Representation learning is a critical ingredient for natural language processing systems.
Recent Transformer language models like BERT learn powerful textual representations, but …

Mutual information (MI) minimization has gained considerable interests in various machine
learning tasks. However, estimating and minimizing MI in high-dimensional spaces remains …

Cross-Domain Recommendation (CDR) is capable of incorporating auxiliary information
from multiple domains to advance recommendation performance. Conventional CDR …

We address the problem of learning on sets of features, motivated by the need of performing
pooling operations in long biological sequences of varying sizes, with long-range …

Multimodal hate detection, which aims to identify the harmful content online such as memes,
is crucial for building a wholesome internet environment. Previous work has made …

The nucleus of online sponsored search systems lies in measuring the relevance between
the search intents of users and the advertising purposes of advertisers. Existing …

Summarizing biomedical discovery from genomics data using natural languages is an
essential step in biomedical research but is mostly done manually. Here, we introduce …

Abstract Event Causality Extraction (ECE) aims to extract the cause-effect event pairs from
the given text, which requires the model to possess a strong reasoning ability to capture …

Generating temporally-ordered event sequences in texts is important to natural language
processing. Two emerging tasks in this direction are temporal event ordering (rearranging …

Text documents are often interconnected in a network structure, eg, academic papers via
citations, Web pages via hyperlinks. On the one hand, though Graph Neural Networks …