While coreference resolution typically involves various linguistic challenges, recent models are based on a single pairwise scorer for all types of pairs. We present LingMess, a new coreference model that defines different categories of coreference cases and optimize multiple pairwise scorers, where each scorer learns a specific set of linguistic challenges. Our model substantially improves pairwise scores for most categories and outperforms cluster-level performance on Ontonotes. Our model is available in https://github.com/shon-otmazgin/lingmess-coref
翻译：虽然共同参照分辨率通常涉及各种语言挑战,但最近的一些模式是以所有类型配对的单一对比分计分器为基础的。我们介绍了LingMess,这是一个新的共同参照模式,它界定了不同类别的共同参照案例,优化了多对称得分器,每个得分器都学习了一套具体的语言挑战。我们的模型大大改进了大多数类别的对等得分,并优于在Ontonotes上的集群业绩。我们的模型可在https://github.com/shon-otmazgin/lingmes-coref查阅。
相关内容
微信扫码咨询专知VIP会员