Search

This paper defines a new visual reasoning paradigm by introducing an important factor, i.e.~transformation. The motivation comes from the fact that most existing visual reasoning tasks, such as CLEVR in VQA, are solely defined to test how well the machine understands the concepts and relations within static settings, like one image. We argue that this kind of \textbf{state driven visual reasoning} approach has limitations in reflecting whether the machine has the ability to infer the dynamics between different states, which has been shown as important as state-level reasoning for human cognition in Piaget's theory. To tackle this problem, we propose a novel \textbf{transformation driven visual reasoning} task. Given both the initial and final states, the target is to infer the corresponding single-step or multi-step transformation, represented as a triplet (object, attribute, value) or a sequence of triplets, respectively. Following this definition, a new dataset namely TRANCE is constructed on the basis of CLEVR, including three levels of settings, i.e.~Basic (single-step transformation), Event (multi-step transformation), and View (multi-step transformation with variant views). Experimental results show that the state-of-the-art visual reasoning models perform well on Basic, but are still far from human-level intelligence on Event and View. We believe the proposed new paradigm will boost the development of machine visual reasoning. More advanced methods and real data need to be investigated in this direction. The resource of TVR is available at https://hongxin2019.github.io/TVR., Comment: Accepted to CVPR 2021. Resources including the TRANCE dataset and the code can be found at our homepage https://hongxin2019.github.io/TVR

Stochastic gradient descent(SGD) is the fundamental sequential method in training large scale machine learning models. To accelerate the training process, researchers proposed to use the asynchronous stochastic gradient descent (A-SGD) method in model learning. However, due to the stale information when updating parameters, A-SGD converges more slowly than SGD in the same iteration number. Moreover, A-SGD often converges to a high loss value and results in lower model accuracy. In this paper, we propose a novel algorithm called Trend-Smooth which can be adapted to the asynchronous parallel environment to overcome the above problems. Specifically, Trend-Smooth makes use of the parameter trend during the training process to shrink the learning rate of some dimensions where the gradients' directions are opposite to the trends of parameters. Experiments on MNIST and CIFAR-10 datasets confirm that Trend-Smooth can accelerate the convergence speed in asynchronous training process. The test accuracy that Trend-Smooth achieves is shown to be higher than other asynchronous parallel baseline methods, and is very close to the SGD method. Moreover, Trend-Smooth can also be combined with other adaptive learning rate methods(like Momentum, RMSProp and Adam) in the asynchronous parallel environment to promote their performance.

Similarity search of massive high-dimensional data is an important issue in the field of text data computation and search, which seriously affects the efficiency and convenience of text search and use. This paper proposes a high-performance text vector similarity search method, and proposes overlapping degree to describe the statistical characteristics of query vectors recurring in inverted index. Based on overlapping degree, candidate data sets are generated and sorted, distance calculation is carried out in candidate data set sequence, unnecessary calculation is reduced, and computation scale is reduced. Similar vectors of query vectors can be quickly obtained with very short index construction time and small memory overhead. The experimental results show that compared with the representative four methods, the index construction time of our method is shortened to 22-223 times, the index size memory overhead is reduced by 2-18 times, and the query speed advantage can be obtained with high recall rate, which greatly improves the performance and efficiency of text data similarity search.

Event detection is an important information extraction task in nature language processing. Recently, the method based on syntactic information and graph convolution network has been wildly used in event detection task and achieved good performance. For event detection, graph convolution network (GCN) based on dependency arcs can capture the sentence syntactic representations and the syntactic information, which is from candidate triggers to arguments. However, existing methods based on GCN with dependency arcs suffer from imbalance and redundant information in graph. To capture important and refined information in graph, we propose Multi-graph Convolution Network with Jump Connection (MGJ-ED). The multi-graph convolution network module adds a core subgraph splitted from dependency graph which selects important one-hop neighbors' syntactic information in breadth via GCN. Also the jump connection architecture aggregate GCN layers' representation with different attention score, which learns the importance of neighbors' syntactic information of different hops away in depth. The experimental results on the widely used ACE 2005 dataset shows the superiority of the other state-of-the-art methods.

Topic-focused multi-document summarization aims to produce a summary over a set of documents and conveys the most important aspects of a given topic. Most existing extractive methods view the task as a multi-criteria ranking problem over sentences, where relevance, salience and diversity are three typical requirements. However, diversity is a challenging problem as it involves modeling the relationship between sentences during ranking, where traditional methods usually tackle it in a heuristic or implicit way. In this paper, we propose a novel relational learning-to-rank approach (R-LTR) to solve this problem. Relational learning-to-rank is a new learning framework which further incorporates relationships into traditional learning-to-rank in an elegant way. Specifically, the ranking function is defined as the combination of content-based score of individual sentence, and relation-based score between the current sentence and those already selected. On this basis, we propose to learn the ranking function by minimizing the likelihood loss based on Plackett-Luce model, which can naturally model the sequential ranking procedure of candidate sentences. Stochastic gradient descent is then employed to conduct the learning process, and the summary is predicted by the greedy selection procedure based on the learned ranking function. Finally, we conduct extensive experiments on benchmark data sets TAC2008 and TAC2009. Experimental results show that our approach can significantly outperform the state-of-the-art methods from both quantitative and qualitative aspects.

Social tagging has grown in popularity on the web due to its effectiveness in organizing and accessing web pages. This short paper addresses the problem of automated social tagging, which aims to predict tags for web pages automatically and help with future navigation, filtering or search. We explore and find three foundations of the collaborative tags in social tagging services, that are consistency, sharability and stability. The complementary advantages are studied among three well-known methods, i.e. TF-weighted keyword extraction, collaborative filtering approach, and Corr-LDA (correspondence latent Dirichlet allocation) topic model. We then propose a blending model for automated social tagging to emphasize all the foundations, which linearly combines those tags generated by the three methods, and a permutation probability model is built to learn the linear blending. With the experiments on 50,000 training and 10,000 testing web pages from Delicious database, the results show that our blending method outperforms the four baselines. Furthermore, compared with both topic models, Corr-LDA and mixed membership LDA, our approach results in 14.2% and 25.6% of NDCG10 improvement separately.

Topic-focused multi-document summarization aims to produce a summary given a specific topic description and a set of related documents. It has become a crucial text processing task in many real applications that can help users consume the massive information. This paper presents a novel extractive approach based on supervised lazy random walk (Super Lazy). This approach naturally combines the rich features of sentences with the intrinsic sentence graph structure in a principled way, and thus enjoys the advantages of both the existing supervised and unsupervised approaches. Moreover, our approach can achieve the three major goals of topic-focused multi-document summarization (i.e. relevance, salience and diversity) simultaneously with a unified ranking process. Experiments on the benchmark dataset TAC2008 and TAC2009 are performed and the ROUGE evaluation results demonstrate that our approach can significantly outperform both the state-of-the-art supervised and unsupervised methods.

Related entity finding (REF) is a promising application, which aims to return a list of related entities given a query that describes the source entity, the specific type of target entities, and the relation between the source entity and target entities. One typical entity ranking strategy is to rank the candidate entities based on the co-occurrence between the candidate entities and the given query. However, such a strategy is inadequate to rank entities properly especially for those related but unpopular entities. In this paper, we propose a bipartite graph based entity ranking method, which leverage the Co-List relationship between candidate entities (i.e., entities co-occurring in the same structured/unstructured lists) to help improve the entity ranking. Specifically, we first estimate the initial relevance scores for the candidate entities based on a generative probabilistic model. We then construct a bipartite graph based on Co-List relation between candidate entities, and apply an iterative refinement process analogous to heat diffusion on the graph to propagate the relevance scores over entities. Finally the candidate entities are ranked according to their refined scores. We further develop an optimization framework for the iterative refinement process in our ranking method. Experimental results on the data collection from the TREC 2010 Entity Track show the effectiveness of our proposed method.

This paper addresses the problem of query classification (QC), which aims to classify Web search queries into one or more predefined categories. The state-of-the-art solution for QC is to employ a bridging classifier via an intermediate taxonomy. In this paper, we advanced the bridging method by leveraging probabilistic topic models. The topic model, referred as RCTM (Regularized Correlated Topic Model), is an extension of the conventional CTM (Correlated Topic Model). RCTM learns a topic model by leveraging weak supervision from existing annotated data rather than in an unsupervised fashion, and thus it can effectively address the problem in topic modeling while the topics are predefined. The experimental evaluations show that our QC approach outperforms other baseline methods.