Heesch Numbers of Unmarked Polyforms

A shape’s Heesch number is the number of layers of copies of the shape that can be placed around it without gaps or overlaps . Experimentation and searching have turned up examples of shapes with finite Heeschnumbers up to six, but nothing higher .…

Federated Artificial Intelligence for Unified Credit Assessment

A federated artificial intelligence platform is proposed with acomprehensive set of system design for efficient and effective credit scoring . The study considerably contributes to the cumulative development of financialintelligence and social computing . It also provides a number of implications for academic bodies, practitioners, and developers of financial technologies.…

Low Latency Real Time Non Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data Driven Linear Prediction

This paper presents a low-latency real-time (LLRT) non-parallel voiceconversion (VC) framework based on cyclic variational autoencoder (CycleVAE)and multiband WaveRNN with data-driven linear prediction (MWDLP) MWDLP is an efficient and a high-qualityneural vocoder that can handle multispeaker data and generate speech waveformfor LLRT applications with CPU .…

Efficient and Robust LiDAR Based End to End Navigation

Deep learning has been used to demonstrate end-to-end neural network learningfor autonomous vehicle control from raw sensory input . We present an efficient and robust LiDAR-based end- to-end navigation framework . We evaluate our system on a full-scale vehicle anddemonstrate lane-stable as well as navigation capabilities .…

CREAD Combined Resolution of Ellipses and Anaphora in Dialogues

Anaphora and ellipses are two common phenomena in dialogues . Without resolving referring expressions and information omission, dialogue systems may fail to generate consistent and coherent responses . In this work, we propose a novel joint learning framework of modeling coreference resolutionand query rewriting for complex, multi-turn dialogue understanding .…

A practical introduction to the Rational Speech Act modeling framework

Recent advances in computational cognitive science have paved the way for significant progress in formal,implementable models of pragmatics . These models formalize and implement one, deriving both qualitative and quantitative predictions of human behavior . The current paper provides a practical introduction to and criticalassessment of the Bayesian Rational Speech Act modeling framework, unpacking theoretical foundations, exploring technological innovations, and drawingconnections to issues beyond current applications .…

Indirect predicates for geometric constructions

Geometric predicates are a basic ingredient to implement a vast range of algorithms in computational geometry . Modern implementations employ floatingpoint filtering techniques to combine efficiency and robustness . If the input to these predicates is an intermediate construction, its floating point representation may be affected by anapproximation error, and correctness is no longer guaranteed .…

Fed EINI An Efficient and Interpretable Inference Framework for Decision Tree Ensembles in Federated Learning

The increasing concerns about data privacy and security drives the emergence of a new field of studying privacy-preserving machine learning from isolated data sources . We propose to protect the decision path by the efficient additivelyhomomorphic encryption method, which allows the disclosure of feature names and thus makes the federated decision trees interpretable .…

Intra Document Cascading Learning to Select Passages for Neural Document Ranking

An emerging recipe for achieving state-of-the-art effectiveness in neuraldocument re-ranking involves utilizing large pre-trained language models -e.g., BERT – to evaluate all individual passages in the document and thenaggregating the outputs by pooling or additional Transformer layers . The proposed Intra-DocumentCascaded Ranking Model (IDCM) leads to over 400% lower query latency by providing essentially the same effectiveness as BERT-based ranking models .…

Simple Transparent Adversarial Examples

There has been a rise in the use of Machine Learning as a Service (MLaaS)Vision APIs as they offer multiple services including pre-built models and algorithms . As these APIs get deployed for high-stakes applications, it’s veryimportant that they are robust to different manipulations .…

MLBiNet A Cross Sentence Collective Event Detection Network

We consider the problem of collectively detecting multiple events,particularly in cross-sentence settings . We reformulate it as a Seq2Seq task and propose a Multi-Layer Bidirectional Network (MLBiNet) to capture the document-level association of events and semantic information simultaneously . An abidirectional decoder is devised to model event inter-dependency withina sentence when decoding the event tag vector sequence.…

POCFormer A Lightweight Transformer Architecture for Detection of COVID 19 Using Point of Care Ultrasound

COVID-19 can be traced back to the inefficiency and shortage of testing kits that offer accurate results in atimely manner . We present an image-based solution that aimsat automating the testing process which allows for rapid mass testing to beconducted with or without a trained medical professional that can be applied torural environments and third world countries .…

Unified Dual view Cognitive Model for Interpretable Claim Verification

Recent studies constructing direct interactions between the claim and each user response (a comment or a relevant article) to capture evidence haveshown remarkable success in interpretable claim verification . Owing todifferent single responses convey different cognition of individual users, the captured evidence belongs to the perspective of individual cognition .…

Measuring Coding Challenge Competence With APPS

Modern machine learning models still cannot code solutions to basic problems . The APPS benchmark measures the ability of models to take an arbitrary language specification and generate Python code fulfilling this specification . Similar to how companies assess candidate software developers, we then evaluate models by checking their generated code on test cases .…

A comprehensive comparative evaluation and analysis of Distributional Semantic Models

Distributional Semantic Model (DSM) evaluation lack a thorough comparison with respect to tested models, semantic tasks,and benchmark datasets . We borrow from cognitive neuroscience the methodology ofRepresentational Similarity Analysis (RSA) to inspect the semantic spaces generated by distributional models . RSA reveals important differences related to the frequency and part-of-speech of lexical items .…

KLUE Korean Language Understanding Evaluation

We introduce Korean Language Understanding Evaluation (KLUE) benchmark . KLUE is a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification, Semantic Textual Similarity, Natural LanguageInference, Named Entity Recognition, Relation Extraction, Dependency Parsing,Machine Reading Comprehension, and Dialogue State Tracking .…

AGSFCOS Based on attention mechanism and Scale Equalizing pyramid network of object detection

Recently, the anchor-free object detection model has shown great potential for accuracy and speed to exceed anchor-based object detection . The attention mechanism module module can capture contextual information well,improve detection accuracy, and use sepc network to help balance abstract and detailed information, and reduce the problem of semantic gap in the featurepyramid network .…

AnaXNet Anatomy Aware Multi label Finding Classification in Chest X ray

Radiologists usually observe anatomical regions of chest X-ray images as well as the overall image before making a decision . Most existing deeplearning models only look at the entire X-rays for classification, failing to utilize important anatomical information . In this paper, we propose a novel multi-label chest x-ray classification model that accurately classifies the image finding and also localizes the findings to their correct anatomical regions .…

Content Augmented Feature Pyramid Network with Light Linear Transformers

Transformers can adaptivelyaggregate similar features from a global view using self-attention mechanism . The CA-FPN significantly outperforms competitive baselines without bells and whistles . Code will be made publicly available and code will be publicly available . For object detection, Feature Pyramid Network (FPN) proposes featureinteraction across layers and proves its extremely importance.…

Probabilistic and Variational Recommendation Denoising

Learning from implicit feedback is one of the most common cases in recommender systems . We propose probabilistic andvariational recommendation denoising for implicit feedback . DPI and DVAE significantly improve recommendation performance compared with normal training . Codes will be open-sourced.…

Towards Personalized Fairness based on Causal Notion

Recommender systems are gaining increasing and critical impacts on human and society since a growing number of users use them for information seeking and decision making . Just like users have personalized preferences on items, users’ demands for fairness are also personalized in many scenarios .…

Minimum Delay Adaptation in Non Stationary Reinforcement Learning via Online High Confidence Change Point Detection

We introduce an algorithm that efficiently learnspolicies in non-stationary environments . It analyzes a possibly infinite stream of data and computes, in real-time, high-confidence change-point detectionstatistics . We show that (i) this algorithm minimizes the delay untilunforeseen changes to a context are detected, thereby allowing for rapidresponses .…

Navigation Turing Test NTT Learning to Evaluate Human Like Navigation

A key challenge on the path to developing agents that learn complex human-like behavior is the need to quickly and accurately quantify human-likeness . While human assessments of such behavior can be highlyaccurate, speed and scalability are limited . We address these limitationsthrough a novel automated Navigation Turing Test (ANTT) that learns to predicthuman judgments of human-likes .…

Adaptive Knowledge Enhanced Bayesian Meta Learning for Few shot Event Detection

Event detection (ED) aims at detecting event trigger words in sentences and classifying them into specific event types . In real-world applications, ED typically does not have sufficient labelled data, thus can be formulated as afew-shot learning problem . We propose a novel knowledge-based few-shot event detection method which uses a definition-based encoder to introduce external event knowledge asthe knowledge prior of event types.…

Nonlinear Hawkes Process with Gaussian Process Self Effects

Traditionally Hawkes processes are used to model time–continuous pointprocesses with history dependence . Here we propose an extended model where theself–effects are of both excitatory and inhibitory type and follow a GaussianProcess . Efficient approximate Bayesian inference is achieved via dataaugmentation, and we describe a mean–field variational inference approach tolearn the model parameters .…

Objective aware Traffic Simulation via Inverse Reinforcement Learning

Conventional traffic simulators usually employ a calibrated physical car-following model to describe vehicles’ behaviour . A fixed physical model tends to be lesseffective in a complicated environment given the non-stationary nature of traffic dynamics . In this paper, we formulate traffic simulation as an inversereinforcement learning problem, and propose a parameter sharing adversarialinverse reinforcement learning model for dynamics-robust simulation learning .…

The impact of virtual mirroring on customer satisfaction

A novel method called “virtual mirroring” topromote employee self-reflection and impact customer satisfaction . The method is based on measuring communication patterns, through social network andsemantic analysis, and mirroring them back to the individual . We find an increase in customers satisfaction in the experimental group and a decrease in the control group .…

High Fidelity and Low Latency Universal Neural Vocoder based on Multiband WaveRNN with Data Driven Linear Prediction for Discrete Waveform Modeling

This paper presents a novel high-fidelity and low-latency universal neuralvocoder framework . MWDLP employs a coarse-fine bit WaveRNNarchitecture for 10-bit mu-law waveform modeling . A sparse gated recurrent unit with a relatively large size of hidden units is utilized, while the multibandmodeling is deployed to achieve real-time low latency usage .…

Dependency Parsing with Bottom up Hierarchical Pointer Networks

Dependency parsing is a crucial step towards deep language understanding . Left-to-right and top-down transition-based algorithms that rely on Pointer Networks are among the most accurate approaches to performing dependency parsing . We develop a bottom-up-oriented HierarchicalPointer Network for the left-to the-right parser .…

BigCQ A large scale synthetic dataset of competency question patterns formalized into SPARQL OWL query templates

BigCQ is createdautomatically from a dataset of frequently used axiom shapes . These pairs of CQtemplates and query templates can be then materialized as actual CQs and SPARQL-OWL queries if filled with resource labels and IRIs from a givenontology . We describe the dataset in detail, provide a description of the process leading to the creation of the dataset and analyze how well the dataset covers real-world examples .…

Survey and Perspective on Social Emotions in Robotics

This study reviews research on social emotions in robotics . We believe that thesehigher-level emotions are worth pursuing in robotics for next-generationsocial-aware robots . Thereafter, research directions towards implementing social emotions into robots are discussed . The study concludes that social emotions, also known ashigher level emotions, have been studied in psychology and neuroscience.…

Head driven Phrase Structure Parsing in O n 3 Time Complexity

Head-driven Phrase Structure Grammar (HPSG) has been found to benefit from joint training and decoding under a uniform formalism . However, decoding this unified grammar has a higher time complexity ($O(n^5)$) than decoding either form individually . We propose an improved head scorer that helpsachieve a novel performance-preserved parscher in $O$($n^3$) time complexity .…