co-hashtags); and 2) learning a unified text representation by a specific GNN model. Generally, the results heavily rely on the quality of the constructed graphs and the specific message passing scheme. However, existing methods have deficiencies in both aspects: 1) They fail to recognize the noisy information induced by unreliable views. 2) Temporal information which works as a vital indicator of events is neglected in most works. To this end, we propose ETGNN, a novel Evidential Temporal-aware Graph Neural Network. Specifically, we construct view-specific graphs whose nodes are the texts and edges are determined by several types of shared elements respectively. To incorporate temporal information into the message passing scheme, we introduce a novel temporalaware aggregator which assigns weights to neighbours according to an adaptive time exponential decay formula. Considering the view-specific uncertainty, the representations of all views are converted into mass functions through evidential deep learning (EDL) neural networks, and further combined via Dempster-Shafer theory (DST) to make the final detection. Experimental results on three real-world datasets demonstrate the effectiveness of ETGNN in accuracy, reliability and robustness in social event detection.

show abstract

Reinforcement Learning-Based Dialogue Guided Event Extraction to Exploit Argument Relations

Cited by 22 publications

References 42 publications

Unbiased and Efficient Self-Supervised Incremental Contrastive Learning

Unbiased and Efficient Self-Supervised Incremental Contrastive Learning

Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding

Evidential Temporal-aware Graph-based Social Event Detection via Dempster-Shafer Theory

Contact Info

Product

Resources

About