Paper: Combining Word Patterns and Discourse Markers for Paradigmatic Relation Classification

ACL ID P14-2086
Title Combining Word Patterns and Discourse Markers for Paradigmatic Relation Classification
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Distinguishing between paradigmatic rela- tions such as synonymy, antonymy and hy- pernymy is an important prerequisite in a range of NLP applications. In this paper, we explore discourse relations as an alter- native set of features to lexico-syntactic patterns. We demonstrate that statistics over discourse relations, collected via ex- plicit discourse markers as proxies, can be utilized as salient indicators for paradig- matic relations in multiple languages, out- performing patterns in terms of recall and F 1 -score. In addition, we observe that markers and patterns provide complemen- tary information, leading to significant classification improvements when applied in combination.