Integrating Multiplicative Features into Supervised Distributional Methods for Lexical Entailment
This work addresses a specific issue in natural language processing for lexical entailment, offering an incremental improvement with a new evaluation setup to reduce biases.
The paper tackled the problem that supervised distributional methods for lexical entailment may not learn relations between words by integrating multiplicative features into representations, resulting in improved performance across different classifiers and evaluation setups.
Supervised distributional methods are applied successfully in lexical entailment, but recent work questioned whether these methods actually learn a relation between two words. Specifically, Levy et al. (2015) claimed that linear classifiers learn only separate properties of each word. We suggest a cheap and easy way to boost the performance of these methods by integrating multiplicative features into commonly used representations. We provide an extensive evaluation with different classifiers and evaluation setups, and suggest a suitable evaluation setup for the task, eliminating biases existing in previous ones.