Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details. But collecting, processing and annotating real data at scale is difficult, expensive, and frequently raises additional privacy, fairness and legal concerns. Synthetic data is a powerful tool with the potential to address these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent or mitigate problems regarding bias, privacy and licensing. Unfortunately, software tools for effective data generation are less mature than those for architecture design and training, which leads to fragmented generation efforts. To address these problems we introduce Kubric, an open-source Python framework that interfaces with PyBullet and Blender to generate photo-realistic scenes, with rich annotations, and seamlessly scales to large jobs distributed over thousands of machines, and generating TBs of data. We demonstrate the effectiveness of Kubric by presenting a series of 13 different generated datasets for tasks ranging from studying 3D NeRF models to optical flow estimation. We release Kubric, the used assets, all of the generation code, as well as the rendered datasets for reuse and modification.

Recent efforts within the AI community have yielded impressive results towards “soft theorem proving” over natural language sentences using language models. We propose a novel, generative adversarial framework for probing and improving these models’ reasoning capabilities. Adversarial attacks in this domain suffer from the logical inconsistency problem, whereby perturbations to the input may alter the label. Our Logically consistent AdVersarial Attacker, LAVA, addresses this by combining a structured generative process with a symbolic solver, guaranteeing logical consistency. Our framework successfully generates adversarial attacks and identifies global weaknesses common across multiple target models. Our analyses reveal naive heuristics and vulnerabilities in these models’ reasoning capabilities, exposing an incomplete grasp of logical deduction under logic programs. Finally, in addition to effective probing of these models, we show that training on the generated samples improves the target model’s performance.

Nihir Vedd, Zixu Wang, Marek Rei, Yishu Miao, Lucia Specia. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Julia Ive, Andy Mingren Li, Yishu Miao, Ozan Caglayan, Pranava Madhyastha, Lucia Specia. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. 2021.

We propose a generative framework for simultaneous machine translation.Conventional approaches use a fixed number of source words to translate or learn dynamic policies for the number of source words by reinforcement learning.Here we formulate simultaneous translation as a structural sequence-tosequence learning problem.A latent variable is introduced to model read or translate actions at every time step, which is then integrated out to consider all the possible translation policies.A re-parameterised Poisson prior is used to regularise the policies which allows the model to explicitly balance translation quality and latency.The experiments demonstrate the effectiveness and robustness of the generative framework, which achieves the best BLEU scores given different average translation latencies on benchmark datasets.

Due to the sparse rewards and high degree of environmental variation, reinforcement learning approaches, such as deep deterministic policy gradient (DDPG), are plagued by issues of high variance when applied in complex real-world environments. We present a new framework for overcoming these issues by incorporating a stochastic switch, allowing an agent to choose between high- and low-variance policies. The stochastic switch can be jointly trained with the original DDPG in the same framework. In this article, we demonstrate the power of the framework in a navigation task, where the robot can dynamically choose to learn through exploration or to use the output of a heuristic controller as guidance. Instead of starting from completely random actions, the navigation capability of a robot can be quickly bootstrapped by several simple independent controllers. The experimental results show that with the aid of stochastic guidance, we are able to effectively and efficiently train DDPG navigation policies and achieve significantly better performance than state-of-the-art baseline models.

Topic models have been prevailing for many years on discovering latent semantics while modeling long documents.However, for short texts they generally suffer from data sparsity because of extremely limited word cooccurrences; thus tend to yield repetitive or trivial topics with low quality.In this paper, to address this issue, we propose a novel neural topic model in the framework of autoencoding with a new topic distribution quantization approach generating peakier distributions that are more appropriate for modeling short texts.Besides the encoding, to tackle this issue in terms of decoding, we further propose a novel negative sampling decoder learning from negative samples to avoid yielding repetitive topics.We observe that our model can highly improve short text topic modeling performance.Through extensive experiments on real-world datasets, we demonstrate our model can outperform both strong traditional and neural baselines under extreme data sparsity scenes, producing high-quality topics.

Matrix factorization has now become a dominant solution for personalized recommendation on the Social Web. To alleviate the cold start problem, previous approaches have incorporated various additional sources of information into traditional matrix factorization models. These upgraded models, however, achieve only "marginal" enhancements on the performance of personalized recommendation. Therefore, inspired by the recent development of deep-semantic modeling, we propose a hybrid deep-semantic matrix factorization (HDMF) model to further improve the performance of tag-aware personalized recommendation by integrating the techniques of deep-semantic modeling, hybrid learning, and matrix factorization. Experimental results show that HDMF significantly outperforms the state-of-the-art baselines in tag-aware personalized recommendation, in terms of all evaluation metrics.

Inertial information processing plays a pivotal role in egomotion awareness for mobile agents, as inertial measurements are entirely egocentric and not environment dependent. However, they are affected greatly by changes in sensor placement/orientation or motion dynamics, and it is infeasible to collect labelled data from every domain. To overcome the challenges of domain adaptation on long sensory sequences, we propose MotionTransformer - a novel framework that extracts domain-invariant features of raw sequences from arbitrary domains, and transforms to new domains without any paired data. Through the experiments, we demonstrate that it is able to efficiently and effectively convert the raw sequence from a new unlabelled target domain into an accurate inertial trajectory, benefiting from the motion knowledge transferred from the labelled source domain. We also conduct real-world experiments to show our framework can reconstruct physically meaningful trajectories from raw IMU measurements obtained with a standard mobile phone in various attachments.

Deep learning approaches for Visual-Inertial Odometry (VIO) have proven successful, but they rarely focus on incorporating robust fusion strategies for dealing with imperfect input sensory data. We propose a novel end-to-end selective sensor fusion framework for monocular VIO, which fuses monocular images and inertial measurements in order to estimate the trajectory whilst improving robustness to real-life issues, such as missing and corrupted data or bad sensor synchronization. In particular, we propose two fusion modalities based on different masking strategies: deterministic soft fusion and stochastic hard fusion, and we compare with previously proposed direct fusion baselines. During testing, the network is able to selectively process the features of the available sensor modalities and produce a trajectory at scale. We present a thorough investigation on the performances on three public autonomous driving, Micro Aerial Vehicle (MAV) and hand-held VIO datasets. The results demonstrate the effectiveness of the fusion strategies, which offer better performances compared to direct fusion, particularly in presence of corrupted data. In addition, we study the interpretability of the fusion networks by visualising the masking layers in different scenarios and with varying data corruption, revealing interesting correlations between the fusion networks and imperfect sensory input data.

Visual place recognition is a fundamental problem for many vision based applications. Sparse feature and deep learning based methods have been successful and dominant over the decade. However, most of them do not explicitly leverage high-level semantic information to deal with challenging scenarios where they may fail. This paper proposes a novel visual place recognition algorithm, termed TextPlace, based on scene texts in the wild. Since scene texts are high-level information invariant to illumination changes and very distinct for different places when considering spatial correlation, it is beneficial for visual place recognition tasks under extreme appearance changes and perceptual aliasing. It also takes spatial-temporal dependence between scene texts into account for topological localization. Extensive experiments show that TextPlace achieves state-of-the-art performance, verifying the effectiveness of using high-level scene texts for robust visual place recognition in urban areas.

Topic models have been widely explored as probabilistic generative models of documents. Traditional inference methods have sought closed-form derivations for updating the models, however as the expressiveness of these models grows, so does the difficulty of performing fast and accurate inference over their parameters. This paper presents alternative neural approaches to topic modelling by providing parameterisable distributions over topics which permit training by backpropagation in the framework of neural variational inference. In addition, with the help of a stick-breaking construction, we propose a recurrent network that is able to discover a notionally unbounded number of topics, analogous to Bayesian non-parametric topic models. Experimental results on the MXM Song Lyrics, 20NewsGroups and Reuters News datasets demonstrate the effectiveness and efficiency of these neural topic models.

Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. The traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructing deterministic models for learning dialogue sentences that fail to capture the conversational stochasticity. In this paper, however, we propose a Latent Intention Dialogue Model that employs a discrete latent variable to learn underlying dialogue intentions in the framework of neural variational inference. Additionally, in a goal-oriented dialogue scenario, the latent intentions can be interpreted as actions guiding the generation of machine responses, which can be further refined autonomously by reinforcement learning. The experiments demonstrate the effectiveness of discrete latent variable models on learning goal-oriented dialogues, and the results outperform the published benchmarks on both corpus-based evaluation and human evaluation.

Recently, many efforts have been put into tag-aware personalized recommendation. However, due to uncontrolled vocabularies, social tags are usually redundant, sparse, and ambiguous. In this paper, we propose a deep neural network approach to solve this problem by mapping the tag-based user and item profiles to an abstract deep feature space, where the deep-semantic similarities between users and their target items (resp., irrelevant items) are maximized (resp., minimized). To ensure the scalability in practice, we further propose to improve this model's training efficiency by using hybrid deep learning and negative sampling. Experimental results show that our approach can significantly outperform the state-of-the-art baselines in tag-aware personalized recommendation (3.8 times better than the best baseline), and that using hybrid deep learning and negative sampling can dramatically enhance the model's training efficiency (hundreds of times quicker), while maintaining similar (and sometimes even better) training quality and recommendation performance.

With the rapid growth of social tagging systems, many efforts have been put on tag-aware personalized recommendation. However, due to uncontrolled vocabularies, social tags are usually redundant, sparse, and ambiguous. In this paper, we propose a deep neural network approach to solve this problem by mapping both the tag-based user and item profiles to an abstract deep feature space, where the deep-semantic similarities between users and their target items (resp., irrelevant items) are maximized (resp., minimized). Due to huge numbers of online items, the training of this model is usually computationally expensive in the real-world context. Therefore, we introduce negative sampling, which significantly increases the model's training efficiency (109.6 times quicker) and ensures the scalability in practice. Experimental results show that our model can significantly outperform the state-of-the-art baselines in tag-aware personalized recommendation: e.g., its mean reciprocal rank is between 5.7 and 16.5 times better than the baselines.

In this work we explore deep generative models of text in which the latent representation of a document is itself drawn from a discrete language model distribution.We formulate a variational auto-encoder for inference in this model and apply it to the task of compressing sentences.In this application the generative model first draws a latent summary sentence from a background language model, and then subsequently draws the observed sentence conditioned on this latent summary.In our empirical evaluation we show that generative formulations of both abstractive and extractive compression yield state-of-the-art results when trained on a large amount of supervised data.Further, we explore semi-supervised compression scenarios where we show that it is possible to achieve performance competitive with previously proposed supervised models while training on a fraction of the supervised data.

Recent advances in neural variational inference have spawned a renaissance in deep latent variable models. In this paper we introduce a generic variational inference framework for generative and conditional models of text. While traditional variational methods derive an analytic approximation for the intractable distributions over latent variables, here we construct an inference network conditioned on the discrete text input to provide the variational distribution. We validate this framework on two very different text modelling applications, generative document modelling and supervised question answering. Our neural variational document model combines a continuous stochastic document representation with a bag-of-words generative model and achieves the lowest reported perplexities on two standard test corpora. The neural answer selection model employs a stochastic representation layer within an attention mechanism to extract the semantics between a question and answer pair. On two question answering benchmarks this model exceeds all previous published benchmarks.