User response prediction plays a crucial role in many applications (e.g. search ranking and personalized recommendation) at online travel platforms. Although existing methods have made a great success by focusing on feature interaction or user behaviors, they cannot synthetically exploit item inclusion relations describing relationships of an item including or being included by another one, which are important components among travel items. To this end, in this paper, we propose a novel Deep Inclusion Relation-aware Network (DIRN) for user response prediction by synthetically exploiting inclusion relations among travel items. Specifically, on the item graph constructed with inclusion relations, we first leverage a node embedding approach to learn the item graph-based embedding. Then, we design Representation-based Interest Layer and Relation Path Interest Layer to extract user latent interest with user behaviors in two ways. Representation-based Interest Layer models the item-to-item similarity based on item representations containing the graph-based embedding with an attention mechanism and obtains user temporal interest by summing up representations of interacted items with similarities. Relation Path Interest Layer measures item-to-item realistic associations to extract user interest with inclusion relation paths. Offline experiments on a real-world data from Fliggy clearly validate the effectiveness of DIRN. Furthermore, DIRN has been successfully deployed online in search ranking at Fliggy and achieves significant improvement.

Click-through rate (CTR) prediction is a crucial task in many applications (e.g. recommender systems). Recently deep learning based models have been proposed and successfully applied for CTR prediction by focusing on feature interaction or user interest based on the item-to-item relevance between user behaviors and candidate item. However, these existing models neglect the user-to-user relevance between the target user and those who like the candidate item, which can reflect the preference of target user. To this end, in this paper, we propose a novel Deep User Match Network (DUMN) which measures the user-to-user relevance for CTR prediction. Specifically, in DUMN, we design a User Representation Layer to learn a unified user representation which contains user latent interest based on user behaviors. Then, User Match Layer is designed to measure the user-to-user relevance by matching the target user and those who have interacted with candidate item and modeling their similarities in user representation space. Extensive experimental results on three public real-world datasets validate the effectiveness of DUMN compared with state-of-the-art methods.

Cognitive diagnosis is a fundamental issue in intelligent education, which aims to discover the proficiency level of students on specific knowledge concepts. Existing approaches usually mine linear interactions of student exercising process by manual-designed function (e.g., logistic function), which is not sufficient for capturing complex relations between students and exercises. In this paper, we propose a general Neural Cognitive Diagnosis (NeuralCD) framework, which incorporates neural networks to learn the complex exercising interactions, for getting both accurate and interpretable diagnosis results. Specifically, we project students and exercises to factor vectors and leverage multi neural layers for modeling their interactions, where the monotonicity assumption is applied to ensure the interpretability of both factors. Furthermore, we propose two implementations of NeuralCD by specializing the required concepts of each exercise, i.e., the NeuralCDM with traditional Q-matrix and the improved NeuralCDM+ exploring the rich text content. Extensive experimental results on real-world datasets show the effectiveness of NeuralCD framework with both accuracy and interpretability.

Cognitive diagnosis is the cornerstone of modern educational techniques. One of the most classic cognitive diagnosis methods is Item Response Theory (IRT), which provides interpretable parameters for analyzing student performance. However, traditional IRT only exploits student response results and has difficulties in fully utilizing the semantics of question texts, which significantly restricts its application. To this end, in this paper, we propose a simple yet surprisingly effective framework to enhance the semantic exploiting process, which we termed Deep Item Response Theory (DIRT). In DIRT, we first use a proficiency vector to represent student proficiency on knowledge concepts and represent question texts and knowledge concepts by dense embedding. Then, we use deep learning to enhance the process of diagnosing parameters of student and question by exploiting question texts and the relationship between question texts and knowledge concepts. Finally, with the diagnosed parameters, we adopt the item response function to predict student performance. Extensive experimental results on real-world data clearly demonstrate the effectiveness and the interpretability of DIRT framework.

Hierarchical multi-label text classification (HMTC) is a fundamental but challenging task of numerous applications (e.g., patent annotation), where documents are assigned to multiple categories stored in a hierarchical structure. Categories at different levels of a document tend to have dependencies. However, the majority of prior studies for the HMTC task employ classifiers to either deal with all categories simultaneously or decompose the original problem into a set of flat multi-label classification subproblems, ignoring the associations between texts and the hierarchical structure and the dependencies among different levels of the hierarchical structure. To that end, in this paper, we propose a novel framework called Hierarchical Attention-based Recurrent Neural Network (HARNN) for classifying documents into the most relevant categories level by level via integrating texts and the hierarchical category structure. Specifically, we first apply a documentation representing layer for obtaining the representation of texts and the hierarchical structure. Then, we develop an hierarchical attention-based recurrent layer to model the dependencies among different levels of the hierarchical structure in a top-down fashion. Here, a hierarchical attention strategy is proposed to capture the associations between texts and the hierarchical structure. Finally, we design a hybrid method which is capable of predicting the categories of each level while classifying all categories in the entire hierarchical structure precisely. Extensive experimental results on two real-world datasets demonstrate the effectiveness and explanatory power of HARNN.

In online education systems, finding similar exercises is a fundamental task of many applications, such as exercise retrieval and student modeling. Several approaches have been proposed for this task by simply using the specific textual content (e.g. the same knowledge concepts or the similar words) in exercises. However, the problem of how to systematically exploit the rich semantic information embedded in multiple heterogenous data (e.g. texts and images) to precisely retrieve similar exercises remains pretty much open. To this end, in this paper, we develop a novel Multimodal Attention-based Neural Network (MANN) framework for finding similar exercises in large-scale online education systems by learning a unified semantic representation from the heterogenous data. In MANN, given exercises with texts, images and knowledge concepts, we first apply a convolutional neural network to extract image representations and use an embedding layer for representing concepts. Then, we design an attention-based long short-term memory network to learn a unified semantic representation of each exercise in a multimodal way. Here, two attention strategies are proposed to capture the associations of texts and images, texts and knowledge concepts, respectively. Moreover, with a Similarity Attention, the similar parts in each exercise pair are also measured. Finally, we develop a pairwise training strategy for returning similar exercises. Extensive experimental results on real-world data clearly validate the effectiveness and the interpretation power of MANN.

In online advertising, Click-Through Rate (CTR) prediction is a crucial task, as it may benefit the ranking and pricing of online ads. To the best of our knowledge, most of the existing CTR prediction methods are shallow layer models (e.g., Logistic Regression and Factorization Machines) or deep layer models (e.g., Neural Networks). Unfortunately, the shallow layer models cannot capture or utilize high-order nonlinear features in ad data. On the other side, the deep layer models cannot satisfy the necessity of updating CTR models online efficiently due to their high computational complexity. To address the shortcomings above, in this paper, we propose a novel hybrid method based on feature learning of both Deep and Shallow Layers (DSL). In DSL, we utilize Deep Neural Network as a deep layer model trained offline to learn high-order nonlinear features and use Factorization Machines as a shallow layer model for CTR prediction. Furthermore, we also develop an online learning implementation based on DSL, i.e., onlineDSL. Extensive experiments on large-scale real-world datasets clearly validate the effectiveness of our DSL method and onlineDSL algorithm compared with several state-of-the-art baselines.