Experimental results on five benchmarks and four cross-domain datasets show the lexicon-based graph convolutional network successfully captures the information of candidate words and helps to improve performance on the benchmarks (Bakeoff-2005 and CTB6) and the cross-domain datasets (SIGHAN-2010).
Besides, the robustness of the previous neural methods is limited by the large-scale annotated data.
Chinese word segmentation (CWS) is an essential task for Chinese downstream NLP tasks.
To address the aforementioned issues, we propose a History-Aware Conversational Dense Retrieval (HAConvDR) system, which incorporates two ideas: context-denoised query reformulation and automatic mining of supervision signals based on the actual impact of historical turns.
An effective way to improve retrieval effectiveness is to expand the current query with historical queries.
In this paper, we propose ConvGQR, a new framework to reformulate conversational queries based on generative pre-trained language models (PLMs), one for query rewriting and another for generating potential answers.