Concession-First Learning and Coarse-to-Fine Retrieval for Open-Domain Conversational Question Answering

We tackle Open-Domain Conversational Question Answering (abbr., ODCQA), a task of answering questions in multi-turn conversations by mining clues from a large passage collection. Recent progress in deep learning and large-scale Pretrained Language Model (PLM) is driving fast-paced advances in ODCQA. However, the typical retriever-reranker-reader (3R) pipeline framework of the existing ODCQA systems suffers from a potential flaw, which is referred to the unavoidable interference from the reader to reranker. Briefly, there are a large number of shareable parameters between the reader and reranker because they share the same PLM-based encoder. During the gradient backpropagation, their directions of updating PLM parameters are most probably inconsistent, which leads to interference in seeking for the optimal solution. In addition, the recent retriever in 3R framework merely utilizes dense representation. Though, dense retrievers are generally weaker than sparse retrievers in lexical matching for rare entities. To address the aforementioned two issues, we first propose to utilize a weak reader to alleviate the interference, and explore three different methods to pursue the goal, including (1) masking gradient, (2) dropping inputs and (3) early stopping. Besides, we propose to hybridize a semanticsensitive dense retriever and a keyword-sensitive sparse retriever, so as to enhance the robustness of retriever in dealing with rare entities. We conduct extensive experiments on the benchmark corpus OR-QUAC. Experimental results show that our approach outperforms the State-of-The-Art (SoTA) models, yeilding an improvement of 6.1% F1-score.