Chinese Spelling Correction (CSC) aims to detect and correct erroneous
c...
Retrieving proper domain knowledge from an external database lies at the...
To model the dependencies between utterances in multi-party conversation...
Predicting personality traits based on online posts has emerged as an
im...
Fine-tuning large pre-trained language models on downstream tasks is apt...
Prompt tuning learns soft prompts to condition frozen Pre-trained Langua...
Task-oriented dialog (TOD) systems often require interaction with an ext...
This paper studies the exposure bias problem in task-oriented dialog sys...
Due to exposure bias, most existing natural language generation (NLG) mo...
Video captioning is a challenging task as it needs to accurately transfo...
Network embedding is an effective technique to learn the low-dimensional...
Structure information extraction refers to the task of extracting struct...
Most of the recent work on personality detection from online posts adopt...
The major paradigm of applying a pre-trained language model to downstrea...
Dialogue policy learning, a subtask that determines the content of syste...
The modeling of conversational context plays a vital role in emotion
rec...
We study the problem of leveraging the syntactic structure of text to en...
This paper presents our pioneering effort for emotion recognition in
con...
This paper presents our task-oriented dialog system UBAR which models
ta...
Aspect term extraction aims to extract aspect terms from review texts as...
Generating fluent and informative responses is of critical importance fo...
Aspect-based sentiment analysis aims to determine the sentiment polarity...
Textual network embeddings aim to learn a low-dimensional representation...
The success of neural summarization models stems from the meticulous
enc...