Antonym-Synonym Classification Based on New Sub-space Embeddings
This work addresses a key problem in lexical-semantic relation extraction for NLP applications, offering an incremental improvement over prior solutions.
The paper tackles the challenge of distinguishing antonyms from synonyms in NLP by proposing a novel approach using pre-trained embeddings and a Distiller model to extract task-specific information, achieving superior performance and speed compared to existing methods.
Distinguishing antonyms from synonyms is a key challenge for many NLP applications focused on the lexical-semantic relation extraction. Existing solutions relying on large-scale corpora yield low performance because of huge contextual overlap of antonym and synonym pairs. We propose a novel approach entirely based on pre-trained embeddings. We hypothesize that the pre-trained embeddings comprehend a blend of lexical-semantic information and we may distill the task-specific information using Distiller, a model proposed in this paper. Later, a classifier is trained based on features constructed from the distilled sub-spaces along with some word level features to distinguish antonyms from synonyms. Experimental results show that the proposed model outperforms existing research on antonym synonym distinction in both speed and performance.