In this paper, we investigate the in-context learning ability of
retriev...
Large Language Models (LLMs) bring transformative benefits alongside uni...
In this work, we study the problem of unsupervised open-domain keyphrase...
When answering complex questions, large language models (LLMs) may produ...
The advancement of large language models (LLMs) brings notable improveme...
We propose and study Complementary Concept Generation (CCGen): given a
c...
Expository documents are vital resources for conveying complex informati...
Recent advancements in Large Language Models, such as ChatGPT, have
demo...
In this paper, we propose DimonGen, which aims to generate diverse sente...
Reasoning is a fundamental aspect of human intelligence that plays a cru...
Entities and relationships between entities are vital in the real world....
Open Information Extraction (OpenIE) has been used in the pipelines of
v...
We propose a new problem called coordinated topic modeling that imitates...
A good speaker not only needs to be correct, but also has the ability to...
Large Pre-Trained Language Models (PLMs) have facilitated and dominated ...
In this paper, we propose Descriptive Knowledge Graph (DKG) - an open an...
We propose a probabilistic approach to select a subset of a target
domai...
Definitions are essential for term understanding. Recently, there is an
...
Webpage information extraction (WIE) is an important step to create know...
Relations between entities can be represented by different instances, e....
We propose to measure fine-grained domain relevance - the degree that a ...
We introduce and study semantic capacity of terms. For example, the sema...
Message-passing neural networks (MPNNs) have been successfully applied t...
Researchers often query online social platforms through their applicatio...
In this paper, we study the problem of using representation learning to
...
Graph is an important data representation which appears in a wide divers...
Graph embedding provides an efficient solution for graph analysis by
con...
Most existing community-related studies focus on detection, which aim to...
Most of the existing graph embedding methods focus on nodes, which aim t...