In particular, we first unify the fine-grained user similarity and the complex matching between user preferences and spatiotemporal activity into a heterogeneous hypergraph.
On the other hand, GUS is introduced to suppress the feature ambiguity in the representation space.
We build the recommenders on the Amazon US Reviews dataset, and tune the pretrained BERT and RoBERTa with the traditional fine-tuned paradigm as well as the new prompt-based learning paradigm.
Structured (tabular) data in the preclinical and clinical domains contains valuable information about individuals and an efficient table-to-text summarization system can drastically reduce manual efforts to condense this data into reports.
This paper proposes a scalable workflow which leverages both structured data and unstructured textual notes from EHRs with techniques including NLP, AutoML and Clinician-in-the-Loop mechanism to build machine learning classifiers to identify patients at scale with given diseases, especially those who might currently be miscoded or missed by ICD codes.
TS PostDiff takes a Bayesian approach to mixing TS and UR: the probability a participant is assigned using UR allocation is the posterior probability that the difference between two arms is `small' (below a certain threshold), allowing for more UR exploration when there is little or no reward to be gained.
Contextualised word embeddings is a powerful tool to detect contextual synonyms.
This paper considers nonlinear measures of intergenerational income mobility such as (i) the effect of parents' permanent income on the entire distribution of child's permanent income, (ii) transition matrices, and (iii) rank-rank correlations when observed annual incomes are treated as measured-with-error versions of permanent incomes.
Specifically, the encoder of a DL model that is pre-trained on the source domain is used to initialize the encoder of a reconstruction model.
Background: The presence of nuclear ground states with stable reflection-asymmetric shapes is supported by rich experimental evidence.
Sentence-level (SL) machine translation (MT) has reached acceptable quality for many high-resourced languages, but not document-level (DL) MT, which is difficult to 1) train with little amount of DL data; and 2) evaluate, as the main methods and data sets focus on SL evaluation.
In order to address these limitations, we introduce the concept of cumulative accessibility functions, which measure the reachability of a goal from a given state within a specified horizon.
While the progress of machine translation of written text has come far in the past several years thanks to the increasing availability of parallel corpora and corpora-based training technologies, automatic translation of spoken text and dialogues remains challenging even for modern systems.
Ranked #1 on Machine Translation on Business Scene Dialogue JA-EN (using extra training data)
The goal is to facilitate the learning process in the target segments by leveraging the learned knowledge from data-sufficient source segments.
Our approach results in (generally informative) bounds on the effect of the policy on actual cases and in point identification of the effect of the policy on other outcomes.
Edge intelligence refers to a set of connected systems and devices for data collection, caching, processing, and analysis in locations close to where data is captured based on artificial intelligence.
In addition, our analysis also pinpoints the importance of choosing a diverging scaling parameter when using Gaussian kernels and suggests a data-driven choice of the scaling parameter that yields tests optimal, up to an iterated logarithmic factor, over a wide range of smooth alternatives.
Human-object interactions (HOI) recognition and pose estimation are two closely related tasks.
To cope with these challenges, we present C2TCP, a flexible end-to-end solution targeting interactive applications requiring high throughput and low delay in cellular networks.
Networking and Internet Architecture
The reproducing kernel Hilbert space (RKHS) embedding of distributions offers a general and flexible framework for testing problems in arbitrary domains and has attracted considerable amount of attention in recent years.