NLVR2 (Suhr et al., 2019) was designed to be robust for language bias through a data collection process that resulted in each natural language sentence appearing with both true and false labels. The process did not provide a similar measure of control for visual bias. This technical report analyzes the potential for visual bias in NLVR2. We show that some amount of visual bias likely exists. Finally, we identify a subset of the test data that allows to test for model performance in a way that is robust to such potential biases. We show that the performance of existing models (Li et al., 2019; Tan and Bansal 2019) is relatively robust to this potential bias. We propose to add the evaluation on this subset of the data to the NLVR2 evaluation protocol, and update the official release to include it. A notebook including an implementation of the code used to replicate this analysis is available at http://nlvr.ai/NLVR2BiasAnalysis.html.
We propose BERTScore, an automatic evaluation metric for text generation. Analogous to common metrics, \method computes a similarity score for each token in the candidate sentence with each token in the reference. However, instead of looking for exact matches, we compute similarity using contextualized BERT embeddings. We evaluate on several machine translation and image captioning benchmarks, and show that BERTScore correlates better with human judgments than existing metrics, often significantly outperforming even task-specific supervised metrics.
We propose an approach for mapping natural language instructions and raw observations to continuous control of a quadcopter drone. Our model predicts interpretable position-visitation distributions indicating where the agent should go during execution and where it should stop, and uses the predicted distributions to select the actions to execute. This two-step model decomposition allows for simple and efficient training using a combination of supervised learning and imitation learning. We evaluate our approach with a realistic drone simulator, and demonstrate absolute task-completion accuracy improvements of 16.85% over two state-of-the-art instruction-following methods.
We study the problem of jointly reasoning about language and vision through a navigation and spatial reasoning task. We introduce the Touchdown task and dataset, where an agent must first follow navigation instructions in a real-life visual urban environment to a goal position, and then identify in the observed image a location described in natural language to find a hidden object. The data contains 9,326 examples of English instructions and spatial descriptions paired with demonstrations. We perform qualitative linguistic analysis, and show that the data displays richer use of spatial reasoning compared to related resources. Empirical analysis shows the data presents an open challenge to existing methods.
Increasingly, perceptual systems are being codified as strict pipelines wherein vision is treated as a pre-processing step to provide a dense representation of the scene to planners for high level reasoning downstream. Problematically, this paradigm forces models to represent nearly every aspect of the scene even if it has no bearing on the task at hand. In this work, we flip this paradigm, by introducing vision models whose feature representations are conditioned on embedded representations of the agent's goal. This allows the model to build scene descriptions that are specifically designed to help achieve that goal. We find this leads to models that learn faster, are substantially more parameter efficient and more robust than existing attention mechanisms in our domain. Our experiments are performed on a simulated robot item retrieval problem and trained in a fully end-to-end manner via imitation learning.
We introduce a new dataset for joint reasoning about language and vision. The data contains 107,296 examples of English sentences paired with web photographs. The task is to determine whether a natural language caption is true about a photograph. We present an approach for finding visually complex images and crowdsourcing linguistically diverse captions. Qualitative analysis shows the data requires complex reasoning about quantities, comparisons, and relationships between objects. Evaluation of state-of-the-art visual reasoning methods shows the data is a challenge for current methods.
Common recurrent neural architectures scale poorly due to the intrinsic difficulty in parallelizing their state computations. In this work, we propose the Simple Recurrent Unit (SRU), a light recurrent unit that balances model capacity and scalability. SRU is designed to provide expressive recurrence, enable highly parallelized implementation, and comes with careful initialization to facilitate training of deep models. We demonstrate the effectiveness of SRU on multiple NLP tasks. SRU achieves 5--9x speed-up over cuDNN-optimized LSTM on classification and question answering datasets, and delivers stronger results than LSTM and convolutional models. We also obtain an average of 0.7 BLEU improvement over the Transformer model on translation by incorporating SRU into the architecture.
We propose to decompose instruction execution to goal prediction and action generation. We design a model that maps raw visual observations to goals using LINGUNET, a language-conditioned image generation network, and then generates the actions required to complete them. Our model is trained from demonstration only without external resources. To evaluate our approach, we introduce two benchmarks for instruction following: LANI, a navigation task; and CHAI, where an agent executes household instructions. Our evaluation demonstrates the advantages of our model decomposition, and illustrates the challenges posed by our new benchmarks.
We propose a learning approach for mapping context-dependent sequential instructions to actions. We address the problem of discourse and state dependencies with an attention-based model that considers both the history of the interaction and the state of the world. To train from start and goal states without access to demonstrations, we propose SESTRA, a learning algorithm that takes advantage of single-step reward observations and immediate expected reward maximization. We evaluate on the SCONE domains, and show absolute accuracy improvements of 9.8%-25.3% across the domains over approaches that use high-level logical representations.
We introduce a method for following high-level navigation instructions by mapping directly from images, instructions and pose estimates to continuous low-level velocity commands for real-time control. The Grounded Semantic Mapping Network (GSMN) is a fully-differentiable neural network architecture that builds an explicit semantic map in the world reference frame by incorporating a pinhole camera projection model within the network. The information stored in the map is learned from experience, while the local-to-world transformation is computed explicitly. We train the model using DAggerFM, a modified variant of DAgger that trades tabular convergence guarantees for improved training speed and memory use. We test GSMN in virtual environments on a realistic quadcopter simulator and show that incorporating an explicit mapping and grounding modules allows GSMN to outperform strong neural baselines and almost reach an expert policy performance. Finally, we analyze the learned map representations and show that using an explicit map leads to an interpretable instruction-following model.