Recently, Transformer has achieved great success in Chinese named entity recognition (NER) owing to its good parallelism and ability to model long-range dependencies, which utilizes self-attention to encode context.
SBAG firstly pre-trains a multi-layer perception network to capture social bot features, and then constructs multiple graph neural networks by embedding the features to model the early propagation of posts, which is further used to detect rumors.
Text-driven fashion synthesis and design is an extremely valuable part of artificial intelligence generative content(AIGC), which has the potential to propel a tremendous revolution in the traditional fashion industry.
Recent advances in deep learning and automatic speech recognition have improved the accuracy of end-to-end speech recognition systems, but recognition of personal content such as contact names remains a challenge.
Recent advances in deep learning and automatic speech recognition (ASR) have enabled the end-to-end (E2E) ASR system and boosted the accuracy to a new level.
Finally, we select the most fitting chains of evidence from the evidence forest and integrate them into the generated story, thereby enhancing the narrative's complexity and credibility.
To this end, we employ domain adversarial learning as a heuristic neural network initialization method, which can help the meta-learning module converge to a better optimal.
Theoretically, we prove the convergence of the meta-learning algorithm in MTEM and analyze the effectiveness of MTEM in achieving domain adaptation.
The pelvis, the lower part of the trunk, supports and balances the trunk.
Based on this insight, we propose an approach called DiffuseExpand for expanding datasets for 2D medical image segmentation using DPM, which first samples a variety of masks from Gaussian noise to ensure the diversity, and then synthesizes images to ensure the alignment of images and masks.
In the inductive setting where test TKGs contain emerging entities, the latest methods are based on symbolic rules or pre-trained language models (PLMs).
Generative models, such as Variational Auto-Encoder (VAE) and Generative Adversarial Network (GAN), have been successfully applied in sequential recommendation.
Different from KGs and TKGs in the transductive setting, constantly emerging entities and relations in incomplete TKGs create demand to predict missing facts with unseen components, which is the extrapolation setting.
To be specific, we design a neural network-based data augmentation module with priori bias, which assists in finding what meets the teacher's strengths but the student's weaknesses, by learning magnitudes and probabilities to generate suitable data samples.
Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents.
Maximum mutual information (MMI) has become one of the two de facto methods for sequence-level training of speech recognition acoustic models.
To address these issues, we establish a new high-quality dataset named RealRain-1k, consisting of $1, 120$ high-resolution paired clean and rainy images with low- and high-density rain streaks, respectively.
Specifically, we collect a sheer number of source codes (both Java and Python) from the Alipay code repository and incorporate both syntactic and semantic code knowledge into our model through the help of code parsers, in which AST information of the source codes can be interpreted and integrated.
To alleviate feature suppression, we propose contrastive learning for unsupervised sentence embedding with soft negative samples (SNCSE).
To achieve such an ambitious goal, new mechanisms for foreign pronunciation generation and language model (LM) enrichment have been devised.
The inheritance part is learned with a similarity loss to transfer the existing learned knowledge from the teacher model to the student model, while the exploration part is encouraged to learn representations different from the inherited ones with a dis-similarity loss.
Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID.
Ranked #5 on Person Re-Identification on PRCC
Second, different body parts possess different scales, and even the same part in different frames can appear at different locations and scales.
Ranked #2 on Gait Recognition on OUMVLP
We tackle implicit discourse relation classification, a task of automatically determining semantic relationships between arguments.
The topology of the adjacency graph is a key factor for modeling the correlations of the input skeletons.
Embedding nodes of a large network into a metric (e. g., Euclidean) space has become an area of active research in statistical machine learning, which has found applications in natural and social sciences.
no code implementations • 3 Jun 2020 • Zhi Shiuh Lim, Changjian Li, Zhen Huang, Xiao Chi, Jun Zhou, Shengwei Zeng, Ganesh Ji Omar, Yuan Ping Feng, Andrivo Rusydi, Stephen John Pennycook, Thirumalai Venkatesan, Ariando Ariando
Here, the emergence, tuning and interpretation of hump-shape Hall Effect from a CaMnO3/CaIrO3/CaMnO3 trilayer structure are studied in detail.
Mesoscale and Nanoscale Physics
We present the detailed mathematical construction of our method.
However, when the translation task involves Chinese, semantic granularity remains at the word and character level, so there is still need more fine-grained translation model of Chinese.
The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization (BN).
Rapid progress has been made in the field of reading comprehension and question answering, where several systems have achieved human parity in some simplified settings.
Ranked #8 on Question Answering on DROP Test
This paper considers the reading comprehension task in which multiple documents are given as input.
Open-domain targeted sentiment analysis aims to detect opinion targets along with their sentiment polarities from a sentence.
Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models.
Machine reading comprehension with unanswerable questions aims to abstain from answering when no answer can be inferred.
Ranked #11 on Question Answering on SQuAD2.0 dev
An effective technique for filtering free-rider episodes is using a partition model to divide an episode into two consecutive subepisodes and comparing the observed support of such episode with its expected support under the assumption that these two subepisodes occur independently.
Enforcing open source licenses such as the GNU General Public License (GPL), analyzing a binary for possible vulnerabilities, and code maintenance are all situations where it is useful to be able to determine the source code provenance of a binary.
Cryptography and Security D.4.6
In this paper, we introduce the Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects.
Ranked #17 on Question Answering on SQuAD1.1 dev
We propose a multi-objective framework to learn both secondary targets not directly related to the intended task of speech enhancement (SE) and the primary target of the clean log-power spectra (LPS) features to be used directly for constructing the enhanced speech signals.
We present a Bayesian approach to adapting parameters of a well-trained context-dependent, deep-neural-network, hidden Markov model (CD-DNN-HMM) to improve automatic speech recognition performance.
Feature selection has attracted significant attention in data mining and machine learning in the past decades.