论文标题
通过大型复杂文档上的基于变压器的模型提高Q＆A精度的技术
Techniques to Improve Q&A Accuracy with Transformer-based models on Large Complex Documents
论文作者
论文摘要
本文讨论了各种文本处理技术的有效性，它们的组合以及编码以降低给定文本语料库中的复杂性和大小。简化的文本语料库被发送到BERT（或类似的基于变压器的模型）进行问答，并可以对用户查询产生更相关的回答。本文采用了一种科学方法来确定各种技术的益处和有效性，并得出结论最佳组合，从而在准确性上产生统计学上的显着提高。
This paper discusses the effectiveness of various text processing techniques, their combinations, and encodings to achieve a reduction of complexity and size in a given text corpus. The simplified text corpus is sent to BERT (or similar transformer based models) for question and answering and can produce more relevant responses to user queries. This paper takes a scientific approach to determine the benefits and effectiveness of various techniques and concludes a best-fit combination that produces a statistically significant improvement in accuracy.
