论文标题
关于选择答案句子的效率，准确性和文档结构的研究
A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection
论文作者
论文摘要
大多数问题答案（QA）系统的一项重要任务是重新列入候选答案集，即答案句子选择（A2S）。这些候选人通常是从保存其自然顺序的一个或多个文件中提取的句子，或者是由搜索引擎检索的。大多数最新的任务方法都使用巨大的神经模型，例如BERT或复杂的专心架构。在本文中，我们认为，通过利用原始等级的固有结构以及有效的单词相关性编码器，我们可以在保持高效率的同时，就最新的状态获得竞争成果。我们的模型需要9.5秒才能在Wikiqa数据集上进行训练，即与标准Bert-Base微调所需的$ \ sim 18 $分钟相比，非常快。
An essential task of most Question Answering (QA) systems is to re-rank the set of answer candidates, i.e., Answer Sentence Selection (A2S). These candidates are typically sentences either extracted from one or more documents preserving their natural order or retrieved by a search engine. Most state-of-the-art approaches to the task use huge neural models, such as BERT, or complex attentive architectures. In this paper, we argue that by exploiting the intrinsic structure of the original rank together with an effective word-relatedness encoder, we can achieve competitive results with respect to the state of the art while retaining high efficiency. Our model takes 9.5 seconds to train on the WikiQA dataset, i.e., very fast in comparison with the $\sim 18$ minutes required by a standard BERT-base fine-tuning.
