Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
This work addresses hypernymy detection for NLP applications, representing an incremental advance by combining existing approaches.
The paper tackled hypernymy detection by integrating path-based and distributional methods, achieving significant improvements over the state-of-the-art.
Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complementary approaches. Distributional methods, whose supervised variants are the current best performers, and path-based methods, which received less research attention. We suggest an improved path-based algorithm, in which the dependency paths are encoded using a recurrent neural network, that achieves results comparable to distributional methods. We then extend the approach to integrate both path-based and distributional signals, significantly improving upon the state-of-the-art on this task.