Recent advances in foundation models present new opportunities for
inter...
In this paper, we propose a novel method, Chain-of-Thoughts Attribute
Ma...
Knowledge graph embeddings (KGE) have been extensively studied to embed
...
Information extraction, e.g., attribute value extraction, has been
exten...
We present a new task setting for attribute mining on e-commerce product...
We introduce ClusterLLM, a novel text clustering framework that leverage...
Recent advances of incorporating layout information, typically bounding ...
Recent advances in weakly supervised text classification mostly focus on...
Deep neural classifiers trained with cross-entropy loss (CE loss) often
...
Sequential recommendation aims to model dynamic user behavior from histo...
Etremely Weakly Supervised Text Classification (XWS-TC) refers to text
c...
State-of-the-art weakly supervised text classification methods, while
si...
Time-series data augmentation mitigates the issue of insufficient traini...
The output distribution of a neural network (NN) over the entire input s...
Pre-trained seq2seq models excel at graph semantic parsing with rich
ann...
Existing federated classification algorithms typically assume the local
...
Human activity recognition (HAR) aims to classify sensory time series in...
Document images are a ubiquitous source of data where the text is organi...
Multilingual transformer language models have recently attracted much
at...
We propose Waveformer that learns attention mechanism in the wavelet
coe...
Personalized natural language generation for explainable recommendations...
How to train an ideal teacher for knowledge distillation is still an ope...
Manually annotating datasets requires domain experts to read through man...
Weakly supervised text classification methods typically train a deep neu...
Recent relation extraction (RE) works have shown encouraging improvement...
Existing backdoor defense methods are only effective for limited trigger...
Fine-tuning pre-trained language models has recently become a common pra...
Automatic extraction of product attributes from their textual descriptio...
High-quality phrase representations are essential to finding topics and
...
Here, we show that the robust overfitting shall be viewed as the early p...
Existing text classification methods mainly focus on a fixed label set,
...
Backdoor attack introduces artificial vulnerabilities into the model by
...
Reading order detection is the cornerstone to understanding visually-ric...
We study the problem of building entity tagging systems by using a few r...
Identifying and understanding quality phrases from context is a fundamen...
Keyphrase generation aims to summarize long documents with a collection ...
Hashtag annotation for microblog posts has been recently formulated as a...
Contextualized representations based on neural language models have furt...
Text categorization is an essential task in Web content analysis. Consid...
Multiple intriguing problems hover in adversarial training, including
ro...
A sensor name, typically an alphanumeric string, encodes the key context...
In this paper, we explore to conduct text classification with extremely ...
Our goal is to understand why the robustness drops after conducting
adve...
Aspect classification, identifying aspects of text segments, facilitates...
Corpus-based set expansion (i.e., finding the "complete" set of entities...
Set expansion aims to expand a small set of seed entities into a complet...
Everyone makes mistakes. So do human annotators when curating labels for...
Taking word sequences as the input, typical named entity recognition (NE...
Recent advances in deep neural models allow us to build reliable named e...
Literature search is critical for any scientific research. Different fro...