Machine learning has been highly successful in data-intensive applications but is often
hampered when the data set is small. Recently, Few-shot Learning (FSL) is proposed to …

Deep learning has been the mainstream technique in natural language processing (NLP)
area. However, the techniques require many labeled data and are less generalizable across …

Current language models are unable to quickly learn new concepts on the fly, often
requiring a more involved finetuning process to learn robustly. Prompting in-context is not …

The capability of learning and generalizing from very few samples successfully is a
noticeable demarcation separating artificial intelligence and human intelligence. Despite the …

Accumulating knowledge to tackle new tasks without necessarily forgetting the old ones is a
hallmark of human-like intelligence. But the current dominant paradigm of machine learning …

Despite differing from the human language processing mechanism in implementation and
algorithms, current language models demonstrate remarkable human-like or surpassing …

Language understanding is a key scientific issue in the fields of cognitive and computer
science. However, the two disciplines differ substantially in the specific research questions …

Deep learning based natural language processing (NLP) has become the mainstream of
research in recent years and significantly outperforms conventional methods. However …

Humans can quickly learn a new word from a few illustrative examples, and then
systematically and flexibly use it in novel contexts. Yet the abilities of current language …

To understand the algorithm that supports the human brain's language representation,
previous research has attempted to predict neural responses to linguistic stimuli using …