An Analogical Reasoning Method Based on Multi-task Learning with Relational Clustering

Analogical QA task is a challenging natural language processing problem. When two word pairs are similar in their relationships, we refer to their relations as analogous. Although the analogy method based on word embedding is well developed, the analogy reasoning is far beyond this scope. At present, the methods based on pre-trained language models have explored only the tip of the iceberg. In this paper, we proposed a multi-task learning method for analogical QA task. First, we obtain word-pair representations by leveraging the output embeddings of the [MASK] token in the pre-trained language model. The representations are prepared for two tasks. The first task aims to train an analogical classifier by supervised learning. The second task is an auxiliary task based on relation clustering to generate relation pseudo-labels for word pairs and train relation classifier. Our method guides the model to analyze the relation similarity in analogical reasoning without relation labels. The experiments show that our method achieve excellent performance on four analogical reasoning datasets without the help of external corpus and knowledge. In the most difficult data set E-KAR, it has increased by at least 4%.