arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.09598cs.CLcs.LG
收藏

DP-KB:知识库数据编程改进了Transformer对答案句子选择的微调

DP-KB: Data Programming with Knowledge Bases Improves Transformer Fine Tuning for Answer Sentence Selection

Alexa AI(亚马逊Alexa人工智能部门)

Nic Jedema, Thuy Vu, Manish Gupta, Alessandro Moschitti

摘要:

虽然Transformers在许多知识密集型(KI)任务上表现出令人印象深刻的性能,但它们作为隐式知识库(KB)的能力仍然有限,如几个插槽填充,问答(QA),事实验证和实体链接任务所示。在本文中,我们实现了一个高效的,数据编程技术,丰富的训练数据与知识库派生的上下文,并提高Transformer利用编码的知识时,微调一个特定的QA任务,即答案句子选择(AS2)。我们的方法优于最先进的Transformer方法在WikiQA和TrecQA,两个广泛研究的AS2基准测试中,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,我们还在Alexa QA对的专有数据集上评估了我们的方法,并显示F1增加了2.3%,MAP增加了2.0%。我们还发现,即使在推理时省略KB上下文,这些改进仍然存在,允许在现有的Transformer工作流中使用我们的模型,而不会产生额外的延迟或部署成本。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑