在对话式段落检索中实现Query Resolution and Reading Comprehension
我们的passage retrieval pipeline 如上图 Figure 1 : Given the original current turn query Q and the conversation history H, 首先perform query resolution, 得到扩展后的查询:resolved query [8]. Next, we perform initial retrieval using to get a list of top-k passages P. Finally, for each passage in P, we combine the scores of a reranking module(BERT) and a reading comprehension module to obtain the final ranked list R. The interpolation weight w(应该是比例权重) is optimized on the TREC CAsT 2019 dataset [1].
query resolution :QuReTeC, a binary term classification query resolution model, whic