An Accurate Model for Predicting the (Graded) Effect of Context in Word Similarity Based on Bert
This work addresses a specific NLP task for semantic analysis, with incremental improvements in performance.
The paper tackled the problem of predicting how context affects human perception of word similarity, achieving first place in the Finnish track and second place in the English track of SemEval 2020 subtask1.
Natural Language Processing (NLP) has been widely used in the semantic analysis in recent years. Our paper mainly discusses a methodology to analyze the effect that context has on human perception of similar words, which is the third task of SemEval 2020. We apply several methods in calculating the distance between two embedding vector generated by Bidirectional Encoder Representation from Transformer (BERT). Our team will_go won the 1st place in Finnish language track of subtask1, the second place in English track of subtask1.