The automatic synthesis of a policy through reinforcement learning (RL) from a given set of formal requirements depends on the construction of a reward signal and consists of the iterative application of many policy-improvement steps. The synthesis algorithm has to balance target, safety, and comfort requirements in a single objective and to guarantee that the policy improvement does not increase the number of safety-requirements violations, especially for safety-critical applications. In this work, we present a solution to the synthesis problem by solving its two main challenges: reward-shaping from a set of formal requirements and safe policy update. For the former, we propose an automatic reward-shaping procedure, defining a scalar reward signal compliant with the task specification. For the latter, we introduce an algorithm ensuring that the policy is improved in a safe fashion with high-confidence guarantees. We also discuss the adoption of a model-based RL algorithm to efficiently use the collected data and train a model-free agent on the predicted trajectories, where the safety violation does not have the same impact as in the real world. Finally, we demonstrate in standard control benchmarks that the resulting learning procedure is effective and robust even under heavy perturbations of the hyperparameters.

Multi-turn dialogue modeling as a challenging branch of natural language understanding (NLU), aims to build representations for machines to understand human dialogues, which provides a solid foundation for multiple downstream tasks. Recent studies of dialogue modeling commonly employ pre-trained language models (PrLMs) to encode the dialogue history as successive tokens, which is insufficient in capturing the temporal characteristics of dialogues. Therefore, we propose Bidirectional Information Decoupling Network (BiDeN) as a universal dialogue encoder, which explicitly incorporates both the past and future contexts and can be generalized to a wide range of dialogue-related tasks. Experimental results on datasets of different downstream tasks demonstrate the universality and effectiveness of our BiDeN.

A prominent challenge for modern language understanding systems is the ability to answer implicit reasoning questions, where the required reasoning steps for answering the question are not mentioned in the text explicitly. In this work, we investigate why current models struggle with implicit reasoning question answering (QA) tasks, by decoupling inference of reasoning steps from their execution. We define a new task of implicit relation inference and construct a benchmark, IMPLICITRELATIONS, where given a question, a model should output a list of concept-relation pairs, where the relations describe the implicit reasoning steps required for answering the question. Using IMPLICITRELATIONS, we evaluate models from the GPT-3 family and find that, while these models struggle on the implicit reasoning QA task, they often succeed at inferring implicit relations. This suggests that the challenge in implicit reasoning questions does not stem from the need to plan a reasoning strategy alone, but to do it while also retrieving and reasoning over relevant information.

Commonsense generation aims to generate a realistic sentence describing a daily scene under the given concepts, which is very challenging, since it requires models to have relational reasoning and compositional generalization capabilities. Previous work focuses on retrieving prototype sentences for the provided concepts to assist generation. They first use a sparse retriever to retrieve candidate sentences, then re-rank the candidates with a ranker. However, the candidates returned by their ranker may not be the most relevant sentences, since the ranker treats all candidates equally without considering their relevance to the reference sentences of the given concepts. Another problem is that re-ranking is very expensive, but only using retrievers will seriously degrade the performance of their generation models. To solve these problems, we propose the metric distillation rule to distill knowledge from the metric (e.g., BLEU) to the ranker. We further transfer the critical knowledge summarized by the distilled ranker to the retriever. In this way, the relevance scores of candidate sentences predicted by the ranker and retriever will be more consistent with their quality measured by the metric. Experimental results on the CommonGen benchmark verify the effectiveness of our proposed method: (1) Our generation model with the distilled ranker achieves a new state-of-the-art result. (2) Our generation model with the distilled retriever even surpasses the previous SOTA.

Pre-trained language models (LMs), such as BERT (Devlin et al., 2018) and its variants, have led to significant improvements on various NLP tasks in past years. However, a theoretical framework for studying their relationships is still missing. In this paper, we fill this gap by investigating the linear dependency between pre-trained LMs. The linear dependency of LMs is defined analogously to the linear dependency of vectors. We propose Language Model Decomposition (LMD) to represent a LM using a linear combination of other LMs as basis, and derive the closed-form solution. A goodness-of-fit metric for LMD similar to the coefficient of determination is defined and used to measure the linear dependency of a set of LMs. In experiments, we find that BERT and eleven (11) BERT-like LMs are 91% linearly dependent. This observation suggests that current state-of-the-art (SOTA) LMs are highly "correlated". To further advance SOTA we need more diverse and novel LMs that are less dependent on existing LMs.

Deep learning has become the dominant approach in coping with various tasks in Natural Language Processing (NLP). Although text inputs are typically represented as a sequence of tokens, there is a rich variety of NLP problems that can be best expressed with a graph structure. As a result, there is a surge of interests in developing new deep learning techniques on graphs for a large number of NLP tasks. In this survey, we present a comprehensive overview on Graph Neural Networks (GNNs) for Natural Language Processing. We propose a new taxonomy of GNNs for NLP, which systematically organizes existing research of GNNs for NLP along three axes: graph construction, graph representation learning, and graph based encoder-decoder models. We further introduce a large number of NLP applications that are exploiting the power of GNNs and summarize the corresponding benchmark datasets, evaluation metrics, and open-source codes. Finally, we discuss various outstanding challenges for making the full use of GNNs for NLP as well as future research directions. To the best of our knowledge, this is the first comprehensive overview of Graph Neural Networks for Natural Language Processing.

Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step of bridging and integrating multi-source KGs. In this paper, we argue that existing GNN-based EA methods inherit the inborn defects from their neural network lineage: weak scalability and poor interpretability. Inspired by recent studies, we reinvent the Label Propagation algorithm to effectively run on KGs and propose a non-neural EA framework -- LightEA, consisting of three efficient components: (i) Random Orthogonal Label Generation, (ii) Three-view Label Propagation, and (iii) Sparse Sinkhorn Iteration. According to the extensive experiments on public datasets, LightEA has impressive scalability, robustness, and interpretability. With a mere tenth of time consumption, LightEA achieves comparable results to state-of-the-art methods across all datasets and even surpasses them on many.

The Google Universal Image Embedding (GUIE) Challenge is one of the first competitions in multi-domain image representations in the wild, covering a wide distribution of objects: landmarks, artwork, food, etc. This is a fundamental computer vision problem with notable applications in image retrieval, search engines and e-commerce. In this work, we explain our 4th place solution to the GUIE Challenge, and our "bag of tricks" to fine-tune zero-shot Vision Transformers (ViT) pre-trained using CLIP.

Direct policy search has been widely applied in modern reinforcement learning and continuous control. However, the theoretical properties of direct policy search on nonsmooth robust control synthesis have not been fully understood. The optimal $\mathcal{H}_\infty$ control framework aims at designing a policy to minimize the closed-loop $\mathcal{H}_\infty$ norm, and is arguably the most fundamental robust control paradigm. In this work, we show that direct policy search is guaranteed to find the global solution of the robust $\mathcal{H}_\infty$ state-feedback control design problem. Notice that policy search for optimal $\mathcal{H}_\infty$ control leads to a constrained nonconvex nonsmooth optimization problem, where the nonconvex feasible set consists of all the policies stabilizing the closed-loop dynamics. We show that for this nonsmooth optimization problem, all Clarke stationary points are global minimum. Next, we identify the coerciveness of the closed-loop $\mathcal{H}_\infty$ objective function, and prove that all the sublevel sets of the resultant policy search problem are compact. Based on these properties, we show that Goldstein's subgradient method and its implementable variants can be guaranteed to stay in the nonconvex feasible set and eventually find the global optimal solution of the $\mathcal{H}_\infty$ state-feedback synthesis problem. Our work builds a new connection between nonconvex nonsmooth optimization theory and robust control, leading to an interesting global convergence result for direct policy search on optimal $\mathcal{H}_\infty$ synthesis.

Imitation learning aims to extract knowledge from human experts' demonstrations or artificially created agents in order to replicate their behaviors. Its success has been demonstrated in areas such as video games, autonomous driving, robotic simulations and object manipulation. However, this replicating process could be problematic, such as the performance is highly dependent on the demonstration quality, and most trained agents are limited to perform well in task-specific environments. In this survey, we provide a systematic review on imitation learning. We first introduce the background knowledge from development history and preliminaries, followed by presenting different taxonomies within Imitation Learning and key milestones of the field. We then detail challenges in learning strategies and present research opportunities with learning policy from suboptimal demonstration, voice instructions and other associated optimization schemes.