Large language models (LLMs) have demonstrated remarkable generalizabili...
Natural language understanding (NLU) models often suffer from unintended...
Event temporal reasoning aims at identifying the temporal relations betw...
Entity bias widely affects pretrained (large) language models, causing t...
Entity names play an effective role in relation extraction (RE) and ofte...
Manipulating objects without grasping them is an essential component of ...
Large language models (LLMs) encode parametric knowledge about world fac...
Relation extraction (RE), which has relied on structurally annotated cor...
Relation Extraction (RE) has been extended to cross-document scenarios
b...
A simple gripper can solve more complex manipulation tasks if it can uti...
Parameter-efficient tuning aims at updating only a small subset of param...
Relation extraction (RE) models have been challenged by their reliance o...
Entity types and textual context are essential properties for sentence-l...
Recent literature focuses on utilizing the entity information in the
sen...
Current question answering (QA) systems primarily consider the single-an...
Robots will experience non-stationary environment dynamics throughout th...
Deep neural networks are often overparameterized and may not easily achi...
Pretrained transformers achieve remarkable performance when the test dat...
Recent efforts for information extraction have relied on many deep neura...
Deploying Reinforcement Learning (RL) agents in the real-world require t...
Sentence-level relation extraction (RE) aims at identifying the relation...
The goal of offline reinforcement learning is to learn a policy from a f...
Document-level relation extraction (RE) poses new challenges compared to...
We propose Learning Off-Policy with Online Planning (LOOP), combining th...
In this paper, we propose a variational approach to unsupervised sentime...
Large pre-trained sentence encoders like BERT start a new chapter in nat...
Deep neural networks usually require massive labeled data, which restric...
Deep neural networks usually require massive labeled data, which restric...
While deep neural models have gained successes on information extraction...
A key challenge in reinforcement learning (RL) is environment generaliza...
In this paper, we propose a variational approach to weakly supervised
do...