论文标题
潜在的组成表示改善了接地问题回答的系统概括
Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering
论文作者
论文摘要
回答涉及多步推理的问题需要分解它们，并使用中级步骤的答案来达到最终答案。但是，扎根的问题回答中的最新模型通常不会明确执行分解，从而导致概括到分布范围的示例中的困难。在这项工作中，我们提出了一个模型，该模型使用CKY风格的解析器以自下而上的，组成方式计算所有问题的表示和指示。我们的模型仅在端到端（答案）监督下引起潜在树。我们表明，与在算术表达式基准和关闭方面的强基础相比，这种对树结构的感应偏见显着改善了对分布外示例的系统概括，该数据集侧重于用于接地问题回答的系统概括。在这个具有挑战性的数据集上，我们的模型的准确性为96.1％，显着高于先前的模型，这些模型几乎可以完美地解决任务以随机的，分配的分配。
Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-of-the-art models in grounded question answering often do not explicitly perform decomposition, leading to difficulties in generalization to out-of-distribution examples. In this work, we propose a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser. Our model induces latent trees, driven by end-to-end (the answer) supervision only. We show that this inductive bias towards tree structures dramatically improves systematic generalization to out-of-distribution examples, compared to strong baselines on an arithmetic expressions benchmark as well as on CLOSURE, a dataset that focuses on systematic generalization for grounded question answering. On this challenging dataset, our model reaches an accuracy of 96.1%, significantly higher than prior models that almost perfectly solve the task on a random, in-distribution split.
