Augmenting pre-trained language models with knowledge graphs (KGs) has achieved success on various commonsense reasoning tasks. However, for a given task instance, the KG, or certain parts of the KG, may not be useful. Although KG-augmented models often use attention to focus on specific KG components, the KG is still always used, and the attention mechanism is never explicitly taught which KG components should be used. Meanwhile, saliency methods can measure how much a KG feature (e.g., graph, node, path) influences the model to make the correct prediction, thus explaining which KG features are useful. This paper explores how saliency explanations can be used to improve KG-augmented models' performance. First, we propose to create coarse (Is the KG useful?) and fine (Which nodes/paths in the KG are useful?) saliency explanations. Second, to motivate saliency-based supervision, we analyze oracle KG-augmented models which directly use saliency explanations as extra inputs for guiding their attention. Third, we propose SalKG, a framework for KG-augmented models to learn from coarse and/or fine saliency explanations. Given saliency explanations created from a task's training set, SalKG jointly trains the model to predict the explanations, then solve the task by attending to KG features highlighted by the predicted explanations. On three commonsense QA benchmarks (CSQA, OBQA, CODAH) and a range of KG-augmented models, we show that SalKG can yield considerable performance gains -- up to 2.76% absolute improvement on CSQA.
翻译:以知识图形( KGs) 增强培训前语言模型, 包括知识图形( KGs), 在各种常见推理任务中取得了成功。 但是, 对于特定任务实例来说, KG 或 KG 的某些部分可能没有用处。 虽然 KG 推荐模型经常关注特定 KG 组件, KG 仍然总是被使用, 关注机制从未被明确教授应该使用 KG 组件。 同时, 突出的方法可以测量 KG 特性( 例如, 图形、 节点、 路径) 在多大程度上影响模型来做出正确的预测, 从而解释 KG 的哪些功能是有用的。 但是, 本文探索了如何使用突出的解释来提高 KG 推荐模型的性能。 首先, 我们提议创建粗略( KG 有用吗? ) 和细微( KG 的节点/ 路径有用? ) ) 突出的解释。 其次, 激励基于模型的监管, 我们分析 KG 和 CG 缩略度解释, 直接使用突出的解释来引导其注意力的 CG 。 第三, 我们提议从 CG 绝对解释 的 CG 和 CG 共同的 的 CG 任务框架。