Search Results for author:
Found 41 papers, 16 papers with code
Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network
Then, the descriptions of the objects are served as a bridge to determine the importance of the association between the objects of image modality and the contextual words of text modality, so as to build a cross-modal graph for each multi-modal instance.
基于循环交互注意力网络的问答立场分析(A Recurrent Interactive Attention Network for Answer Stance Analysis)
针对问答立场任务中, 现有方法难以提取问答文本间的依赖关系问题, 本文提出一种基于循环交互注意力(Recurrent Interactive Attention, RIA)网络的问答立场分析方法。该方法通过模仿人类阅读理解时的思维方式, 基于交互注意力机制和循环迭代方法, 有效地从问题和答案的相互联系中挖掘问答文本的立场信息。此外, 该方法将问题进行陈述化表示, 有效地解决疑问句表述下问题文本无法明确表达自身立场的问题。实验结果表明, 本文方法取得了比现有模型方法更好的效果, 同时证明该方法能有效拟合问答立场分析任务中的问答对依赖关系。
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection
In this paper, we propose a joint contrastive learning (JointCL) framework, which consists of stance contrastive learning and target-aware prototypical graph contrastive learning.
Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge
To be specific, we first regard each aspect as a pivot to derive aspect-aware words that are highly related to the aspect from external affective commonsense knowledge.
基于主题提示学习的零样本立场检测方法(A Topic-based Prompt Learning Method for Zero-Shot Stance Detection)
“零样本立场检测目的是针对未知目标数据进行立场极性预测。一般而言, 文本的立场表达是与所讨论的目标主题是紧密联系的。针对未知目标的立场检测, 本文将立场表达划分为两种类型:一类在说话者面向不同的主题和讨论目标时表达相同的立场态度, 称之为目标无关的表达;另一类在说话者面向特定主题和讨论目标时才表达相应的立场态度, 本文称之为目标依赖的表达。对这两种表达进行区分, 有效学习到目标无关的表达方式并忽略目标依赖的表达方式, 有望强化模型的可迁移能力, 使其更加适应零样本立场检测任务。据此, 本文提出了一种基于主题提示学习的零样本立场检测方法。具体而言, 受自监督学习的启发, 本文为了零样本立场检测设置了一个代理任务框架。其中, 代理任务通过掩盖上下文中的目标主题词生成辅助样本, 并基于提示学习分别预测原样本和辅助样本的立场表达, 随后判断原样本和辅助样本的立场表达是否一致, 从而在无需人工标注的情况下判断样本的立场表达是否依赖于目标的代理标签。然后, 将此代理标签提供给立场检测模型, 对应学习可迁移的立场检测特征。在两个基准数据集上的大量实验表明, 本文提出的方法在零样本立场检测任务中相比基线模型取得了更优的性能。”
Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis
This essentially allows the framework to understand the appropriate graph structures for learning intricate relations among different modalities.
面向话题的讽刺识别:新任务、新数据和新方法(Topic-Oriented Sarcasm Detection: New Task, New Dataset and New Method)
“现有的文本讽刺识别研究通常只停留在句子级别的讽刺表达分类, 缺乏考虑讽刺对象对讽刺表达的影响。针对这一问题, 本文提出一个新的面向话题的讽刺识别任务。该任务通过话题的引入, 以话题作为讽刺对象, 有助于更好地理解和建模讽刺表达。对应地, 本文构建了一个新的面向话题的讽刺识别数据集。这个数据集包含了707个话题, 以及对应的4871个话题-评论对组。在此基础上, 基于提示学习和大规模预训练语言模型, 提出了一种面向话题的讽刺表达提示学习模型。在本文构建的面向话题讽刺识别数据集上的实验结果表明, 相比基线模型, 本文所提出的面向话题的讽刺表达提示学习模型取得了更优的性能。同时, 实验分析也表明本文提出的面向话题的讽刺识别任务相比传统的句子级讽刺识别任务更具挑战性。”
Argument Pair Extraction with Mutual Guidance and Inter-sentence Relation Graph
In this paper, we tackle the APE task by a mutual guidance framework, which could utilize the information of an argument in one passage to guide the identification of arguments that can form pairs with it in another passage.
Ranked #1 on
Argument Pair Extraction (APE)
on RR
Agile and versatile bipedal robot tracking control through reinforcement learning
Finally, we evaluate the tracking accuracy of our controller on various bipedal tasks, and the effectiveness of our control framework is verified in the simulation environment.
CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
To this end, this paper proposes a novel text-guided video inpainting model that achieves better consistency, controllability and compatibility.
PerLTQA: A Personal Long-Term Memory Dataset for Memory Classification, Retrieval, and Synthesis in Question Answering
This dataset is collected to investigate the use of personalized memories, focusing on social interactions and events in the QA task.
COPR: Continual Human Preference Learning via Optimal Policy Regularization
Reinforcement Learning from Human Feedback (RLHF) is commonly utilized to improve the alignment of Large Language Models (LLMs) with human preferences.
Mitigating Biases of Large Language Models in Stance Detection with Calibration
Large language models (LLMs) have achieved remarkable progress in many natural language processing tasks.
Multi-modal Stance Detection: New Datasets and Model
Stance detection is a challenging task that aims to identify public opinion from social media platforms with respect to specific targets.
PPNet: A Novel Neural Network Structure for End-to-End Near-Optimal Path Planning
The results show PPNet can find a near-optimal solution in 15. 3ms, which is much shorter than the state-of-the-art path planners.
Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patches
Existing defense methods often necessitate modifications to the target model or result in unacceptable time overhead.
Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks
Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models.
Multi-discontinuous Functional based Sliding Mode Cascade Observer for Estimation and Closed-loop Compensation Controller
The proposed observer consists of two layers: the first layer is a traditional sliding mode observer, and the second layer is a cascade observer.
MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System
Multi-modal sarcasm detection has attracted much recent attention.
CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models
We then generate text representations by perturbing the latent space which causes fluctuation in predictive uncertainty.
Learning Diverse Risk Preferences in Population-based Self-play
In this paper, we aim to introduce diversity from the perspective that agents could have diverse risk preferences in the face of uncertainty.
Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs
Large Language Models (LLMs), such as \texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities.
Data-driven prognostics based on time-frequency analysis and symbolic recurrent neural network for fuel cells under dynamic load
Data-centric prognostics is beneficial to improve the reliability and safety of proton exchange membrane fuel cell (PEMFC).
Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention
Foldformer can complete multi-step cloth manipulation tasks even when configurations of the cloth (e. g., size and pose) vary from configurations in the general demonstrations.
Domain Generalization by Learning and Removing Domain-specific Features
With the images output by the encoder-decoder network, another classifier is designed to learn the domain-invariant features to conduct image classification.
Ranked #18 on
Domain Generalization
on PACS
Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox
With the breakthrough of AlphaGo, deep reinforcement learning becomes a recognized technique for solving sequential decision-making problems.
Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization
A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information.
Latent-Variable Advantage-Weighted Policy Optimization for Offline RL
Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions.
A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning
The integration of Reinforcement Learning (RL) and Evolutionary Algorithms (EAs) aims at simultaneously exploiting the sample efficiency as well as the diversity and robustness of the two paradigms.
Probability Density Estimation Based Imitation Learning
In general, IL methods can be categorized into Behavioral Cloning (BC) and Inverse Reinforcement Learning (IRL).
AI in Human-computer Gaming: Techniques, Challenges and Opportunities
Through this survey, we 1) compare the main difficulties among different kinds of games and the corresponding techniques utilized for achieving professional human level AIs; 2) summarize the mainstream frameworks and techniques that can be properly relied on for developing AIs for complex human-computer gaming; 3) raise the challenges or drawbacks of current techniques in the successful AIs; and 4) try to point out future trends in human-computer gaming AIs.
Offline Reinforcement Learning with Value-based Episodic Memory
Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data.
Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation
In this paper, we present IQ, i. e., interference-aware deep Q-learning, to mitigate catastrophic interference in single-task deep reinforcement learning.
We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signature
Recently, the object detection based on deep learning has proven to be vulnerable to adversarial patch attacks.
Jointly Learning Aspect-Focused and Inter-Aspect Relations with Graph Convolutional Networks for Aspect Sentiment Analysis
Besides, to interactively extract the inter-aspect relations for the specific aspect, an inter-aspect GCN is adopted to model the representations learned by aspect-focused GCN based on the inter-aspect graph which is constructed by the relative dependencies between the aspect words and other aspects.
Utilizing machine learning to prevent water main breaks by understanding pipeline failure drivers
Data61 and Western Water worked collaboratively to apply engineering expertise and Machine Learning tools to find a cost-effective solution to the pipe failure problem in the region west of Melbourne, where on average 400 water main failures occur per year.
Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition
Deep-learning recently show great success across disciplines yet conventionally require time-consuming computer processing or bulky-sized diffractive elements.
Context-aware Embedding for Targeted Aspect-based Sentiment Analysis
Attention-based neural models were employed to detect the different aspects and sentiment polarities of the same target in targeted aspect-based sentiment analysis (TABSA).
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise Reduction
Consequently, the adversarial example can be effectively detected by comparing the classification results of a given sample and its denoised version, without referring to any prior knowledge of attacks.
Deep Text Classification Can be Fooled
In this paper, we present an effective method to craft text adversarial samples, revealing one important yet underestimated fact that DNN-based text classifiers are also prone to adversarial sample attack.
