Recognition of Mental Adjectives in An Efficient and Automatic Style
This work addresses a specific problem in natural language processing for researchers by proposing an incremental improvement in resource-efficient classification for commonsense reasoning.
The authors tackled the problem of commonsense reasoning by introducing a new lexical inference task, Mental and Physical Classification (MPC), to categorize words into mental and physical attributes. They fine-tuned a BERT model with active learning, achieving satisfactory accuracy while requiring only about 300 labeled words.
In recent years, commonsense reasoning has received more and more attention from academic community. We propose a new lexical inference task, Mental and Physical Classification (MPC), to handle commonsense reasoning in a reasoning graph. Mental words relate to mental activities, which fall into six categories: Emotion, Need, Perceiving, Reasoning, Planning and Personality. Physical words describe physical attributes of an object, like color, hardness, speed and malleability. A BERT model is fine-tuned for this task and active learning algorithm is adopted in the training framework to reduce the required annotation resources. The model using ENTROPY strategy achieves satisfactory accuracy and requires only about 300 labeled words. We also compare our result with SentiWordNet to check the difference between MPC and subjectivity classification task in sentiment analysis.