论文标题
DP-KB：具有知识库的数据编程改善了变压器的微调，以选择答案句子。
DP-KB: Data Programming with Knowledge Bases Improves Transformer Fine Tuning for Answer Sentence Selection
论文作者
论文摘要
尽管变形金刚在许多知识密集（KI）任务上表现出令人印象深刻的表现，但它们作为内隐知识库（KB）的能力仍然有限，如几个插槽填充，提问（QA），事实验证和实体链接任务所示。在本文中，我们实施了一种高效的数据编程技术，该技术在微调特定的QA任务（即回答句子选择（AS2））时，用KB衍生的上下文丰富了培训数据，并改善了编码知识的变压器利用。我们的方法在Wikiqa和Trecqa上的最先进的变压器方法的表现超过了两个广泛研究的AS2基准，分别增加了2.0％P@1，1.3％MAP，1.1％MRR和4.4％P@1，0.9％MAP，2.4％MRR。为了证明我们在行业环境中的改进，我们还评估了Alexa QA Pairs的专有数据集的方法，并显示2.3％F1和2.0％的地图增加。我们还发现，即使在推理时间省略了KB上下文，这些改进仍保留，从而允许在现有的变压器工作流程中使用我们的模型，而无需额外的延迟或部署成本。
While transformers demonstrate impressive performance on many knowledge intensive (KI) tasks, their ability to serve as implicit knowledge bases (KBs) remains limited, as shown on several slot-filling, question-answering (QA), fact verification, and entity-linking tasks. In this paper, we implement an efficient, data-programming technique that enriches training data with KB-derived context and improves transformer utilization of encoded knowledge when fine-tuning for a particular QA task, namely answer sentence selection (AS2). Our method outperforms state of the art transformer approach on WikiQA and TrecQA, two widely studied AS2 benchmarks, increasing by 2.0% p@1, 1.3% MAP, 1.1% MRR, and 4.4% p@1, 0.9% MAP, 2.4% MRR, respectively. To demonstrate our improvements in an industry setting, we additionally evaluate our approach on a proprietary dataset of Alexa QA pairs, and show increase of 2.3% F1 and 2.0% MAP. We additionally find that these improvements remain even when KB context is omitted at inference time, allowing for the use of our models within existing transformer workflows without additional latency or deployment costs.
