Predicting Word Similarity in Context with Referential Translation Machines
This addresses the challenge of context-dependent word similarity for natural language processing applications, but appears incremental as it builds on existing RTM methods.
The paper tackles the problem of predicting word similarity in context by framing it as machine translation performance prediction between words, using referential translation machines (RTMs) to achieve top results in the Graded Word Similarity in Context (GWSC) task.
We identify the similarity between two words in English by casting the task as machine translation performance prediction (MTPP) between the words given the context and the distance between their similarities. We use referential translation machines (RTMs), which allows a common representation for training and test sets and stacked machine learning models. RTMs can achieve the top results in Graded Word Similarity in Context (GWSC) task.