Hasil untuk "Comparative grammar"

Ngoc-Quang Le, T. Thanh-Lam Nguyen, Quoc-Trung Phu et al.

Comparative opinion mining involves comparing products from different reviews. However, transformer-based models designed for this task often lack transparency, which can adversely hinder the development of trust in users. In this paper, we propose XCom, an enhanced transformer-based model separated into two principal modules, i.e., (i) aspect-based rating prediction and (ii) semantic analysis for comparative opinion mining. XCom also incorporates a Shapley additive explanations module to provide interpretable insights into the model's deliberative decisions. Empirically, XCom achieves leading performances compared to other baselines, which demonstrates its effectiveness in providing meaningful explanations, making it a more reliable tool for comparative opinion mining. Source code is available at: https://anonymous.4open.science/r/XCom.

Manoj Reddy Bethi, Sai Rupa Jhade, Pravallika Yaganti et al.

Modeling human aesthetic judgments in visual art presents significant challenges due to individual preference variability and the high cost of obtaining labeled data. To reduce cost of acquiring such labels, we propose to apply a comparative learning framework based on pairwise preference assessments rather than direct ratings. This approach leverages the Law of Comparative Judgment, which posits that relative choices exhibit less cognitive burden and greater cognitive consistency than direct scoring. We extract deep convolutional features from painting images using ResNet-50 and develop both a deep neural network regression model and a dual-branch pairwise comparison model. We explored four research questions: (RQ1) How does the proposed deep neural network regression model with CNN features compare to the baseline linear regression model using hand-crafted features? (RQ2) How does pairwise comparative learning compare to regression-based prediction when lacking access to direct rating values? (RQ3) Can we predict individual rater preferences through within-rater and cross-rater analysis? (RQ4) What is the annotation cost trade-off between direct ratings and comparative judgments in terms of human time and effort? Our results show that the deep regression model substantially outperforms the baseline, achieving up to $328\%$ improvement in $R^2$. The comparative model approaches regression performance despite having no access to direct rating values, validating the practical utility of pairwise comparisons. However, predicting individual preferences remains challenging, with both within-rater and cross-rater performance significantly lower than average rating prediction. Human subject experiments reveal that comparative judgments require $60\%$ less annotation time per item, demonstrating superior annotation efficiency for large-scale preference modeling.

Baltag Alexandru, Smets Sonja

We use a novel type of epistemic logic, employing comparative knowledge assertions, to analyze the relative epistemic powers of individuals or groups of agents. Such comparative assertions can express that a group has the potential to (collectively) know everything that another group can know. Moreover, we look at comparisons involving various types of knowledge (fully introspective, positively introspective, etc.), satisfying the corresponding modal-epistemic conditions (e.g., $S5$, $S4$, $KT$). For each epistemic attitude, we are particularly interested in what agents or groups can know about their own epistemic position relative to that of others.

Qasim Khan, Anthony Suen

In this article, we explore the effectiveness of two polynomial methods in solving non-linear time and space fractional partial differential equations. We first outline the general methodology and then apply it to five distinct experiments. The proposed method, noted for its simplicity, demonstrates a high degree of accuracy. Comparative analysis with existing techniques reveals that our approach yields more precise solutions. The results, presented through graphs and tables, indicate that He's and Daftardar-Jafari polynomials significantly enhance accuracy. Additionally, we provide an in-depth discussion on the computational costs associated with these polynomials. Due to its straightforward implementation, the proposed method can be extended for application to a broader range of problems.

Zhaojing Yang, Miru Jun, Jeremy Tien et al.

Learning from human feedback has gained traction in fields like robotics and natural language processing in recent years. While prior works mostly rely on human feedback in the form of comparisons, language is a preferable modality that provides more informative insights into user preferences. In this work, we aim to incorporate comparative language feedback to iteratively improve robot trajectories and to learn reward functions that encode human preferences. To achieve this goal, we learn a shared latent space that integrates trajectory data and language feedback, and subsequently leverage the learned latent space to improve trajectories and learn human preferences. To the best of our knowledge, we are the first to incorporate comparative language feedback into reward learning. Our simulation experiments demonstrate the effectiveness of the learned latent space and the success of our learning algorithms. We also conduct human subject studies that show our reward learning algorithm achieves a 23.9% higher subjective score on average and is 11.3% more time-efficient compared to preference-based reward learning, underscoring the superior performance of our method. Our website is at https://liralab.usc.edu/comparative-language-feedback/

Alfred Galichon, Yu-Wei Hsieh, Maxime Sylvestre

We propose monotone comparative statics results for maximizers of submodular functions, as opposed to maximizers of supermodular functions as in the classical theory put forth by Veinott, Topkis, Milgrom, and Shannon among others. We introduce matrons, a natural structure that is dual to sublattices that generalizes existing structures such as matroids and polymatroids in combinatorial optimization and M-sets in discrete convex analysis. Our monotone comparative statics result is based on a natural order on matrons, which is dual in some sense to Veinott's strong set order on sublattices. As an application, we propose a deferred acceptance algorithm that operates in the case of divisible goods, and we study its convergence properties.

Sohail Ahmed Khan, Duc-Tien Dang-Nguyen

This paper present a comprehensive comparative analysis of supervised and self-supervised models for deepfake detection. We evaluate eight supervised deep learning architectures and two transformer-based models pre-trained using self-supervised strategies (DINO, CLIP) on four benchmarks (FakeAVCeleb, CelebDF-V2, DFDC, and FaceForensics++). Our analysis includes intra-dataset and inter-dataset evaluations, examining the best performing models, generalisation capabilities, and impact of augmentations. We also investigate the trade-off between model size and performance. Our main goal is to provide insights into the effectiveness of different deep learning architectures (transformers, CNNs), training strategies (supervised, self-supervised), and deepfake detection benchmarks. These insights can help guide the development of more accurate and reliable deepfake detection systems, which are crucial in mitigating the harmful impact of deepfakes on individuals and society.

Avi Chawla, Nidhi Mulay, Vikas Bishnoi et al.

Recent years of research in Natural Language Processing (NLP) have witnessed dramatic growth in training large models for generating context-aware language representations. In this regard, numerous NLP systems have leveraged the power of neural network-based architectures to incorporate sense information in embeddings, resulting in Contextualized Word Embeddings (CWEs). Despite this progress, the NLP community has not witnessed any significant work performing a comparative study on the contextualization power of such architectures. This paper presents a comparative study and an extensive analysis of nine widely adopted Transformer models. These models are BERT, CTRL, DistilBERT, OpenAI-GPT, OpenAI-GPT2, Transformer-XL, XLNet, ELECTRA, and ALBERT. We evaluate their contextualization power using two lexical sample Word Sense Disambiguation (WSD) tasks, SensEval-2 and SensEval-3. We adopt a simple yet effective approach to WSD that uses a k-Nearest Neighbor (kNN) classification on CWEs. Experimental results show that the proposed techniques also achieve superior results over the current state-of-the-art on both the WSD tasks

Adam Faci, Marie-Jeanne Lesot, Claire Laudy

Conceptual Graphs (CG) are a graph-based knowledge representation and reasoning formalism; fuzzy Conceptual Graphs (fCG) constitute an extension that enriches their expressiveness, exploiting the fuzzy set theory so as to relax their constraints at various levels. This paper proposes a comparative study of existing approaches over their respective advantages and possible limitations. The discussion revolves around three axes: (a) Critical view of each approach and comparison with previous propositions from the state of the art; (b) Presentation of the many possible interpretations of each definition to illustrate its potential and its limits; (c) Clarification of the part of CG impacted by the definition as well as the relaxed constraint.

Rifkat Davronova, Fatima Adilovab

Quantitative structure-activity relationship (QSAR) is a computer modeling technique for identifying relationships between the structural properties of chemical compounds and biological activity. QSAR modeling is necessary for drug discovery, but it has many limitations. Ensemble-based machine learning approaches have been used to overcome limitations and generate reliable predictions. Ensemble learning creates a set of diverse models and combines them. In our comparative analysis, each ensemble algorithm was paired with each of the basic algorithms, but the basic algorithms were also investigated separately. In this configuration, 57 algorithms were developed and compared on 4 different datasets. Thus, a technique for complex ensemble method is proposed that builds diversified models and integrates them. The proposed individual models did not show impressive results as a unified model, but it was considered the most important predictor when combined. We assessed whether ensembles always give better results than individual algorithms. The Python code written to get experimental results in this article has been uploaded to Github (https://github.com/rifqat/Comparative-Analysis).

Bernardo A. Huberman, Puneet Sharma

As Communication Service Providers (CSPs) adopt the Network Function Virtualization (NFV) paradigm, they need to transition their network function capacity to a virtualized infrastructure with different Network Functions running on a set of heterogeneous servers. This abstract describes a novel technique for allocating server resources (compute, storage and network) for a given set of Virtual Network Function (VNF) requirements. Our approach helps the telco providers decide the most effective way to run several VNFs on servers with different performance characteristics. Our analysis of prior VNF performance characterization on heterogeneous/different server resource allocations shows that the ability to arbitrarily create many VNFs among different servers' resource allocations leads to a comparative advantage among servers. We propose a VNF resource allocation method called COMPARE that maximizes the total throughput of the system by formulating this resource allocation problem as a comparative advantage problem among heterogeneous servers. There several applications for using the VNF resource allocation from COMPARE including transitioning current Telco deployments to NFV based solutions and providing initial VNF placement for Service Function Chain (SFC) provisioning.

Mehedi Kalam, Sk. Monowar Hossein, Sajahan Molla

The inner structure of neutron star is considered from theoretical point of view and is compared with the observed data. We have proposed a form of an equation of state relating pressure with matter density which indicates the stiff equation of state of neutron stars. From our study we have calculated mass(M), compactness(u) and surface red-shift(Zs ) for the neutron stars namely PSR J1614-2230, PSR J1903+327, Cen X-3, SMC X-1, Vela X-1, Her X-1 and compared with the recent observational data. We have also indicated the possible radii of the different stars which needs further study. Finally we have examined the stability for such type of theoretical structure.

Brijesh Dongol, John Derrick

Linearizability has become the key correctness criterion for concurrent data structures, ensuring that histories of the concurrent object under consideration are consistent, where consistency is judged with respect to a sequential history of a corresponding abstract data structure. Linearizability allows any order of concurrent (i.e., overlapping) calls to operations to be picked, but requires the real-time order of non-overlapping to be preserved. Over the years numerous techniques for verifying linearizability have been developed, using a variety of formal foundations such as refinement, shape analysis, reduction, etc. However, as the underlying framework, nomenclature and terminology for each method differs, it has become difficult for practitioners to judge the differences between each approach, and hence, judge the methodology most appropriate for the data structure at hand. We compare the major of methods used to verify linearizability, describe the main contribution of each method, and compare their advantages and limitations.

C. Klein, J. -C. Saut

We survey and compare, mainly in the two-dimensional case, various results obtained by IST and PDE techniques for integrable equations. We also comment on what can be predicted from integrable equations on non integrable ones.

Peter Sasvari

A novel comparative research and analysis method is proposed and applied on the Hungarian economic sectors. The question of what factors have an effect on their net income is essential for enterprises. First, the potential indicators related to economic sectors were studied and then compared to the net income of the surveyed enterprises. The data resulting from the comparison showed that the growing penetration of electronic marketpalces contributed to the change of the net income of enterprises in various economic sectors to the extent of 37%. Among all the potential indicators, only the indicator of electronic marketplaces has a direct influence on the net income of enterprises. Two clusters based on the potential indicators were indicated.

Alexander Saichev, Svetlana Lapinova

Comparative statistical properties of Parkinson, Garman-Klass, Roger-Satchell and bridge oscillation estimators are discussed. Point and interval estimations, related with mentioned estimators are considered

A. L. Sellerio, B. Bassetti, H. Isambert et al.

We present a comparative analysis of large-scale topological and evolutionary properties of transcription networks in three species, the two distant bacteria E. coli and B. subtilis, and the yeast S. cerevisiae. The study focuses on the global aspects of feedback and hierarchy in transcriptional regulatory pathways. While confirming that gene duplication has a significant impact on the shaping of all the analyzed transcription networks, our results point to distinct trends between the bacteria, where time constraints in the transcription of downstream genes might be important in shaping the hierarchical structure of the network, and yeast, which seems able to sustain a higher wiring complexity, that includes the more feedback, intricate hierarchy, and the combinatorial use of heterodimers made of duplicate transcription factors.

Ahmed Ait Ali, Fabien Michaut, Francis Lepage

In recent years, there has been a strong interest in measuring the available bandwidth of network paths. Several methods and techniques have been proposed and various measurement tools have been developed and evaluated. However, there have been few comparative studies with regards to the actual performance of these tools. This paper presents a study of available bandwidth measurement techniques and undertakes a comparative analysis in terms of accuracy, intrusiveness and response time of active probing tools. Finally, measurement errors and the uncertainty of the tools are analysed and overall conclusions made.

S. Minton, J. Bresina, M. Drummond

For many years, the intuitions underlying partial-order planning were largely taken for granted. Only in the past few years has there been renewed interest in the fundamental principles underlying this paradigm. In this paper, we present a rigorous comparative analysis of partial-order and total-order planning by focusing on two specific planners that can be directly compared. We show that there are some subtle assumptions that underly the wide-spread intuitions regarding the supposed efficiency of partial-order planning. For instance, the superiority of partial-order planning can depend critically upon the search strategy and the structure of the search space. Understanding the underlying assumptions is crucial for constructing efficient planners.

S. Dürr, Ch. Hoelbling, U. Wenger

We perform a comparative study of the infrared properties of overlap and staggered fermions in QCD. We observe that the infrared spectrum of the APE/HYP improved staggered Dirac operator develops a four-fold near-degeneracy and is in quantitative agreement with the infrared spectrum of the overlap operator. The near-degeneracy allows us to identify the zero modes of the staggered operator and we find that the number of zero modes is in line with the topological index of the overlap operator.