QuoteR: A Benchmark of Quote Recommendation for Writing
This work addresses the problem of inconsistent benchmarking for quote recommendation, primarily benefiting researchers in natural language processing and writing assistance tools, though it is incremental as it builds on existing methods with a new dataset.
The authors tackled the lack of standardized evaluation in quote recommendation by building QuoteR, a large open dataset in English, standard Chinese, and classical Chinese, and proposed a new model that significantly outperformed previous methods on all parts of the dataset.
It is very common to use quotations (quotes) to make our writings more elegant or convincing. To help people find appropriate quotes efficiently, the task of quote recommendation is presented, aiming to recommend quotes that fit the current context of writing. There have been various quote recommendation approaches, but they are evaluated on different unpublished datasets. To facilitate the research on this task, we build a large and fully open quote recommendation dataset called QuoteR, which comprises three parts including English, standard Chinese and classical Chinese. Any part of it is larger than previous unpublished counterparts. We conduct an extensive evaluation of existing quote recommendation methods on QuoteR. Furthermore, we propose a new quote recommendation model that significantly outperforms previous methods on all three parts of QuoteR. All the code and data of this paper are available at https://github.com/thunlp/QuoteR.