Recent research has shown that neural text-to-SQL models can effectively translate natural language questions into corresponding SQL queries on unseen databases. Working mostly on the Spider dataset, researchers have been proposing increasingly sophisticated modelling approaches to the problem. Contrary to this trend, in this paper we identify the aspects in which text-to-SQL models can be simplified. We begin by building DuoRAT, a re-implementation of the state-of-the-art RAT-SQL model that unlike RAT-SQL is using only relation-aware or vanilla transformers as the building blocks. We perform several ablation experiments using DuoRAT as the baseline model. Our experiments confirm the usefulness of some of the techniques and point out the redundancy of others, including structural SQL features and features that link the question with the schema.
Language User Interfaces (LUIs) could improve human-machine interaction for a wide variety of tasks, such as playing music, getting insights from databases, or instructing domestic robots. In contrast to traditional hand-crafted approaches, recent work attempts to build LUIs in a data-driven way using modern deep learning methods. To satisfy the data needs of such learning algorithms, researchers have constructed benchmarks that emphasize the quantity of collected data at the cost of its naturalness and relevance to real-world LUI use cases. As a consequence, research findings on such benchmarks might not be relevant for developing practical LUIs. The goal of this paper is to bootstrap the discussion around this issue, which we refer to as the benchmarks' low ecological validity. To this end, we describe what we deem an ideal methodology for machine learning research on LUIs and categorize five common ways in which recent benchmarks deviate from it. We give concrete examples of the five kinds of deviations and their consequences. Lastly, we offer a number of recommendations as to how to increase the ecological validity of machine learning research on LUIs.
The BabyAI platform is designed to measure the sample efficiency of training an agent to follow grounded-language instructions. BabyAI 1.0 presents baseline results of an agent trained by deep imitation or reinforcement learning. BabyAI 1.1 improves the agent's architecture in three minor ways. This increases reinforcement learning sample efficiency by up to 3 times and improves imitation learning performance on the hardest level from 77 % to 90.4 %. We hope that these improvements increase the computational efficiency of BabyAI experiments and help users design better agents.
In adversarial imitation learning, a discriminator is trained to differentiate agent episodes from expert demonstrations representing the desired behavior. However, as the trained policy learns to be more successful, the negative examples (the ones produced by the agent) become increasingly similar to expert ones. Despite the fact that the task is successfully accomplished in some of the agent's trajectories, the discriminator is trained to output low values for them. We hypothesize that this inconsistent training signal for the discriminator can impede its learning, and consequently leads to worse overall performance of the agent. We show experimental evidence for this hypothesis and that the 'False Negatives' (i.e. successful agent episodes) significantly hinder adversarial imitation learning, which is the first contribution of this paper. Then, we propose a method to alleviate the impact of false negatives and test it on the BabyAI environment. This method consistently improves sample efficiency over the baselines by at least an order of magnitude.
The CLEVR dataset of natural-looking questions about 3D-rendered scenes has recently received much attention from the research community. A number of models have been proposed for this task, many of which achieved very high accuracies of around 97-99%. In this work, we study how systematic the generalization of such models is, that is to which extent they are capable of handling novel combinations of known linguistic constructs. To this end, we test models' understanding of referring expressions based on matching object properties (such as e.g. "the object that is the same size as the red ball") in novel contexts. Our experiments on the thereby constructed CLOSURE benchmark show that state-of-the-art models often do not exhibit systematicity after being trained on CLEVR. Surprisingly, we find that an explicitly compositional Neural Module Network model also generalizes badly on CLOSURE, even when it has access to the ground-truth programs at test time. We improve the NMN's systematic generalization by developing a novel Vector-NMN module architecture with vector-valued inputs and outputs. Lastly, we investigate the extent to which few-shot transfer learning can help models that are pretrained on CLEVR to adapt to CLOSURE. Our few-shot learning experiments contrast the adaptation behavior of the models with intermediate discrete programs with that of the end-to-end continuous models.
In this paper, we present a technique that improves the process of training an agent (using RL) for instruction following. We develop a training curriculum that uses a nominal number of expert demonstrations and trains the agent in a manner that draws parallels from one of the ways in which humans learn to perform complex tasks, i.e by starting from the goal and working backwards. We test our method on the BabyAI platform and show an improvement in sample efficiency for some of its tasks compared to a PPO (proximal policy optimization) baseline.
Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily adapted to any given task with little adaptation and (ii) intuitively appealing modular models that require background knowledge to be instantiated. We compare both types of models in how much they lend themselves to a particular form of systematic generalization. Using a synthetic VQA test, we evaluate which models are capable of reasoning about all possible object pairs after training on only a small subset of them. Our findings show that the generalization of modular models is much more systematic and that it is highly sensitive to the module layout, i.e. to how exactly the modules are connected. We furthermore investigate if modular models that generalize well could be made more end-to-end by learning their layout and parametrization. We find that end-to-end methods from prior work often learn a wrong layout and a spurious parametrization that do not facilitate systematic generalization. Our results suggest that, in addition to modularity, systematic generalization in language understanding may require explicit regularizers or priors.
Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language which is a proper subset of English. The platform also provides a heuristic expert agent for the purpose of simulating a human teacher. We report baseline results and estimate the amount of human involvement that would be required to train a neural network-based agent on some of the BabyAI levels. We put forward strong evidence that current deep learning methods are not yet sufficiently sample efficient when it comes to learning a language with compositional properties.
Recent work has shown that deep reinforcement-learning agents can learn to follow language-like instructions from infrequent environment rewards. However, this places on environment designers the onus of designing language-conditional reward functions which may not be easily or tractably implemented as the complexity of the environment and the language scales. To overcome this limitation, we present a framework within which instruction-conditional RL agents are trained using rewards obtained not from the environment, but from reward models which are jointly trained from expert examples. As reward models improve, they learn to accurately reward agents for completing tasks for environment configurations---and for instructions---not present amongst the expert data. This framework effectively separates the representation of what instructions require from how they can be executed. In a simple grid world, it enables an agent to learn a range of commands requiring interaction with blocks and understanding of spatial relations and underspecified abstract arrangements. We further show the method allows our agent to adapt to changes in the environment without requiring new expert examples.
Commonsense knowledge bases such as ConceptNet represent knowledge in the form of relational triples. Inspired by the recent work by Li et al., we analyse if knowledge base completion models can be used to mine commonsense knowledge from raw text. We propose novelty of predicted triples with respect to the training set as an important factor in interpreting results. We critically analyse the difficulty of mining novel commonsense knowledge, and show that a simple baseline method outperforms the previous state of the art on predicting more novel.