Search

Contextualized embeddings based on large language models (LLMs) are available for various languages, but their coverage is often limited for lower resourced languages. Training LLMs for such languages is often difficult due to insufficient data and high computational cost. Especially for very low resource languages, static word embeddings thus still offer a viable alternative. There is, however, a notable lack of comprehensive repositories with such embeddings for diverse languages. To address this, we present LowREm, a centralized repository of static embeddings for 87 low-resource languages. We also propose a novel method to enhance GloVe-based embeddings by integrating multilingual graph knowledge, utilizing another source of knowledge. We demonstrate the superior performance of our enhanced embeddings as compared to contextualized embeddings extracted from XLM-R on sentiment analysis. Our code and data are publicly available under https://huggingface.co/DFKI., Comment: Short paper, preview

The nature of neutrino (whether Majorana or Dirac) and the origin of neutrino masses are still some of the mysteries to be resolved. Also, the recent results on (g-2)$_{e,\mu}$ measurements deviate from the Standard Model (SM) predictions and motivate us towards new physics beyond the SM. In this work, we propose a model with the minimal field content in the framework of anomaly free extension of Standard Model; i.e. U(1)$_{L_e-L_{\mu}}$ symmetry model. We find this model capable of explaining the low energy neutrino phenomenology and anomalous magnetic moment(g-2)$_{e,\mu}$ of electron and muon, simultaneously. The field content is extended by a SU(2)$_L$ singlet scalar field $\phi$ and three right handed neutrinos N$_R$(R = 1,2,3). Thus, the neutrino masses are generated using the Type-I seesaw mechanism. The extended model leads to the results, which are in consistency with the experimental values of (g-2)$_{e,\mu}$ and also satisfy all the relevant experimental data., Comment: 13 pages, 10 figures and 2 tables

We provide upper bounds on the total number of irreducible factors, and in particular irreducibility criteria for some classes of bivariate polynomials $f(x,y)$ over an arbitrary field $\mathbb{K}$. Our results rely on information on the degrees of the coefficients of $f$, and on information on the factorization of the constant term and of the leading coefficient of $f$, viewed as a polynomial in $y$ with coefficients in $\mathbb{K}[x]$. In particular, we provide a generalization of the bivariate version of Perron's irreducibility criterion, and similar results for polynomials in an arbitrary number of indeterminates. The proofs use non-Archimedean absolute values, that are suitable for finding information on the location of the roots of $f$ in an algebraic closure of $\mathbb{K}(x)$., Comment: 14 pages

Mathematical reasoning serves as a cornerstone for assessing the fundamental cognitive capabilities of human intelligence. In recent times, there has been a notable surge in the development of Large Language Models (LLMs) geared towards the automated resolution of mathematical problems. However, the landscape of mathematical problem types is vast and varied, with LLM-oriented techniques undergoing evaluation across diverse datasets and settings. This diversity makes it challenging to discern the true advancements and obstacles within this burgeoning field. This survey endeavors to address four pivotal dimensions: i) a comprehensive exploration of the various mathematical problems and their corresponding datasets that have been investigated; ii) an examination of the spectrum of LLM-oriented techniques that have been proposed for mathematical problem-solving; iii) an overview of factors and concerns affecting LLMs in solving math; and iv) an elucidation of the persisting challenges within this domain. To the best of our knowledge, this survey stands as one of the first extensive examinations of the landscape of LLMs in the realm of mathematics, providing a holistic perspective on the current state, accomplishments, and future challenges in this rapidly evolving field., Comment: EACL 2024 Student Research Workshop, 8 pages

Building on previous work using reinforcement learning (RL) focused on identification of exfiltration paths, this work expands the methodology to include protocol and payload considerations. The former approach to exfiltration path discovery, where reward and state are associated specifically with the determination of optimal paths, are presented with these additional realistic characteristics to account for nuances in adversarial behavior. The paths generated are enhanced by including communication payload and protocol into the Markov decision process (MDP) in order to more realistically emulate attributes of network based exfiltration events. The proposed method will help emulate complex adversarial considerations such as the size of a payload being exported over time or the protocol on which it occurs, as is the case where threat actors steal data over long periods of time using system native ports or protocols to avoid detection. As such, practitioners will be able to improve identification of expected adversary behavior under various payload and protocol assumptions more comprehensively.

Fine-grained financial sentiment analysis on news headlines is a challenging task requiring human-annotated datasets to achieve high performance. Limited studies have tried to address the sentiment extraction task in a setting where multiple entities are present in a news headline. In an effort to further research in this area, we make publicly available SEntFiN 1.0, a human-annotated dataset of 10,753 news headlines with entity-sentiment annotations, of which 2,847 headlines contain multiple entities, often with conflicting sentiments. We augment our dataset with a database of over 1,000 financial entities and their various representations in news media amounting to over 5,000 phrases. We propose a framework that enables the extraction of entity-relevant sentiments using a feature-based approach rather than an expression-based approach. For sentiment extraction, we utilize 12 different learning schemes utilizing lexicon-based and pre-trained sentence representations and five classification approaches. Our experiments indicate that lexicon-based n-gram ensembles are above par with pre-trained word embedding schemes such as GloVe. Overall, RoBERTa and finBERT (domain-specific BERT) achieve the highest average accuracy of 94.29% and F1-score of 93.27%. Further, using over 210,000 entity-sentiment predictions, we validate the economic effect of sentiments on aggregate market movements over a long duration., Comment: 32 Pages

In recent years, there has been an increasing interest in the use of graph neural networks (GNNs) for analyzing dynamic graphs, which are graphs that evolve over time. However, there is still a lack of understanding of how different temporal graph neural network (TGNs) configurations can impact the accuracy of predictions on dynamic graphs. Moreover, the hunt for benchmark datasets for these TGNs models is still ongoing. Up until recently, Pytorch Geometric Temporal came up with a few benchmark datasets but most of these datasets have not been analyzed with different TGN models to establish the state-of-the-art. Therefore, this project aims to address this gap in the literature by performing a qualitative analysis of spatial-temporal dependence structure learning on dynamic graphs, as well as a comparative study of the effectiveness of selected TGNs on node and edge prediction tasks. Additionally, an extensive ablation study will be conducted on different variants of the best-performing TGN to identify the key factors contributing to its performance. By achieving these objectives, this project will provide valuable insights into the design and optimization of TGNs for dynamic graph analysis, with potential applications in areas such as disease spread prediction, social network analysis, traffic prediction, and more. Moreover, an attempt is made to convert snapshot-based data to the event-based dataset and make it compatible with the SOTA model namely TGN to perform node regression task.

In our recent work we identify the hybrid textures of neutrino mass matrix which simultaneously account for dark matter (DM) and neutrinoless double beta decay ($0\nu\beta\beta$). We also obtained the bounds on dark matter mass and effective Majorana mass $|M_{ee}|$. In this work we look for those hybrid textures which altogether accounts for DM, $0\nu\beta\beta$ and leptogenesis. We have found correlation of baryon asymmetry of universe $Y$ with dark matter mass $M_1$ and effective Majorana mass $|M_{ee}|$. We use experimental bounds on relic density of dark matter ($\Omega h^2$) and baryon asymmetry of universe to identify the hybrid textures. We found that out of five hybrid textures which simultaneously satisfies the physics observations of the DM and $0\nu\beta\beta$ only three hybrid textures altogether satisfy the DM, $0\nu\beta\beta$ and leptogenesis. It is interesting to note that these three hybrid textures gives lower bound to the effective Majorana mass $|M_{ee}|$ which can be probed in current and future experiments like SuperNEMO, KamLAND-Zen, NEXT, and nEXO (5 year) have sensitivity reaches of 0.05 eV, 0.045 eV, 0.03 eV, and 0.015 eV, respectively., Comment: 19 pages, 6 figures, 4 tables, section 2, 3 and 5 restructured

We proposed a model which can explain the neutrino phenomenology, dark matter and anomalous magnetic moment$(g-2)$ in a common framework. The inverted sea saw (ISS)(2,3) mechanism has been incorporated, in which we get an extra sterile state and this state act as a viable dark matter candidate. The right handed neutrino mass is obtained in TeV scale, which is accessible at LHC. The anomaly free $U(1)_{L_{e}-L{\mu}}$ gauge symmetry is introduced to explain the anomalous magnetic moment of electron and muon because it provides a natural origin of $(g-2)$ in a very minimal setup. The corresponding MeV scale gauge boson successfully explain the anomalous magnetic moment of electron and muon$(g-2)_{e,\mu}$, simultaneously. Thus obtained neutrino phenomenology and relic abundance of dark matter are compatible with experimental results., Comment: 16 pages, 4 figures, 2 tables