Combining Word Patterns and Discourse Markers for Paradigmatic Relation Classification
Combining Word Patterns and Discourse Markers for Paradigmatic Relation Classification
复制标题
DOI：
10.3115/v1/p14-2086
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
Michael Roth;Sabine Schulte im Walde
中科院分区：
文献类型：
--
作者：
Michael Roth;Sabine Schulte im Walde
区分同义关系、反义关系和上位关系等聚合关系是NLP应用的一个重要前提。在本文中，我们探讨话语关系作为一个替代的一套功能，词汇句法模式。我们表明，统计话语关系，收集通过明确的话语标记作为代理，可以被用来作为突出的指标，在多种语言的聚合关系，优于模式的召回和F1分数。此外，我们观察到，标记和模式提供了互补的信息，导致显着的分类改进时，组合应用。
Distinguishing between paradigmatic relations such as synonymy, antonymy and hypernymy is an important prerequisite in a range of NLP applications. In this paper, we explore discourse relations as an alternative set of features to lexico-syntactic patterns. We demonstrate that statistics over discourse relations, collected via explicit discourse markers as proxies, can be utilized as salient indicators for paradigmatic relations in multiple languages, outperforming patterns in terms of recall and F1-score. In addition, we observe that markers and patterns provide complementary information, leading to significant classification improvements when applied in combination.