Controllable text generation is a fundamental aspect of natural language...
Retrieval-Augmented Generation (RAG) is a promising approach for mitigat...
Enabling large language models to effectively utilize real-world tools i...
Named entity recognition in real-world applications suffers from the
div...
Understanding documents is central to many real-world tasks but remains ...
Memory is one of the most essential cognitive functions serving as a
rep...
Event schema provides a conceptual, structural and formal language to
re...
Large language models (LLMs) like ChatGPT have gained increasing promine...
Large language models (LLMs) such as ChatGPT and GPT-4 have made signifi...
Knowledge plays a critical role in artificial intelligence. Recently, th...
Since the meaning representations are detailed and accurate annotations ...
The challenge of information extraction (IE) lies in the diversity of la...
Entity matching (EM) is the most critical step for entity resolution (ER...
Information extraction suffers from its varying targets, heterogeneous
s...
Low-shot relation extraction (RE) aims to recognize novel relations with...
Events are considered as the fundamental building blocks of the world. M...
Prompt-based probing has been widely used in evaluating the abilities of...
Few-shot NER needs to effectively capture information from limited insta...
Procedural text understanding requires machines to reason about entity s...
Bootstrapping has become the mainstream method for entity set expansion....
Event detection has long been troubled by the trigger curse:
overfitting...
Conventional entity typing approaches are based on independent classific...
Despite recent success in machine reading comprehension (MRC), learning
...
Open relation extraction aims to cluster relation instances referring to...
Denoising is the essential step for distant supervision based named enti...
Distant supervision tackles the data bottleneck in NER by automatically
...
Event extraction is challenging due to the complex structure of event re...
Previous literatures show that pre-trained masked language models (MLMs)...
Current event-centric knowledge graphs highly rely on explicit connectiv...
Semantic parsing is challenging due to the structure gap and the semanti...
BERT-based text ranking models have dramatically advanced the
state-of-t...
One of the biggest bottlenecks in building accurate, high coverage neura...
A fundamental ability of humans is to utilize commonsense knowledge in
l...
Distant supervision (DS) is a promising approach for relation extraction...
ISCAS participated in two subtasks of SemEval 2020 Task 5: detecting
cou...
Traditional event coreference systems usually rely on pipeline framework...
Query expansion aims to mitigate the mismatch between the language used ...
Fine-tuning pretrained model has achieved promising performance on stand...
Knowledge graph models world knowledge as concepts, entities, and the
re...
In this paper, we introduce CAIL2019-SCM, Chinese AI and Law 2019 Simila...
In supervised event detection, most of the mislabeling occurs between a ...
Sequential labeling-based NER approaches restrict each word belonging to...
A major challenge of semantic parsing is the vocabulary mismatch problem...
In this paper, we give an overview of the Legal Judgment Prediction (LJP...
This paper proposes a neural semantic parsing approach -- Sequence-to-Ac...
In this paper, we introduce the Chinese AI and Law
challenge dataset (CA...
This paper focuses on detection tasks in information extraction, where
p...
Neural network based models commonly regard event detection as a word-wi...
Partially inspired by successful applications of variational recurrent n...