University of Science and Technology of China


Sequence-to-Sequence Learning via Shared Latent Representation

AAAI Conferences

Sequence-to-sequence learning is a popular research area in deep learning, such as video captioning and speech recognition. Existing methods model this learning as a mapping process by first encoding the input sequence to a fixed-sized vector, followed by decoding the target sequence from the vector. Although simple and intuitive, such mapping model is task-specific, unable to be directly used for different tasks. In this paper, we propose a star-like framework for general and flexible sequence-to-sequence learning, where different types of media contents (the peripheral nodes) could be encoded to and decoded from a shared latent representation (SLR) (the central node). This is inspired by the fact that human brain could learn and express an abstract concept in different ways. The media-invariant property of SLR could be seen as a high-level regularization on the intermediate vector, enforcing it to not only capture the latent representation intra each individual media like the auto-encoders, but also their transitions like the mapping models. Moreover, the SLR model is content-specific, which means it only needs to be trained once for a dataset, while used for different tasks. We show how to train a SLR model via dropout and use it for different sequence-to-sequence tasks. Our SLR model is validated on the Youtube2Text and MSR-VTT datasets, achieving superior performance on video-to-sentence task, and the first sentence-to-video results.


Multi-Scale Face Restoration With Sequential Gating Ensemble Network

AAAI Conferences

Restoring face images from distortions is important in face recognition applications and is challenged by multiple scale issues, which is still not well-solved in research area. In this paper, we present a Sequential Gating Ensemble Network (SGEN) for multi-scale face restoration issue. We first employ the principle of ensemble learning into SGEN architecture design to reinforce predictive performance of the network. The SGEN aggregates multi-level base-encoders and base-decoders into the network, which enables the network to contain multiple scales of receptive field. Instead of combining these base-en/decoders directly with non-sequential operations, the SGEN takes base-en/decoders from different levels as sequential data. Specifically, the SGEN learns to sequentially extract high level information from base-encoders in bottom-up manner and restore low level information from base-decoders in top-down manner. Besides, we propose to realize bottom-up and top-down information combination and selection with Sequential Gating Unit (SGU). The SGU sequentially takes two inputs from different levels and decides the output based on one active input. Experiment results demonstrate that our SGEN is more effective at multi-scale human face restoration with more image details and less noise than state-of-the-art image restoration models. By using adversarial training, SGEN also produces more visually preferred results than other models through subjective evaluation.


How Images Inspire Poems: Generating Classical Chinese Poetry from Images with Memory Networks

AAAI Conferences

With the recent advances of neural models and natural language processing, automatic generation of classical Chinese poetry has drawn significant attention due to its artistic and cultural value. Previous works mainly focus on generating poetry given keywords or other text information, while visual inspirations for poetry have been rarely explored. Generating poetry from images is much more challenging than generating poetry from text, since images contain very rich visual information which cannot be described completely using several keywords, and a good poem should convey the image accurately. In this paper, we propose a memory based neural model which exploits images to generate poems. Specifically, an Encoder-Decoder model with a topic memory network is proposed to generate classical Chinese poetry from images. To the best of our knowledge, this is the first work attempting to generate classical Chinese poetry from images with neural networks. A comprehensive experimental investigation with both human evaluation and quantitative analysis demonstrates that the proposed model can generate poems which convey images accurately.


Dual Transfer Learning for Neural Machine Translation with Marginal Distribution Regularization

AAAI Conferences

Neural machine translation (NMT) heavily relies on parallel bilingual data for training. Since large-scale, high-quality parallel corpora are usually costly to collect, it is appealing to exploit monolingual corpora to improve NMT. Inspired by the law of total probability, which connects the probability of a given target-side monolingual sentence to the conditional probability of translating from a source sentence to the target one, we propose to explicitly exploit this connection to learn from and regularize the training of NMT models using monolingual data. The key technical challenge of this approach is that there are exponentially many source sentences for a target monolingual sentence while computing the sum of the conditional probability given each possible source sentence. We address this challenge by leveraging the dual translation model (target-to-source translation) to sample several mostly likely source-side sentences and avoid enumerating all possible candidate source sentences. That is, we transfer the knowledge contained in the dual model to boost the training of the primal model (source-to-target translation), and we call such an approach dual transfer learning. Experiment results on English-French and German-English tasks demonstrate that dual transfer learning achieves significant improvement over several strong baselines and obtains new state-of-the-art results.


Video-Based Sign Language Recognition Without Temporal Segmentation

AAAI Conferences

Millions of hearing impaired people around the world routinely use some variants of sign languages to communicate, thus the automatic translation of a sign language is meaningful and important. Currently, there are two sub-problems in Sign Language Recognition (SLR), i.e., isolated SLR that recognizes word by word and continuous SLR that translates entire sentences. Existing continuous SLR methods typically utilize isolated SLRs as building blocks, with an extra layer of preprocessing (temporal segmentation) and another layer of post-processing (sentence synthesis). Unfortunately, temporal segmentation itself is non-trivial and inevitably propagates errors into subsequent steps. Worse still, isolated SLR methods typically require strenuous labeling of each word separately in a sentence, severely limiting the amount of attainable training data. To address these challenges, we propose a novel continuous sign recognition framework, the Hierarchical Attention Network with Latent Space (LS-HAN), which eliminates the preprocessing of temporal segmentation. The proposed LS-HAN consists of three components: a two-stream Convolutional Neural Network (CNN) for video feature representation generation, a Latent Space (LS) for semantic gap bridging, and a Hierarchical Attention Network (HAN) for latent space based recognition. Experiments are carried out on two large scale datasets. Experimental results demonstrate the effectiveness of the proposed framework.


Domain Generalization via Conditional Invariant Representations

AAAI Conferences

Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: training data and test data have different distributions, and the training set contains heterogeneous samples from different distributions. Let X denote the features, and Y be the class labels. Existing domain generalization methods address the dataset bias problem by learning a domain-invariant representation h(X) that has the same marginal distribution P(h(X)) across multiple source domains. The functional relationship encoded in P(Y|X) is usually assumed to be stable across domains such that P(Y|h(X)) is also invariant. However, it is unclear whether this assumption holds in practical problems. In this paper, we consider the general situation where both P(X) and P(Y|X) can change across all domains. We propose to learn a feature representation which has domain-invariant class conditional distributions P(h(X)|Y). With the conditional invariant representation, the invariance of the joint distribution P(h(X),Y) can be guaranteed if the class prior P(Y) does not change across training and test domains. Extensive experiments on both synthetic and real data demonstrate the effectiveness of the proposed method.


On Multiset Selection With Size Constraints

AAAI Conferences

This paper considers the multiset selection problem with size constraints, which arises in many real-world applications such as budget allocation. Previous studies required the objective function f to be submodular, while we relax this assumption by introducing the notion of the submodularity ratios (denoted by α_f and β_f). We propose an anytime randomized iterative approach POMS, which maximizes the given objective f and minimizes the multiset size simultaneously. We prove that POMS using a reasonable time achieves an approximation guarantee of max{1-1/e^(β_f), (α_f/2)(1-1/e^(α_f))}. Particularly, when f is submdoular, this bound is at least as good as that of the previous greedy-style algorithms. In addition, we give lower bounds on the submodularity ratio for the objectives of budget allocation. Experimental results on budget allocation as well as a more complex application, namely, generalized influence maximization, exhibit the superior performance of the proposed approach.


Measuring the Popularity of Job Skills in Recruitment Market: A Multi-Criteria Approach

AAAI Conferences

To cope with the accelerating pace of technological changes, talents are urged to add and refresh their skills for staying in active and gainful employment. This raises a natural question: what are the right skills to learn? Indeed, it is a nontrivial task to measure the popularity of job skills due to the diversified criteria of jobs and the complicated connections within job skills. To that end, in this paper, we propose a data driven approach for modeling the popularity of job skills based on the analysis of large-scale recruitment data. Specifically, we first build a job skill network by exploring a large corpus of job postings. Then, we develop a novel Skill Popularity based Topic Model (SPTM) for modeling the generation of the skill network. In particular, SPTM can integrate different criteria of jobs (e.g., salary levels, company size) as well as the latent connections within skills, thus we can effectively rank the job skills based on their multi-faceted popularity. Extensive experiments on real-world recruitment data validate the effectiveness of SPTM for measuring the popularity of job skills, and also reveal some interesting rules, such as the popular job skills which lead to high-paid employment.


Confidence-Aware Matrix Factorization for Recommender Systems

AAAI Conferences

Collaborative filtering (CF), particularly matrix factorization (MF) based methods, have been widely used in recommender systems. The literature has reported that matrix factorization methods often produce superior accuracy of rating prediction in recommender systems. However, existing matrix factorization methods rarely consider confidence of the rating prediction and thus cannot support advanced recommendation tasks. In this paper, we propose a Confidence-aware Matrix Factorization (CMF) framework to simultaneously optimize the accuracy of rating prediction and measure the prediction confidence in the model. Specifically, we introduce variance parameters for both users and items in the matrix factorization process. Then, prediction interval can be computed to measure confidence for each predicted rating. These confidence quantities can be used to enhance the quality of recommendation results based on Confidence-aware Ranking (CR). We also develop two effective implementations of our framework to compute the confidence-aware matrix factorization for large-scale data. Finally, extensive experiments on three real-world datasets demonstrate the effectiveness of our framework from multiple perspectives.


Joint Training for Neural Machine Translation Models with Monolingual Data

AAAI Conferences

Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation tasks where parallel data are not rich enough. In this paper, we propose a novel approach to better leveraging monolingual data for neural machine translation by jointly learning source-to-target and target-to-source NMT models for a language pair with a joint EM optimization method. The training process starts with two initial NMT models pre-trained on parallel data for each direction, and these two models are iteratively updated by incrementally decreasing translation losses on training data.In each iteration step, both NMT models are first used to translate monolingual data from one language to the other, forming pseudo-training data of the other NMT model. Then two new NMT models are learnt from parallel data together with the pseudo training data. Both NMT models are expected to be improved and better pseudo-training data can be generated in next step. Experiment results on Chinese-English and English-German translation tasks show that our approach can simultaneously improve translation quality of source-to-target and target-to-source models, significantly outperforming strong baseline systems which are enhanced with monolingual data for model training including back-translation.