Diversity is a long-studied topic in information retrieval that usually refers to the requirement that retrieved results should be non-repetitive and cover different aspects. In a conversational setting, an additional dimension of diversity matters: an engaging response generation system should be able to output responses that are diverse and interesting. Sequence-to-sequence (Seq2Seq) models have been shown to be very effective for response generation. However, dialogue responses generated by Seq2Seq models tend to have low diversity. In this paper, we review known sources and existing approaches to this low-diversity problem. We also identify a source of low diversity that has been little studied so far, namely model over-confidence. We sketch several directions for tackling model over-confidence and, hence, the low-diversity problem, including confidence penalties and label smoothing.

In company with the data explosion over the past decade, deep neural network (DNN) based software has experienced unprecedented leap and is becoming the key driving force of many novel industrial applications, including many safety-critical scenarios such as autonomous driving. Despite great success achieved in various human intelligence tasks, similar to traditional software, DNNs could also exhibit incorrect behaviors caused by hidden defects causing severe accidents and losses. In this paper, we propose an automated fuzz testing framework for hunting potential defects of general-purpose DNNs. It performs metamorphic mutation to generate new semantically preserved tests, and leverages multiple plugable coverage criteria as feedback to guide the test generation from different perspectives. To be scalable towards practical-sized DNNs, our framework maintains tests in batch, and prioritizes the tests selection based on active feedback. The effectiveness of our framework is extensively investigated on 3 popular datasets (MNIST, CIFAR-10, ImageNet) and 7 DNNs with diverse complexities, under large set of 6 coverage criteria as feedback. The large-scale experiments demonstrate that our fuzzing framework can (1) significantly boost the coverage with guidance; (2) generate useful tests to detect erroneous behaviors and facilitate the DNN model quality evaluation; (3) accurately capture potential defects during DNN quantization for platform migration.

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer. Hindsight experience replay (HER) (Andrychowicz et al. 2017) was recently proposed to tackle this difficulty by manipulating unsuccessful transitions, but in doing so, HER introduces a significant bias in the replay buffer experiences and therefore achieves a suboptimal improvement in sample-efficiency. In this paper, we present an analysis on the source of bias in HER, and propose a simple and effective method to counter the bias, to most effectively harness the sample-efficiency provided by HER. Our method, motivated by counterfactual reasoning and called ARCHER, extends HER with a tradeoff to make rewards calculated for hindsight experiences numerically greater than real rewards. We validate our algorithm on two continuous control environments from DeepMind Control Suite (Tassa et al. 2018) - Reacher and Finger, which simulate manipulation tasks with a robotic arm - in combination with various reward functions, task complexities and goal sampling strategies. Our experiments consistently demonstrate that countering bias using more aggressive hindsight rewards increases sample efficiency, thus establishing the greater benefit of ARCHER in RL applications with limited computing budget.

This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that How does reward scaling affect non-saturating ReLU networks in RL? This question matters because ReLU is one of the most effective activation functions for deep learning models. We also propose an Adaptive Network Scaling framework to find a suitable scale of the rewards during learning for better performance. We conducted empirical studies to justify the solution.

We present two categories of model-agnostic adversarial strategies that reveal the weaknesses of several generative, task-oriented dialogue models: Should-Not-Change strategies that evaluate over-sensitivity to small and semantics-preserving edits, as well as Should-Change strategies that test if a model is over-stable against subtle yet semantics-changing modifications. We next perform adversarial training with each strategy, employing a max-margin approach for negative generative examples. This not only makes the target dialogue model more robust to the adversarial inputs, but also helps it perform significantly better on the original inputs. Moreover, training on all strategies combined achieves further improvements, achieving a new state-of-the-art performance on the original task (also verified via human evaluation). In addition to adversarial training, we also address the robustness task at the model-level, by feeding it subword units as both inputs and outputs, and show that the resulting model is equally competitive, requires only 1/4 of the original vocabulary size, and is robust to one of the adversarial strategies (to which the original model is vulnerable) even without adversarial training.

The ability to extract the sequence of game events for a given player's play-through has traditionally required access to the game's engine or source code. This serves as a barrier to researchers, developers, and hobbyists who might otherwise benefit from these game logs. In this paper we present two approaches to derive game logs from game video via convolutional neural networks and transfer learning. We evaluate the approaches in a Super Mario Bros. clone, Mega Man and Skyrim. Our results demonstrate our approach outperforms random forest and other transfer baselines.

Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentation techniques, and methods capturing temporal dependency for segmentation have to depend on pretrained optical flow models, leading to suboptimal solutions for the problem. End-to-end sequential learning to explore spatialtemporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i.e., even the largest video segmentation dataset only contains 90 short video clips. To solve this problem, we build a new large-scale video object segmentation dataset called YouTube Video Object Segmentation dataset (YouTube-VOS). Our dataset contains 4,453 YouTube video clips and 94 object categories. This is by far the largest video object segmentation dataset to our knowledge and has been released at http://youtube-vos.org. We further evaluate several existing state-of-the-art video object segmentation algorithms on this dataset which aims to establish baselines for the development of new algorithms in the future. Keywords: Video object segmentation, Large-scale dataset, Benchmark.

Customers are usually exposed to online digital advertisement channels, such as email marketing, display advertising, paid search engine marketing, along their way to purchase or subscribe products( aka. conversion). The marketers track all the customer journey data and try to measure the effectiveness of each advertising channel. The inference about the influence of each channel plays an important role in budget allocation and inventory pricing decisions. Several simplistic rule-based strategies and data-driven algorithmic strategies have been widely used in marketing field, but they do not address the issues, such as channel interaction, time dependency, user characteristics. In this paper, we propose a novel attribution algorithm based on deep learning to assess the impact of each advertising channel. We present Deep Neural Net With Attention multi-touch attribution model (DNAMTA) model in a supervised learning fashion of predicting if a series of events leads to conversion, and it leads us to have a deep understanding of the dynamic interaction effects between media channels. DNAMTA also incorporates user-context information, such as user demographics and behavior, as control variables to reduce the estimation biases of media effects. We used computational experiment of large real world marketing dataset to demonstrate that our proposed model is superior to existing methods in both conversion prediction and media channel influence evaluation.

In this paper, we introduce a stochastic learning framework for long-term video interpolation. While most existing interpolation models require two reference frames with a short interval, our framework predicts a plausible intermediate sequence between a long interval. Our model consists of two parts: (1) a deterministic estimation to guarantee the spatial and temporal coherency among frames, (2) a stochastic sampling process to generate dynamics from inferred distributions. Experimental results show that our model is able to generate sharp and clear sequences with variations. Moreover, motions in the generated sequence are realistic and able to transfer smoothly from the referenced start frame to the end frame.

Recommendation algorithms are widely adopted in marketplaces to help users find the items they are looking for. The sparsity of the items by user matrix and the cold-start issue in marketplaces pose challenges for the off-the-shelf matrix factorization based recommender systems. To understand user intent and tailor recommendations to their needs, we use deep learning to explore various heterogeneous data available in marketplaces. This paper summarizes five lessons we learned from experimenting with state-of-the-art deep learning recommenders at the leading Norwegian marketplace \textit{FINN.no}. We design a hybrid recommender system that takes the user-generated contents of a marketplace (including text, images and meta attributes) and combines them with user behavior data such as page views and messages to provide recommendations for marketplace items. Among various tactics we experimented with, the following five show the best impact: staged training instead of end-to-end training, leveraging rich user behaviors beyond page views, using user behaviors as noisy labels to train embeddings, using transfer learning to solve the unbalanced data problem, and using attention mechanisms in the hybrid model. This system is currently running with around 20\% click-through-rate in production at \textit{FINN.no} and serves over one million visitors everyday.