Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

To ask the adequate question, deep learning and reinforcement learning have been recently applied.

For MNIST, the approximated answerer is count-based and its recognition accuracy can be controlled proportional to the actual answerer's accuracy. For GuessWhat, the approximated answerer is trained in a variety of ways -- on the same training data as the actual answerer, on predicted answers from the actual answerer, on a different training data split as the actual answerer, and on a different training data split as the actual answerer followed by imitation of predicted answers on the other split. And the proposed approach outperforms the random baseline. Interestingly, the authors find that the depA* models perform better than the indA* models -- showing that training on predicted answers is a stronger signal for building an accurate mental model than just sharing training data. I'm happy to recommend this for publication.

It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected. This view dominates the current literature in computational models for language-vision tasks, where visual and linguistic inputs are mostly processed independently before being fused into a single representation. In this paper, we deviate from this classic pipeline and propose to modulate the entire visual processing by a linguistic input. Specifically, we introduce Conditional Batch Normalization (CBN) as an efficient mechanism to modulate convolutional feature maps by a linguistic embedding. We apply CBN to a pre-trained Residual Network (ResNet), leading to the MODulatEd ResNet (MODERN) architecture, and show that this significantly improves strong baselines on two visual question answering tasks. Our ablation study confirms that modulating from the early stages of the visual processing is beneficial.

Interactive visual grounding in Human-Robot Interaction (HRI) is challenging yet practical due to the inevitable ambiguity in natural languages. It requires robots to disambiguate the user input by active information gathering. Previous approaches often rely on predefined templates to ask disambiguation questions, resulting in performance reduction in realistic interactive scenarios. In this paper, we propose TiO, an end-to-end system for interactive visual grounding in human-robot interaction. Benefiting from a unified formulation of visual dialogue and grounding, our method can be trained on a joint of extensive public data, and show superior generality to diversified and challenging open-world scenarios. In the experiments, we validate TiO on GuessWhat?! and InViG benchmarks, setting new state-of-the-art performance by a clear margin. Moreover, we conduct HRI experiments on the carefully selected 150 challenging scenes as well as real-robot platforms. Results show that our method demonstrates superior generality to diversified visual and language inputs with a high success rate. Codes and demos are available at https://github.com/jxu124/TiO.

Decoding strategies play a crucial role in natural language generation systems. They are usually designed and evaluated in open-ended text-only tasks, and it is not clear how different strategies handle the numerous challenges that goal-oriented multimodal systems face (such as grounding and informativeness). To answer this question, we compare a wide variety of different decoding strategies and hyper-parameter configurations in a Visual Dialogue referential game. Although none of them successfully balance lexical richness, accuracy in the task, and visual grounding, our in-depth analysis allows us to highlight the strengths and weaknesses of each decoding strategy. We believe our findings and suggestions may serve as a starting point for designing more effective decoding algorithms that handle the challenges of Visual Dialogue tasks.

Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor theoretical understanding of the objectives in text-generation and their relation to the learning process (i.e., model training). To this end, we propose a new theoretical framework for learning to generate text in dialogue. Compared to existing theories of learning, our framework allows for analysis of the multi-faceted goals inherent to text-generation. We use our framework to develop theoretical guarantees for learners that adapt to unseen data. As an example, we apply our theory to study data-shift within a cooperative learning algorithm proposed for the GuessWhat?! visual dialogue game. From this insight, we propose a new algorithm, and empirically, we demonstrate our proposal improves both task-success and human-likeness of the generated text. Finally, we show statistics from our theory are empirically predictive of multiple qualities of the generated dialogue, suggesting our theory is useful for model-selection when human evaluations are not available.

Investigating cooperativity of interlocutors is central in studying pragmatics of dialogue. Models of conversation that only assume cooperative agents fail to explain the dynamics of strategic conversations. Thus, we investigate the ability of agents to identify non-cooperative interlocutors while completing a concurrent visual-dialogue task. Within this novel setting, we study the optimality of communication strategies for achieving this multi-task objective. We use the tools of learning theory to develop a theoretical model for identifying non-cooperative interlocutors and apply this theory to analyze different communication strategies. We also introduce a corpus of non-cooperative conversations about images in the GuessWhat?! dataset proposed by De Vries et al. (2017). We use reinforcement learning to implement multiple communication strategies in this context and find empirical results validate our theory.

GuessWhat?! is a visual dialogue task between a guesser and an oracle. The guesser aims to locate an object supposed by the oracle oneself in an image by asking a sequence of Yes/No questions. Asking proper questions with the progress of dialogue is vital for achieving successful final guess. As a result, the progress of dialogue should be properly represented and tracked. Previous models for question generation pay less attention on the representation and tracking of dialogue states, and therefore are prone to asking low quality questions such as repeated questions. This paper proposes visual dialogue state tracking (VDST) based method for question generation. A visual dialogue state is defined as the distribution on objects in the image as well as representations of objects. Representations of objects are updated with the change of the distribution on objects. An object-difference based attention is used to decode new question. The distribution on objects is updated by comparing the question-answer pair and objects. Experimental results on GuessWhat?! dataset show that our model significantly outperforms existing methods and achieves new state-of-the-art performance. It is also noticeable that our model reduces the rate of repeated questions from more than 50% to 21.9% compared with previous state-of-the-art methods.