Reasoning is a cognitive process of using evidence to reach a sound
conc...
Self-supervised sound source localization is usually challenged by the
m...
Nowadays, autonomous cars can drive smoothly in ordinary cases, and it i...
Large language models rely on real-valued representations of text to mak...
Compositional neural scene graph studies have shown that radiance fields...
We introduce a novel dependency parser, the hexatagger, that constructs
...
We uncover a systematic bias in the evaluation paradigm of adopting larg...
We show that most structured prediction problems can be solved in linear...
Pretrained language models have achieved remarkable success in a variety...
In the constant updates of the product dialogue systems, we need to retr...
Video multimodal fusion aims to integrate multimodal signals in videos, ...
Several recent papers claim human parity at sentence-level Machine
Trans...
Continual learning (CL) aims to constantly learn new knowledge over time...
Continual relation extraction (CRE) models aim at handling emerging new
...
The k-tensor Ising model is an exponential family on a p-dimensional
bin...
Operating unmanned aerial vehicles (UAVs) in complex environments that
f...
We study the approximability of the four-vertex model, a special case of...
Harvesting question-answer (QA) pairs from customer service chatlog in t...
Recent years have seen a paradigm shift in NLP towards using pretrained
...
Machine translation (MT) has almost achieved human parity at sentence-le...
While interacting with chatbots, users may elicit multiple intents in a
...
As a powerful Bayesian non-parameterized algorithm, the Gaussian process...
Continual relation extraction (CRE) aims to continually learn new relati...
Continual relation extraction (CRE) requires the model to continually le...
A crucial task in the political redistricting problem is to sample
redis...
Many natural language processing tasks, e.g., coreference resolution and...
Fine-tuning pretrained language models (PLMs) on downstream tasks has be...
Most previous studies aim at extracting events from a single sentence, w...
Hierarchical text classification (HTC) is a challenging subtask of
multi...
As Abstract Meaning Representation (AMR) implicitly involves compound
se...
In modern sales applications, automatic script extraction and management...
The visible capability is critical in many robot applications, such as
i...
PAC-Bayesian is an analysis framework where the training error can be
ex...
Multi-task indoor scene understanding is widely considered as an intrigu...
Abstract Meaning Representation (AMR) parsing translates sentences to th...
Few-Shot Sequence Labeling (FSSL) is a canonical solution for the taggin...
Few-Shot Event Classification (FSEC) aims at developing a model for even...
The movement of humans and goods in cities can be represented by constra...
Aspect Sentiment Triplet Extraction (ASTE) aims to recognize targets, th...
Document-level event extraction aims to recognize event information from...
Reasoning is one of the major challenges of Human-like AI and has recent...
The manpower scheduling problem is a kind of critical combinational
opti...
The manpower scheduling problem is a critical research field in the reso...
Many methods have been proposed to detect concept drift, i.e., the chang...
Large pretrained generative models like GPT-3 often suffer from hallucin...
For real-time multirotor kinodynamic motion planning, the efficiency of
...
In open domain table-to-text generation, we notice that the unfaithful
g...
Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from...
By leveraging experience from previous tasks, meta-learning algorithms c...
An innumerable number of individual choices go into discovering a new bo...