Instead of relying on human-annotated training samples to build a classi...
A real-world text corpus sometimes comprises not only text documents but...
Edges in many real-world social/information networks are associated with...
Due to the exponential growth of scientific publications on the Web, the...
Masked Language Modeling (MLM) has been one of the most prominent approa...
Instead of mining coherent topics from a given text corpus in a complete...
Recent studies have revealed the intriguing few-shot learning ability of...
We study the problem of few-shot Fine-grained Entity Typing (FET), where...
Discovering latent topics from text corpora has been studied for decades...
We present a new framework AMOS that pretrains text encoders with an
Adv...
Topic models have been the prominent tools for automatic topic discovery...
Pretrained language models (PLMs) have demonstrated remarkable performan...
As a core technology of the autonomous driving system, pedestrian trajec...
We study the problem of weakly supervised text classification, which aim...
Opinion summarization aims to profile a target by extracting opinions fr...
We study the problem of training named entity recognition (NER) models u...
Identifying and understanding quality phrases from context is a fundamen...
We present COCO-LM, a new self-supervised learning framework that pretra...
Categorizing documents into a given label hierarchy is intuitively appea...
Current text classification methods typically require a good number of
h...
Taxonomy is not only a fundamental form of knowledge representation, but...
Aspect-based sentiment analysis of review texts is of great value for
un...
Mining a set of meaningful topics organized into a hierarchy is intuitiv...
Document categorization, which aims to assign a topic label to each docu...
In personal email search, user queries often impose different requiremen...
Unsupervised text embedding has shown great power in a wide range of NLP...
GitHub has become an important platform for code sharing and scientific
...
Intensive computation is entering data centers with multiple workloads o...
Unsupervised word embedding has benefited a wide spectrum of NLP tasks d...
Hierarchical text classification, which aims to classify text documents ...
Deep neural networks are gaining increasing popularity for the classic t...
Monocular camera systems are prevailing in intelligent transportation
sy...