Reasoning is a cognitive process of using evidence to reach a sound
conc...
Few-shot sequence labeling aims to identify novel classes based on only ...
Traditional multitask learning methods basically can only exploit common...
Multilingual pre-trained language models have demonstrated impressive
(z...
We uncover a systematic bias in the evaluation paradigm of adopting larg...
Pretrained language models have achieved remarkable success in a variety...
In the constant updates of the product dialogue systems, we need to retr...
Video multimodal fusion aims to integrate multimodal signals in videos, ...
Context-dependent Text-to-SQL aims to translate multi-turn natural langu...
Continual relation extraction (CRE) models aim at handling emerging new
...
When students make a mistake in an exercise, they can consolidate it by
...
Recently, more and more people study online for the convenience of acces...
Harvesting question-answer (QA) pairs from customer service chatlog in t...
We present DualNER, a simple and effective framework to make full use of...
Contrastive learning has become a new paradigm for unsupervised sentence...
Stroke is the basic element of Chinese character and stroke extraction h...
While interacting with chatbots, users may elicit multiple intents in a
...
Chinese Grammatical Error Correction (CGEC) is both a challenging NLP ta...
Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling...
Continual relation extraction (CRE) aims to continually learn new relati...
Continual relation extraction (CRE) requires the model to continually le...
To automatically correct handwritten assignments, the traditional approa...
Entity Set Expansion (ESE) is a valuable task that aims to find entities...
Chinese Spell Checking (CSC) task aims to detect and correct Chinese spe...
Context-dependent text-to-SQL is the task of translating multi-turn ques...
Hierarchical text classification (HTC) is a challenging subtask of
multi...
In modern sales applications, automatic script extraction and management...
Grammatical Error Correction (GEC) aims to automatically detect and corr...
Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling...
The standard BERT adopts subword-based tokenization, which may break a w...
Cognitive diagnosis, the goal of which is to obtain the proficiency leve...
Existing text- and image-based multimodal dialogue systems use the
tradi...
Math Word Problem (MWP) solving needs to discover the quantitative
relat...
Few-Shot Sequence Labeling (FSSL) is a canonical solution for the taggin...
In multi-label text classification (MLTC), each given document is associ...
Chinese Spell Checking (CSC) aims to detect and correct erroneous charac...
In educational applications, Knowledge Tracing (KT), the problem of
accu...
Pre-trained Transformer-based neural language models, such as BERT, have...
We study the learning of a matching model for dialogue response selectio...
In a multi-turn knowledge-grounded dialog, the difference between the
kn...
This paper introduces one of our group's work on the Dialog System Techn...