Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence最新文献_第3页

LADA-Trans-NER: Adaptive Efficient Transformer for Chinese Named Entity Recognition Using Lexicon-Attention and Data-Augmentation LADA-Trans-NER:基于词典关注和数据增强的中文命名实体识别自适应高效转换器

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i11.26554

Jiguo Liu, Chao Liu, Nan Li, Shihao Gao, Mingqi Liu, Dali Zhu

{"title":"LADA-Trans-NER: Adaptive Efficient Transformer for Chinese Named Entity Recognition Using Lexicon-Attention and Data-Augmentation","authors":"Jiguo Liu, Chao Liu, Nan Li, Shihao Gao, Mingqi Liu, Dali Zhu","doi":"10.1609/aaai.v37i11.26554","DOIUrl":"https://doi.org/10.1609/aaai.v37i11.26554","url":null,"abstract":"Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic and boundary information of Chinese words. However, these methods tend to ignore the semantic relationship before and after the sentence after integrating lexical information. Therefore, the regularity of word length information has not been fully explored in various word-character fusion methods. In this work, we propose a Lexicon-Attention and Data-Augmentation (LADA) method for Chinese NER. We discuss the challenges of using existing methods in incorporating word information for NER and show how our proposed methods could be leveraged to overcome those challenges. LADA is based on a Transformer Encoder that utilizes lexicon to construct a directed graph and fuses word information through updating the optimal edge of the graph. Specially, we introduce the advanced data augmentation method to obtain the optimal representation for the NER task. Experimental results show that the augmentation done using LADA can considerably boost the performance of our NER system and achieve significantly better results than previous state-of-the-art methods and variant models in the literature on four publicly available NER datasets, namely Resume, MSRA, Weibo, and OntoNotes v4. We also observe better generalization and application to a real-world setting from LADA on multi-source complex entities.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"21 1","pages":"13236-13245"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75024279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Xaitk-Saliency: An Open Source Explainable AI Toolkit for Saliency Xaitk-Saliency:一个开源的可解释的AI工具包

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.26871

Brian Hu, Paul Tunison, Brandon Richard Webster, Anthony J. Hoogs

{"title":"Xaitk-Saliency: An Open Source Explainable AI Toolkit for Saliency","authors":"Brian Hu, Paul Tunison, Brandon Richard Webster, Anthony J. Hoogs","doi":"10.1609/aaai.v37i13.26871","DOIUrl":"https://doi.org/10.1609/aaai.v37i13.26871","url":null,"abstract":"Advances in artificial intelligence (AI) using techniques such as deep learning have fueled the recent progress in fields such as computer vision. However, these algorithms are still often viewed as \"black boxes\", which cannot easily explain how they arrived at their final output decisions. Saliency maps are one commonly used form of explainable AI (XAI), which indicate the input features an algorithm paid attention to during its decision process. Here, we introduce the open source xaitk-saliency package, an XAI framework and toolkit for saliency. We demonstrate its modular and flexible nature by highlighting two example use cases for saliency maps: (1) object detection model comparison and (2) doppelganger saliency for person re-identification. We also show how the xaitk-saliency package can be paired with visualization tools to support the interactive exploration of saliency maps. Our results suggest that saliency maps may play a critical role in the verification and validation of AI models, ensuring their trusted use and deployment. The code is publicly available at: https://github.com/xaitk/xaitk-saliency.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"20 1","pages":"15760-15766"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72614360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Tackling Safe and Efficient Multi-Agent Reinforcement Learning via Dynamic Shielding (Student Abstract) 通过动态屏蔽实现安全高效的多智能体强化学习(学生摘要)

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.27041

Wenli Xiao, Yiwei Lyu, J. Dolan

引用次数: 0

InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting InParformer:用于长期时间序列预测的具有交互平行关注的演化分解变压器

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i6.25845

Haizhou Cao, Zhenhao Huang, Tiechui Yao, Jue Wang, Hui He, Yangang Wang

{"title":"InParformer: Evolutionary Decomposition Transformers with Interactive Parallel Attention for Long-Term Time Series Forecasting","authors":"Haizhou Cao, Zhenhao Huang, Tiechui Yao, Jue Wang, Hui He, Yangang Wang","doi":"10.1609/aaai.v37i6.25845","DOIUrl":"https://doi.org/10.1609/aaai.v37i6.25845","url":null,"abstract":"Long-term time series forecasting (LTSF) provides substantial benefits for numerous real-world applications, whereas places essential demands on the model capacity to capture long-range dependencies. Recent Transformer-based models have significantly improved LTSF performance. It is worth noting that Transformer with the self-attention mechanism was originally proposed to model language sequences whose tokens (i.e., words) are discrete and highly semantic. However, unlike language sequences, most time series are sequential and continuous numeric points. Time steps with temporal redundancy are weakly semantic, and only leveraging time-domain tokens is hard to depict the overall properties of time series (e.g., the overall trend and periodic variations). To address these problems, we propose a novel Transformer-based forecasting model named InParformer with an Interactive Parallel Attention (InPar Attention) mechanism. The InPar Attention is proposed to learn long-range dependencies comprehensively in both frequency and time domains. To improve its learning capacity and efficiency, we further design several mechanisms, including query selection, key-value pair compression, and recombination. Moreover, InParformer is constructed with evolutionary seasonal-trend decomposition modules to enhance intricate temporal pattern extraction. Extensive experiments on six real-world benchmarks show that InParformer outperforms the state-of-the-art forecasting Transformers.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"177 1","pages":"6906-6915"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74963333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Photogrammetry and VR for Comparing 2D and Immersive Linguistic Data Collection (Student Abstract) 比较二维和沉浸式语言数据采集的摄影测量和VR(学生摘要)

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.27016

Jacob Rubinstein, Cynthia Matuszek, Don Engel

引用次数: 0

Towards Global Video Scene Segmentation with Context-Aware Transformer 基于上下文感知转换器的全局视频场景分割

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i3.25426

Yang Yang, Yurui Huang, Weili Guo, Baohua Xu, Dingyin Xia

{"title":"Towards Global Video Scene Segmentation with Context-Aware Transformer","authors":"Yang Yang, Yurui Huang, Weili Guo, Baohua Xu, Dingyin Xia","doi":"10.1609/aaai.v37i3.25426","DOIUrl":"https://doi.org/10.1609/aaai.v37i3.25426","url":null,"abstract":"Videos such as movies or TV episodes usually need to divide the long storyline into cohesive units, i.e., scenes, to facilitate the understanding of video semantics. The key challenge lies in finding the boundaries of scenes by comprehensively considering the complex temporal structure and semantic information. To this end, we introduce a novel Context-Aware Transformer (CAT) with a self-supervised learning framework to learn high-quality shot representations, for generating well-bounded scenes. More specifically, we design the CAT with local-global self-attentions, which can effectively consider both the long-term and short-term context to improve the shot encoding. For training the CAT, we adopt the self-supervised learning schema. Firstly, we leverage shot-to-scene level pretext tasks to facilitate the pre-training with pseudo boundary, which guides CAT to learn the discriminative shot representations that maximize intra-scene similarity and inter-scene discrimination in an unsupervised manner. Then, we transfer contextual representations for fine-tuning the CAT with supervised data, which encourages CAT to accurately detect the boundary for scene segmentation. As a result, CAT is able to learn the context-aware shot representations and provides global guidance for scene segmentation. Our empirical analyses show that CAT can achieve state-of-the-art performance when conducting the scene segmentation task on the MovieNet dataset, e.g., offering 2.15 improvements on AP.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"23 3 1","pages":"3206-3213"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77373482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Phase-Informed Bayesian Ensemble Models Improve Performance of COVID-19 Forecasts 相位知情贝叶斯集成模型提高COVID-19预测性能

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.26855

A. Adiga, Gursharn Kaur, Lijing Wang, Benjamin Hurt, P. Porebski, S. Venkatramanan, B. Lewis, M. Marathe

{"title":"Phase-Informed Bayesian Ensemble Models Improve Performance of COVID-19 Forecasts","authors":"A. Adiga, Gursharn Kaur, Lijing Wang, Benjamin Hurt, P. Porebski, S. Venkatramanan, B. Lewis, M. Marathe","doi":"10.1609/aaai.v37i13.26855","DOIUrl":"https://doi.org/10.1609/aaai.v37i13.26855","url":null,"abstract":"Despite hundreds of methods published in the literature, forecasting epidemic dynamics remains challenging yet important. The challenges stem from multiple sources, including: the need for timely data, co-evolution of epidemic dynamics with behavioral and immunological adaptations, and the evolution of new pathogen strains. The ongoing COVID-19 pandemic highlighted these challenges; in an important article, Reich et al. did a comprehensive analysis highlighting many of these challenges.\u0000\u0000In this paper, we take another step in critically evaluating existing epidemic forecasting methods. Our methods are based on a simple yet crucial observation - epidemic dynamics go through a number of phases (waves). Armed with this understanding, we propose a modification to our deployed Bayesian ensembling case time series forecasting framework. We show that ensembling methods employing the phase information and using different weighting schemes for each phase can produce improved forecasts. We evaluate our proposed method with both the currently deployed model and the COVID-19 forecasthub models. The overall performance of the proposed model is consistent across the pandemic but more importantly, it is ranked third and first during two critical rapid growth phases in cases, regimes where the performance of most models from the CDC forecasting hub dropped significantly.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"74 1","pages":"15647-15653"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77380139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Fast and Accurate Binary Neural Networks Based on Depth-Width Reshaping 基于深度-宽度重构的快速精确二值神经网络

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i9.26268

Ping Xue, Yang Lu, Jingfei Chang, Xing Wei, Zhenchun Wei

{"title":"Fast and Accurate Binary Neural Networks Based on Depth-Width Reshaping","authors":"Ping Xue, Yang Lu, Jingfei Chang, Xing Wei, Zhenchun Wei","doi":"10.1609/aaai.v37i9.26268","DOIUrl":"https://doi.org/10.1609/aaai.v37i9.26268","url":null,"abstract":"Network binarization (i.e., binary neural networks, BNNs) can efficiently compress deep neural networks and accelerate model inference but cause severe accuracy degradation. Existing BNNs are mainly implemented based on the commonly used full-precision network backbones, and then the accuracy is improved with various techniques. However, there is a question of whether the full-precision network backbone is well adapted to BNNs. We start from the factors of the performance degradation of BNNs and analyze the problems of directly using full-precision network backbones for BNNs: for a given computational budget, the backbone of a BNN may need to be shallower and wider compared to the backbone of a full-precision network. With this in mind, Depth-Width Reshaping (DWR) is proposed to reshape the depth and width of existing full-precision network backbones and further optimize them by incorporating pruning techniques to better fit the BNNs. Extensive experiments demonstrate the analytical result and the effectiveness of the proposed method. Compared with the original backbones, the DWR backbones constructed by the proposed method result in close to O(√s) decrease in activations, while achieving an absolute accuracy increase by up to 1.7% with comparable computational cost. Besides, by using the DWR backbones, existing methods can achieve new state-of-the-art (SOTA) accuracy (e.g., 67.2% on ImageNet with ResNet-18 as the original backbone). We hope this work provides a novel insight into the backbone design of BNNs. The code is available at https://github.com/pingxue-hfut/DWR.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"150 1","pages":"10684-10692"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77477351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-Level Wavelet Mapping Correlation for Statistical Dependence Measurement: Methodology and Performance 统计相关性测量的多级小波映射关联:方法与性能

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i5.25799

Yixin Ren, Hao Zhang, Yewei Xia, J. Guan, Shuigeng Zhou

引用次数: 0

Debiasing Intrinsic Bias and Application Bias Jointly via Invariant Risk Minimization (Student Abstract) 基于不变风险最小化的联合消除内在偏差和应用偏差(学生摘要)

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.27000

Yuzhou Mao, Liu Yu, Yi Yang, Fan Zhou, Ting Zhong

{"title":"Debiasing Intrinsic Bias and Application Bias Jointly via Invariant Risk Minimization (Student Abstract)","authors":"Yuzhou Mao, Liu Yu, Yi Yang, Fan Zhou, Ting Zhong","doi":"10.1609/aaai.v37i13.27000","DOIUrl":"https://doi.org/10.1609/aaai.v37i13.27000","url":null,"abstract":"Demographic biases and social stereotypes are common in pretrained language models (PLMs), while the fine-tuning in downstream applications can also produce new biases or amplify the impact of the original biases. Existing works separate the debiasing from the fine-tuning procedure, which results in a gap between intrinsic bias and application bias. In this work, we propose a debiasing framework CauDebias to eliminate both biases, which directly combines debiasing with fine-tuning and can be applied for any PLMs in downstream tasks. We distinguish the bias-relevant (non-causal factors) and label-relevant (causal factors) parts in sentences from a causal invariant perspective. Specifically, we perform intervention on non-causal factors in different demographic groups, and then devise an invariant risk minimization loss to trade-off performance between bias mitigation and task accuracy. Experimental results on three downstream tasks show that our CauDebias can remarkably reduce biases in PLMs while minimizing the impact on downstream tasks.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"197 1","pages":"16280-16281"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79768635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0