Open Access. Powered by Scholars. Published by Universities.®

Physical Sciences and Mathematics Commons™

Open Access. Powered by Scholars. Published by Universities.®

2022

Discipline
Institution
Keyword
Publication
Publication Type
File Type

Articles 661 - 690 of 18218

Full-Text Articles in Physical Sciences and Mathematics

Predicting Publication Of Clinical Trials Using Structured And Unstructured Data: Model Development And Validation Study, Siyang Wang, Simon Šuster, Timothy Baldwin, Karin Verspoor Dec 2022

Predicting Publication Of Clinical Trials Using Structured And Unstructured Data: Model Development And Validation Study, Siyang Wang, Simon Šuster, Timothy Baldwin, Karin Verspoor

Natural Language Processing Faculty Publications

Background: Publication of registered clinical trials is a critical step in the timely dissemination of trial findings. However, a significant proportion of completed clinical trials are never published, motivating the need to analyze the factors behind success or failure to publish. This could inform study design, help regulatory decision-making, and improve resource allocation. It could also enhance our understanding of bias in the publication of trials and publication trends based on the research direction or strength of the findings. Although the publication of clinical trials has been addressed in several descriptive studies at an aggregate level, there is a lack …

Go to article

Assisting The Human Fact-Checkers: Detecting All Previously Fact-Checked Claims In A Document, Shaden Shaar, Nikola Georgiev, Firoj Alam, Giovanni Da San Martino, Aisha Mohamed, Preslav Nakov Dec 2022

Assisting The Human Fact-Checkers: Detecting All Previously Fact-Checked Claims In A Document, Shaden Shaar, Nikola Georgiev, Firoj Alam, Giovanni Da San Martino, Aisha Mohamed, Preslav Nakov

Natural Language Processing Faculty Publications

Given the recent proliferation of false claims online, there has been a lot of manual fact-checking effort. As this is very time-consuming, human fact-checkers can benefit from tools that can support them and make them more efficient. Here, we focus on building a system that could provide such support. Given an input document, it aims to detect all sentences that contain a claim that can be verified by some previously fact-checked claims (from a given database). The output is a re-ranked list of the document sentences, so that those that can be verified are ranked as high as possible, together …

Go to article

Overview Of The Wanlp 2022 Shared Task On Propaganda Detection In Arabic, Firoj Alam, Hamdy Mubarak, Wajdi Zaghouani, Giovanni Da San Martino, Preslav Nakov Dec 2022

Overview Of The Wanlp 2022 Shared Task On Propaganda Detection In Arabic, Firoj Alam, Hamdy Mubarak, Wajdi Zaghouani, Giovanni Da San Martino, Preslav Nakov

Natural Language Processing Faculty Publications

Propaganda is the expression of an opinion or an action by an individual or a group deliberately designed to influence the opinions or the actions of other individuals or groups with reference to predetermined ends, which is achieved by means of well-defined rhetorical and psychological devices. Propaganda techniques are commonly used in social media to manipulate or to mislead users. Thus, there has been a lot of recent research on automatic detection of propaganda techniques in text as well as in memes. However, so far the focus has been primarily on English. With the aim to bridge this language gap, …

Go to article

Vegetation Type Is An Important Predictor Of The Arctic Summer Land Surface Energy Budget, Jacqueline Oehri, Gabriela Schaepman-Strub, Jin Soo Kim, Raleigh Grysko, Heather Kropp, Inge Grünberg, Vitalii Zemlianskii, Oliver Sonnentag, Eugénie S. Euskirchen, Merin Reji Chacko, Giovanni Muscari, Peter D. Blanken, Joshua F. Dean, Alcide Di Sarra, Richard J. Harding, Ireneusz Sobota, Lars Kutzbach, Elena Plekhanova, Aku Riihelä, Julia Boike, Nathaniel B. Miller, Jason Beringer, Efrén López-Blanco, Paul C. Stoy, Ryan C. Sullivan, Marek Kejna, Frans Jan W. Parmentier, John A. Gamon, Mikhail Mastepanov, Christian Wille, Marcin Jackowicz-Korczynski, Dirk N. Karger, William L. Quinton, Jaakko Putkonen, Dirk Van As, Torben R. Christensen, Maria Z. Hakuba, Robert S. Stone, Stefan Metzger, Baptiste Vandecrux Dec 2022

Vegetation Type Is An Important Predictor Of The Arctic Summer Land Surface Energy Budget, Jacqueline Oehri, Gabriela Schaepman-Strub, Jin Soo Kim, Raleigh Grysko, Heather Kropp, Inge Grünberg, Vitalii Zemlianskii, Oliver Sonnentag, Eugénie S. Euskirchen, Merin Reji Chacko, Giovanni Muscari, Peter D. Blanken, Joshua F. Dean, Alcide Di Sarra, Richard J. Harding, Ireneusz Sobota, Lars Kutzbach, Elena Plekhanova, Aku Riihelä, Julia Boike, Nathaniel B. Miller, Jason Beringer, Efrén López-Blanco, Paul C. Stoy, Ryan C. Sullivan, Marek Kejna, Frans Jan W. Parmentier, John A. Gamon, Mikhail Mastepanov, Christian Wille, Marcin Jackowicz-Korczynski, Dirk N. Karger, William L. Quinton, Jaakko Putkonen, Dirk Van As, Torben R. Christensen, Maria Z. Hakuba, Robert S. Stone, Stefan Metzger, Baptiste Vandecrux

School of Natural Resources: Faculty Publications

Despite the importance of high-latitude surface energy budgets (SEBs) for land-climate interactions in the rapidly changing Arctic, uncertainties in their prediction persist. Here, we harmonize SEB observations across a network of vegetated and glaciated sites at circumpolar scale (1994–2021). Our variance-partitioning analysis identifies vegetation type as an important predictor for SEB-components during Arctic summer (June-August), compared to other SEB-drivers including climate, latitude and permafrost characteristics. Differences among vegetation types can be of similar magnitude as between vegetation and glacier surfaces and are especially high for summer sensible and latent heat fluxes. The timing of SEB-flux summer-regimes (when daily mean values …

Go to article

(R1981) Evaluating The Mhd Non-Newtonian Fluid Motion Past A Stretching Sheet Under The Influence Of Non-Uniform Thickness With Dufour And Soret Effects Implementing Chebyshev Spectral Method, M. M. Khader, Ram Prakash Sharma Dec 2022

(R1981) Evaluating The Mhd Non-Newtonian Fluid Motion Past A Stretching Sheet Under The Influence Of Non-Uniform Thickness With Dufour And Soret Effects Implementing Chebyshev Spectral Method, M. M. Khader, Ram Prakash Sharma

Applications and Applied Mathematics: An International Journal (AAM)

A study is made on the development of hydromagnetic non-Newtonian Casson and Williamson boundary layer flow in an electrically conducting fluid in the presence of heat flux, mass flux, and the uniform magnetic field. The governing non-linear system of PDEs is transformed into a set of non-linear coupled ODEs and then treated numerically by using the Chebyshev spectral method. The velocity, temperature, and concentration fields of the steady boundary layer flow, which are generated by the stretched sheet with non-uniform thickness are discussed. The simultaneous effects of the external magnetic field, Soret and Dufour phenomena with reference have been explored. …

Go to article

(R1886) Effect Of Aggregation Function In Moma-Plus Method For Obtaining Pareto Optimal Solutions, Alexandre Som, Abdoulaye Compaoré, Kounhinir Somé, Blaise Somé Dec 2022

(R1886) Effect Of Aggregation Function In Moma-Plus Method For Obtaining Pareto Optimal Solutions, Alexandre Som, Abdoulaye Compaoré, Kounhinir Somé, Blaise Somé

Applications and Applied Mathematics: An International Journal (AAM)

In this work, we have proposed some variants of MOMA-Plus method that we have numerically tested for the resolution of nonlinear multiobjective optimization problems. This MOMA-Plus method and variants differ from each other by the choice of aggregation functions in order to reduce the number of objective functions. The theoretical results allowing us to use these aggregation functions to transform multiobjective optimization problems into single objective optimization problems are proved by two theorems. This study has highlighted the advantages of each aggregation function according to the type of Pareto front of the optimization problem. Six benchmarks test problems have been …

Go to article

Earlier Snowmelt May Lead To Late Season Declines In Plant Productivity And Carbon Sequestration In Arctic Tundra Ecosystems, Donatella Zona, Peter M. Lafleur, Koen Hufkens, Barbara Bailey, Beniamino Gioli, George Burba, Jordan P. Goodrich, Anna K. Liljedahl, Eugénie S. Euskirchen, Jennifer D. Watts, Mary Farina, John S. Kimball, Martin Heimann, Mathias Göckede, Martijn Pallandt, Torben R. Christensen, Mikhail Mastepanov, Efrén López-Blanco, Marcin Jackowicz-Korczynski, Albertus J. Dolman, Luca Belelli Marchesini, Roisin Commane, Steven C. Wofsy, Charles E. Miller, David A. Lipson, Josh Hashemi, Kyle A. Arndt, Lars Kutzbach, David Holl, Julia Boike, Christian Wille, Torsten Sachs, Aram Kalhori, Xia Song Dec 2022

Earlier Snowmelt May Lead To Late Season Declines In Plant Productivity And Carbon Sequestration In Arctic Tundra Ecosystems, Donatella Zona, Peter M. Lafleur, Koen Hufkens, Barbara Bailey, Beniamino Gioli, George Burba, Jordan P. Goodrich, Anna K. Liljedahl, Eugénie S. Euskirchen, Jennifer D. Watts, Mary Farina, John S. Kimball, Martin Heimann, Mathias Göckede, Martijn Pallandt, Torben R. Christensen, Mikhail Mastepanov, Efrén López-Blanco, Marcin Jackowicz-Korczynski, Albertus J. Dolman, Luca Belelli Marchesini, Roisin Commane, Steven C. Wofsy, Charles E. Miller, David A. Lipson, Josh Hashemi, Kyle A. Arndt, Lars Kutzbach, David Holl, Julia Boike, Christian Wille, Torsten Sachs, Aram Kalhori, Xia Song

Daugherty Water for Food Global Institute: Faculty Publications

Arctic warming is affecting snow cover and soil hydrology, with consequences for carbon sequestration in tundra ecosystems. The scarcity of observations in the Arctic has limited our understanding of the impact of covarying environmental drivers on the carbon balance of tundra ecosystems. In this study, we address some of these uncertainties through a novel record of 119 site-years of summer data from eddy covariance towers representing dominant tundra vegetation types located on continuous permafrost in the Arctic. Here we found that earlier snowmelt was associated with more tundra net CO2 sequestration and higher gross primary productivity (GPP) only in June …

Go to article

Which Interval-Valued Alternatives Are Possibly Optimal If We Use Hurwicz Criterion, Marina Tuyako Mizukoshi, Weldon Lodwick, Martine Ceberio, Vladik Kreinovich Dec 2022

Which Interval-Valued Alternatives Are Possibly Optimal If We Use Hurwicz Criterion, Marina Tuyako Mizukoshi, Weldon Lodwick, Martine Ceberio, Vladik Kreinovich

Departmental Technical Reports (CS)

In many practical situations, for each alternative i, we do not know the corresponding gain xi, we only know the interval [li,ui] of possible gains. In such situations, a reasonable way to select an alternative is to choose some value α from the interval [0,1] and select the alternative i for which the Hurwicz combination α*ui + (1 − α)*li is the largest possible. In situations when we do not know the user's α, a reasonable idea is to select all alternatives that are optimal for some α. In this paper, we describe a feasible algorithm for such a selection.

Go to article

Supervised Acoustic Embeddings And Their Transferability Across Languages, Sreepratha Ram, Hanan Aldarmaki Dec 2022

Supervised Acoustic Embeddings And Their Transferability Across Languages, Sreepratha Ram, Hanan Aldarmaki

Natural Language Processing Faculty Publications

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pretraining has been proposed as a way to improve both supervised and unsupervised speech recognition, including frame-level feature representations and Acoustic Word Embeddings (AWE) for variable-length segments. However, self-supervised models alone cannot learn perfect separation of the linguistic content as they are trained to optimize indirect objectives. In this work, we experiment with different pre-trained self-supervised features as input to AWE models and show that they work best …

Go to article

(R1885) Analytical And Numerical Solutions Of A Fractional-Order Mathematical Model Of Tumor Growth For Variable Killing Rate, N. Singha, C. Nahak Dec 2022

(R1885) Analytical And Numerical Solutions Of A Fractional-Order Mathematical Model Of Tumor Growth For Variable Killing Rate, N. Singha, C. Nahak

Applications and Applied Mathematics: An International Journal (AAM)

This work intends to analyze the dynamics of the most aggressive form of brain tumor, glioblastomas, by following a fractional calculus approach. In describing memory preserving models, the non-local fractional derivatives not only deliver enhanced results but also acknowledge new avenues to be further explored. We suggest a mathematical model of fractional-order Burgess equation for new research perspectives of gliomas, which shall be interesting for biomedical and mathematical researchers. We replace the classical derivative with a non-integer derivative and attempt to retrieve the classical solution as a particular case. The prime motive is to acquire both analytical and numerical solutions …

Go to article

(R1899) Asymptotic Normality Of The Conditional Hazard Function In The Local Linear Estimation Under Functional Mixing Data, Amina Goutal, Boubaker Mechab, Omar Fetitah, Torkia Merouan Dec 2022

(R1899) Asymptotic Normality Of The Conditional Hazard Function In The Local Linear Estimation Under Functional Mixing Data, Amina Goutal, Boubaker Mechab, Omar Fetitah, Torkia Merouan

Applications and Applied Mathematics: An International Journal (AAM)

In this study, we are interested in using the local linear technique to estimate the conditional hazard function for functional dependent data where the scalar response is conditioned by a functional random variable. The asymptotic normality of this constructed estimator is demonstrated under some extreme conditions. Our estimator’s performance is demonstrated through simulations.

Go to article

(R1894) Invariant Solution For Two-Dimensional And Axisymmetric Jet Of Power-Law Fluids, Bhavixa Bhagat, M. G. Timol Dec 2022

(R1894) Invariant Solution For Two-Dimensional And Axisymmetric Jet Of Power-Law Fluids, Bhavixa Bhagat, M. G. Timol

Applications and Applied Mathematics: An International Journal (AAM)

An invariant solution is derived using the Lie symmetry technique for steady laminar two-dimensional and axisymmetric boundary layer jet flow of incompressible power-law fluids with appropriate boundary conditions. Using symmetry, the nonlinear partial differential equation of the jet flow problem is transformed into a nonlinear ordinary differential equation. The resultant nonlinear ordinary differential equation with boundary conditions is converted to an initial value problem using the Lie symmetry technique. A numerical solution for the resulting initial value problem is derived using Fehlberg’s fourth-fifth order Runge-Kutta method through Maple software. The graphical representation of the characteristics of the velocity field for …

Go to article

(R1500) Type-I Generalized Spherical Interval Valued Fuzzy Soft Sets In Medical Diagnosis For Decision Making, M. Palanikumar, K. Arulmozhi Dec 2022

(R1500) Type-I Generalized Spherical Interval Valued Fuzzy Soft Sets In Medical Diagnosis For Decision Making, M. Palanikumar, K. Arulmozhi

Applications and Applied Mathematics: An International Journal (AAM)

In the present communication, we introduce the concept of Type-I generalized spherical interval valued fuzzy soft set and define some operations. It is a generalization of the interval valued fuzzy soft set and the spherical fuzzy soft set. The spherical interval valued fuzzy soft set theory satisfies the condition that the sum of its degrees of positive, neutral, and negative membership does not exceed unity and that these parameters are assigned independently. We also propose an algorithm to solve the decision making problem based on a Type-I generalized soft set model. We introduce a similarity measure based on the Type-I …

Go to article

(R1964) Solving Multi-Objective Linear Fractional Programming Problems Via Zero-Sum Game, Gizem Temelcan, Inci Albayrak, Mustafa Sivri Dec 2022

(R1964) Solving Multi-Objective Linear Fractional Programming Problems Via Zero-Sum Game, Gizem Temelcan, Inci Albayrak, Mustafa Sivri

Applications and Applied Mathematics: An International Journal (AAM)

This study presents a hybrid algorithm consisting of game theory and the first order Taylor series approach to find compromise solutions to multi-objective linear fractional programming (MOLFP) problems. The proposed algorithm consists of three phases including different techniques: in the first phase, the optimal solution to each LFP problem is found using the simplex method; in the second phase, a zero-sum game is solved to determine the weights of the objective functions via the ratio matrix obtained from a payoff matrix; in the last phase, fractional objective functions of the MOLFP problem are linearized using the 1st order Taylor series. …

Go to article

(R1971) Analysis Of Feedback Queueing Model With Differentiated Vacations Under Classical Retrial Policy, Poonam Gupta, Naveen Kumar, Rajni Gupta Dec 2022

(R1971) Analysis Of Feedback Queueing Model With Differentiated Vacations Under Classical Retrial Policy, Poonam Gupta, Naveen Kumar, Rajni Gupta

Applications and Applied Mathematics: An International Journal (AAM)

This paper analyzes an M/M/1 retrial queue under differentiated vacations and Bernoulli feedback policy. On receiving the service, if the customer is not satisfied, then he may join the retrial group again with some probability and demand for service or may leave the system with the complementary probability. Using the probability generating functions technique, the steady-state solutions of the system are obtained. Furthermore, we have obtained some of the important performance measures such as expected orbit length, expected length of the system, sojourn times and probability of server being in different states. Using MATLAB software, we have represented the graphical …

Go to article

(R1984) Analysis Of M^[X1], M^[X2]/G1, G_2^(A,B)/1 Queue With Priority Services, Server Breakdown, Repair, Modified Bernoulli Vacation, Immediate Feedback, G. Ayyappan, S. Nithya, B. Somasundaram Dec 2022

(R1984) Analysis Of M^[X1], M^[X2]/G1, G_2^(A,B)/1 Queue With Priority Services, Server Breakdown, Repair, Modified Bernoulli Vacation, Immediate Feedback, G. Ayyappan, S. Nithya, B. Somasundaram

Applications and Applied Mathematics: An International Journal (AAM)

In this investigation, the steady state analysis of two individualistic batch arrival queues with immediate feedback, modified Bernoulli vacation and server breakdown are introduced. Two different categories of customers like priority and ordinary are to be considered. This model propose nonpreemptive priority discipline. Ordinary and priority customers arrive as per Poisson processes. The server consistently afford single service for priority customers and the general bulk service for the ordinary customers and the service follows general distribution. The ordinary customers to be served only if the batch size should be greater than or equal to "a", else the server should not …

Go to article

(R2024) A New Weighted Poisson Distribution For Over- And Under-Dispersion Situations, Michel Koukouatikissa Diafouka, Gelin Chedly Louzayadio, Rodnellin Onéime Malouata Dec 2022

(R2024) A New Weighted Poisson Distribution For Over- And Under-Dispersion Situations, Michel Koukouatikissa Diafouka, Gelin Chedly Louzayadio, Rodnellin Onéime Malouata

Applications and Applied Mathematics: An International Journal (AAM)

In this paper, we propose a four-parameter weighted Poisson distribution that includes and generalizes the weighted Poisson distribution proposed by Castillo and Pérez-Casany and the Conway- Maxwell-Poisson distribution, as well as other well-known distributions. It is a distribution that is a member of the exponential family and is an exponential combination formulation between the weighted Poisson distribution proposed by Castillo and Pérez-Casany and the Conway-Maxwell- Poisson distribution. This new distribution with an additional parameter of dispersion is more flexible, and the Fisher dispersion index can be greater than, equal to, or less than one. This last property allows it to …

Go to article

(R1978) Heated Laminar Vertical Jet Of Psudoplastic Fluids-Against Gravity, Manisha Patel, M. G. Timol Dec 2022

(R1978) Heated Laminar Vertical Jet Of Psudoplastic Fluids-Against Gravity, Manisha Patel, M. G. Timol

Applications and Applied Mathematics: An International Journal (AAM)

A heated laminar jet of Pseudo-plastic fluid flowing vertically upwards from a long narrow slit into a region of the same fluid which is at a rest and at a uniform temperature is considered. The governing non-linear Partial differential equations (PDEs) for the defined flow problem are transformed into non-linear ordinary differential equations using the effective similarity technique-one parameter deductive group theory method. The obtained non-linear coupled Ordinary differential equations are solved and the results are presented by graphs. The effect of the Prandtl number and Grashof number on the velocity and temperature of the jet flow is discussed. Also, …

Go to article

(R1985) Study The Effect Of Modified Newtonian Force On The Restricted 3-Body Configuration In Non-Linear Sense, Bhawna Singh, Kumari Shalini, Sada Nand Prasad, Abdullah A. Ansari Dec 2022

(R1985) Study The Effect Of Modified Newtonian Force On The Restricted 3-Body Configuration In Non-Linear Sense, Bhawna Singh, Kumari Shalini, Sada Nand Prasad, Abdullah A. Ansari

Applications and Applied Mathematics: An International Journal (AAM)

This paper aims to investigate the non-linear stability of the triangular libration point in the restricted three-body problem (R3BP). The model, we use for our problem consists of a primary body as a heterogeneous spheroid with N-layers having different densities of each layer and a secondary body as a point mass that is producing the modified Newtonian Potential. We determine the equation of motion of the smallest body which is under the influence of the above-mentioned perturbations and also influenced by Coriolis as well as Centrifugal forces and then evaluated the Lagrangian for the evaluated system of equations. Afterwards, we …

Go to article

(R1980) Effect Of Climate Change On Brain Tumor, Pardeep Kumar, Sarita Jha, Rajiv Aggarwal, Govind Kumar Jha Dec 2022

(R1980) Effect Of Climate Change On Brain Tumor, Pardeep Kumar, Sarita Jha, Rajiv Aggarwal, Govind Kumar Jha

Applications and Applied Mathematics: An International Journal (AAM)

In this paper, we introduce a new dynamical model addressing the variation in climate condition due the presence of microorganisms. We also introduce a new dynamical model of cancer growth which includes three interactive cell populations with drug free environment, namely tumor cells, healthy host cells, and immune effector cells. In this, we considered the super growth of tumor cells. For the choice of certain parameters, both of the systems exhibit chaotic behavior. The aim of this work is to design the controller to control the chaos and to provide sufficient conditions which achieve synchronization of two non-identical systems, which …

Go to article

Camelira: An Arabic Multi-Dialect Morphological Disambiguator, Ossama Obeid, Go Inoue, Nizar Habash Dec 2022

Camelira: An Arabic Multi-Dialect Morphological Disambiguator, Ossama Obeid, Go Inoue, Nizar Habash

Computer Vision Faculty Publications

We present Camelira, a web-based Arabic multi-dialect morphological disambiguation tool that covers four major variants of Arabic: Modern Standard Arabic, Egyptian, Gulf, and Levantine. Camelira offers a user-friendly web interface that allows researchers and language learners to explore various linguistic information, such as part-of-speech, morphological features, and lemmas. Our system also provides an option to automatically choose an appropriate dialect-specific disambiguator based on the prediction of a dialect identification component. Camelira is publicly accessible at http://camelira.camel-lab.com.

Go to article

Pasta: Table-Operations Aware Fact Verification Via Sentence-Table Cloze Pre-Training, Zihui Gu, Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, Xiaoyong Du Dec 2022

Pasta: Table-Operations Aware Fact Verification Via Sentence-Table Cloze Pre-Training, Zihui Gu, Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, Xiaoyong Du

Natural Language Processing Faculty Publications

Fact verification has attracted a lot of research attention recently, e.g., in journalism, marketing, and policymaking, as misinformation and disinformation online can sway one's opinion and affect one's actions. While fact-checking is a hard task in general, in many cases, false statements can be easily debunked based on analytics over tables with reliable information. Hence, table-based fact verification has recently emerged as an important and growing research area. Yet, progress has been limited due to the lack of datasets that can be used to pre-train language models (LMs) to be aware of common table operations, such as aggregating a column …

Go to article

Greener: Graph Neural Networks For News Media Profiling, Panayot Panayotov, Utsav Shukla, Husrev T. Sencar, Mohamed Nabeel, Preslav Nakov Dec 2022

Greener: Graph Neural Networks For News Media Profiling, Panayot Panayotov, Utsav Shukla, Husrev T. Sencar, Mohamed Nabeel, Preslav Nakov

Natural Language Processing Faculty Publications

We study the problem of profiling news media on the Web with respect to their factuality of reporting and bias. This is an important but under-studied problem related to disinformation and “fake news” detection, but it addresses the issue at a coarser granularity compared to looking at an individual article or an individual claim. This is useful as it allows to profile entire media outlets in advance. Unlike previous work, which has focused primarily on text (e.g., on the articles published by the target website, or on the textual description in their social media profiles or in Wikipedia), here we …

Go to article

Asdot: Any-Shot Data-To-Text Generation With Pretrained Language Models, Jiannan Xiang, Zhengzhong Liu, Yucheng Zhou, Eric P. Xing, Zhiting Hu Dec 2022

Asdot: Any-Shot Data-To-Text Generation With Pretrained Language Models, Jiannan Xiang, Zhengzhong Liu, Yucheng Zhou, Eric P. Xing, Zhiting Hu

Machine Learning Faculty Publications

Data-to-text generation is challenging due to the great variety of the input data in terms of domains (e.g., finance vs sports) or schemata (e.g., diverse predicates). Recent end-to-end neural methods thus require substantial training examples to learn to disambiguate and describe the data. Yet, real-world data-to-text problems often suffer from various data-scarce issues: one may have access to only a handful of or no training examples, and/or have to rely on examples in a different domain or schema. To fill this gap, we propose Any-Shot Data-to-Text (ASDOT), a new approach flexibly applicable to diverse settings by making efficient use of …

Go to article

(R1953) M-Regression Estimation With The K Nearest Neighbors Smoothing Under Quasi-Associated Data In Functional Statistics, Bellatrach Nadjet, Bouabsa Wahiba, Attouch Mohammed Kadi, Fetitah Omar Dec 2022

(R1953) M-Regression Estimation With The K Nearest Neighbors Smoothing Under Quasi-Associated Data In Functional Statistics, Bellatrach Nadjet, Bouabsa Wahiba, Attouch Mohammed Kadi, Fetitah Omar

Applications and Applied Mathematics: An International Journal (AAM)

The main goal of this paper is to study the non parametric M-estimation under quasi-associated sequence with the k Nearest Neighbor’s method shortly (kNN). We construct an estimator of this nonparametric function and we study its asymptotic properties. Furthermore, a comparison study based on simulated data is also provided to illustrate the highly sensitive of the kNN approach to the presence of even a small proportion of outliers in the data.

Go to article

Impact Of Digital Twins And Metaverse On Cities: History, Current Situation, And Application Perspectives, Zhihan Lv, Wen Long Shang, Mohsen Guizani Dec 2022

Impact Of Digital Twins And Metaverse On Cities: History, Current Situation, And Application Perspectives, Zhihan Lv, Wen Long Shang, Mohsen Guizani

Machine Learning Faculty Publications

To promote the expansion and adoption of Digital Twins (DTs) in Smart Cities (SCs), a detailed review of the impact of DTs and digitalization on cities is made to assess the progression of cities and standardization of their management mode. Combined with the technical elements of DTs, the coupling effect of DTs technology and urban construction and the internal logic of DTs technology embedded in urban construction are discussed. Relevant literature covering the full range of DTs technologies and their applications is collected, evaluated, and collated, relevant studies are concatenated, and relevant accepted conclusions are summarized by modules. First, the …

Go to article

Resel: N-Ary Relation Extraction From Scientific Text And Tables By Learning To Retrieve And Select, Yuchen Zhuang, Yinghao Li, Jerry Junyang Cheung, Yue Yu, Yingjun Mou, Xiang Chen, Le Song, Chao Zhang Dec 2022

Resel: N-Ary Relation Extraction From Scientific Text And Tables By Learning To Retrieve And Select, Yuchen Zhuang, Yinghao Li, Jerry Junyang Cheung, Yue Yu, Yingjun Mou, Xiang Chen, Le Song, Chao Zhang

Machine Learning Faculty Publications

We study the problem of extracting N-ary relation tuples from scientific articles. This task is challenging because the target knowledge tuples can reside in multiple parts and modalities of the document. Our proposed method RESEL decomposes this task into a two-stage procedure that first retrieves the most relevant paragraph/table and then selects the target entity from the retrieved component. For the high-level retrieval stage, RESEL designs a simple and effective feature set, which captures multilevel lexical and semantic similarities between the query and components. For the low-level selection stage, RESEL designs a cross-modal entity correlation graph along with a multi-view …

Go to article

Efficient (Soft) Q-Learning For Text Generation With Limited Good Data, Han Guo, Bowen Tan, Zhengzhong Liu, Eric P. Xing, Zhiting Hu Dec 2022

Efficient (Soft) Q-Learning For Text Generation With Limited Good Data, Han Guo, Bowen Tan, Zhengzhong Liu, Eric P. Xing, Zhiting Hu

Machine Learning Faculty Publications

Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial attacks or generating prompts to control language models. Reinforcement learning (RL) on the other hand offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. Yet previous RL algorithms for text generation, such as policy gradient (on-policy RL) and Q-learning (off-policy RL), are often notoriously inefficient or unstable to train due to the large sequence space and the sparse reward received only …

Go to article

Amp: Automatically Finding Model Parallel Strategies With Heterogeneity Awareness, Dacheng Li, Hongyi Wang, Eric Xing, Hao Zhang Dec 2022

Amp: Automatically Finding Model Parallel Strategies With Heterogeneity Awareness, Dacheng Li, Hongyi Wang, Eric Xing, Hao Zhang

Machine Learning Faculty Publications

Scaling up model sizes can lead to fundamentally new capabilities in many machine learning (ML) tasks. However, training big models requires strong distributed system expertise to carefully design model-parallel execution strategies that suit the model architectures and cluster setups. In this paper, we develop AMP, a framework that automatically derives such strategies. AMP identifies a valid space of model parallelism strategies and efficiently searches the space for high-performed strategies, by leveraging a cost model designed to capture the heterogeneity of the model and cluster specifications. Unlike existing methods, AMP is specifically tailored to support complex models composed of uneven layers …

Go to article

Unpaired Image-To-Image Translation With Density Changing Regularization, Shaoan Xie, Qirong Ho, Kun Zhang Dec 2022

Unpaired Image-To-Image Translation With Density Changing Regularization, Shaoan Xie, Qirong Ho, Kun Zhang

Machine Learning Faculty Publications

Unpaired image-to-image translation aims to translate an input image to another domain such that the output image looks like an image from another domain while important semantic information are preserved. Inferring the optimal mapping with unpaired data is impossible without making any assumptions. In this paper, we make a density changing assumption where image patches of high probability density should be mapped to patches of high probability density in another domain. Then we propose an efficient way to enforce this assumption: we train the flows as density estimators and penalize the variance of density changes. Despite its simplicity, our method …

Go to article

First Prev Next Last