Sharing food has become very popular with the development of social media. For many real-world applications, people are keen to know the underlying recipes of a food item. In this paper, we are interested in automatically generating cooking instructions for food. We investigate an open research task of generating cooking instructions based on only food images and ingredients, which is similar to the image captioning task. However, compared with image captioning datasets, the target recipes are long-length paragraphs and do not have annotations on structure information. To address the above limitations, we propose a novel framework of Structure-aware Generation Network (SGN) to tackle the food recipe generation task. Our approach brings together several novel ideas in a systematic framework: (1) exploiting an unsupervised learning approach to obtain the sentence-level tree structure labels before training; (2) generating trees of target recipes from images with the supervision of tree structure labels learned from (1); and (3) integrating the inferred tree structures with the recipe generation procedure. Our proposed model can produce high-quality and coherent recipes, and achieve the state-of-the-art performance on the benchmark Recipe1M dataset.
Recipe generation from food images and ingredients is a challenging task, which requires the interpretation of the information from another modality. Different from the image captioning task, where the captions usually have one sentence, cooking instructions contain multiple sentences and have obvious structures. To help the model capture the recipe structure and avoid missing some cooking details, we propose a novel framework: Decomposed Generation Networks (DGN) with structure prediction, to get more structured and complete recipe generation outputs. To be specific, we split each cooking instruction into several phases, and assign different sub-generators to each phase. Our approach includes two novel ideas: (i) learning the recipe structures with the global structure prediction component and (ii) producing recipe phases in the sub-generator output component based on the predicted structure. Extensive experiments on the challenging large-scale Recipe1M dataset validate the effectiveness of our proposed model DGN, which improves the performance over the state-of-the-art results.
Due to air quality significantly affects human health, it is becoming increasingly important to accurately and timely predict the Air Quality Index (AQI). To this end, this paper proposes a new federated learning-based aerial-ground air quality sensing framework for fine-grained 3D air quality monitoring and forecasting. Specifically, in the air, this framework leverages a light-weight Dense-MobileNet model to achieve energy-efficient end-to-end learning from haze features of haze images taken by Unmanned Aerial Vehicles (UAVs) for predicting AQI scale distribution. Furthermore, the Federated Learning Framework not only allows various organizations or institutions to collaboratively learn a well-trained global model to monitor AQI without compromising privacy, but also expands the scope of UAV swarms monitoring. For ground sensing systems, we propose a Graph Convolutional neural network-based Long Short-Term Memory (GC-LSTM) model to achieve accurate, real-time and future AQI inference. The GC-LSTM model utilizes the topological structure of the ground monitoring station to capture the spatio-temporal correlation of historical observation data, which helps the aerial-ground sensing system to achieve accurate AQI inference. Through extensive case studies on a real-world dataset, numerical results show that the proposed framework can achieve accurate and energy-efficient AQI sensing without compromising the privacy of raw data.
In 5G and Beyond networks, Artificial Intelligence applications are expected to be increasingly ubiquitous. This necessitates a paradigm shift from the current cloud-centric model training approach to the Edge Computing based collaborative learning scheme known as edge learning, in which model training is executed at the edge of the network. In this article, we first introduce the principles and technologies of collaborative edge learning. Then, we establish that a successful, scalable implementation of edge learning requires the communication, caching, computation, and learning resources (3C-L) of end devices and edge servers to be leveraged jointly in an efficient manner. However, users may not consent to contribute their resources without receiving adequate compensation. In consideration of the heterogeneity of edge nodes, e.g., in terms of available computation resources, we discuss the challenges of incentive mechanism design to facilitate resource sharing for edge learning. Furthermore, we present a case study involving optimal auction design using Deep Learning to price fresh data contributed for edge learning. The performance evaluation shows the revenue maximizing properties of our proposed auction over the benchmark schemes.
Empathetic dialogue systems have been shown to improve user satisfaction and task outcomes in numerous domains. In Psychology, persona has been shown to be highly correlated to personality, which in turn influences empathy. In addition, our empirical analysis also suggests that persona plays an important role in empathetic dialogues. To this end, we propose a new task to endow empathetic dialogue systems with personas and present the first empirical study on the impacts of persona on empathetic responding. Specifically, we first present a novel large-scale multi-domain dataset for empathetic dialogues with personas. We then propose CoBERT, an efficient BERT-based response selection model that obtains the state-of-the-art performance on our dataset. Finally, we conduct extensive experiments to investigate the impacts of persona on empathetic responding. Notably, our results show that persona improves empathetic responding more when CoBERT is trained on empathetic dialogues than non-empathetic ones, establishing an empirical link between persona and empathy in human dialogues.
Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data. We propose a "divide&conquer" strategy for the challenging LVIS task: divide the whole data into balanced parts and then apply incremental learning to conquer each one. This derives a novel learning paradigm: class-incremental few-shot learning, which is especially effective for the challenge evolving over time: 1) the class imbalance among the old-class knowledge review and 2) the few-shot data in new-class learning. We call our approach Learning to Segment the Tail (LST). In particular, we design an instance-level balanced replay scheme, which is a memory-efficient approximation to balance the instance-level samples from the old-class images. We also propose to use a meta-module for new-class learning, where the module parameters are shared across incremental phases, gaining the learning-to-learn knowledge incrementally, from the data-rich head to the data-poor tail. We empirically show that: at the expense of a little sacrifice of head-class forgetting, we can gain a significant 8.3% AP improvement for the tail classes with less than 10 instances, achieving an overall 2.0% AP boost for the whole 1,230 classes.
Messages in human conversations inherently convey emotions. The task of detecting emotions in textual conversations leads to a wide range of applications such as opinion mining in social networks. However, enabling machines to analyze emotions in conversations is challenging, partly because humans often rely on the context and commonsense knowledge to express emotions. In this paper, we address these challenges by proposing a Knowledge-Enriched Transformer (KET), where contextual utterances are interpreted using hierarchical self-attention and external commonsense knowledge is dynamically leveraged using a context-aware affective graph attention mechanism. Experiments on multiple textual conversation datasets demonstrate that both context and commonsense knowledge are consistently beneficial to the emotion detection performance. In addition, the experimental results show that our KET model outperforms the state-of-the-art models on most of the tested datasets in F1 score.
Commonsense knowledge plays an important role when we read. The performance of BERT on SQuAD dataset shows that the accuracy of BERT can be better than human users. However, it does not mean that computers can surpass the human being in reading comprehension. CommonsenseQA is a large-scale dataset which is designed based on commonsense knowledge. BERT only achieved an accuracy of 55.9% on it. The result shows that computers cannot apply commonsense knowledge like human beings to answer questions. Comprehension Ability Test (CAT) divided the reading comprehension ability at four levels. We can achieve human like comprehension ability level by level. BERT has performed well at level 1 which does not require common knowledge. In this research, we propose a system which aims to allow computers to read articles and answer related questions with commonsense knowledge like a human being for CAT level 2. This system consists of three parts. Firstly, we built a commonsense knowledge graph; and then automatically constructed the commonsense knowledge question dataset according to it. Finally, BERT is combined with the commonsense knowledge to achieve the reading comprehension ability at CAT level 2. Experiments show that it can pass the CAT as long as the required common knowledge is included in the knowledge base.