Search

This paper exploits the zero-shot capabilities of pre-trained large language models (LLMs) for music genre classification. The proposed approach splits audio signals into 20 ms chunks and processes them through convolutional feature encoders, a transformer encoder, and additional layers for coding audio units and generating feature vectors. The extracted feature vectors are used to train a classification head. During inference, predictions on individual chunks are aggregated for a final genre classification. We conducted a comprehensive comparison of LLMs, including WavLM, HuBERT, and wav2vec 2.0, with traditional deep learning architectures like 1D and 2D convolutional neural networks (CNNs) and the audio spectrogram transformer (AST). Our findings demonstrate the superior performance of the AST model, achieving an overall accuracy of 85.5%, surpassing all other models evaluated. These results highlight the potential of LLMs and transformer-based architectures for advancing music information retrieval tasks, even in zero-shot scenarios., Comment: 7 pages

This paper presents our findings on the automatic summarization of Java methods within Ericsson, a global telecommunications company. We evaluate the performance of an approach called Automatic Semantic Augmentation of Prompts (ASAP), which uses a Large Language Model (LLM) to generate leading summary comments for Java methods. ASAP enhances the $LLM's$ prompt context by integrating static program analysis and information retrieval techniques to identify similar exemplar methods along with their developer-written Javadocs, and serves as the baseline in our study. In contrast, we explore and compare the performance of four simpler approaches that do not require static program analysis, information retrieval, or the presence of exemplars as in the ASAP method. Our methods rely solely on the Java method body as input, making them lightweight and more suitable for rapid deployment in commercial software development environments. We conducted experiments on an Ericsson software project and replicated the study using two widely-used open-source Java projects, Guava and Elasticsearch, to ensure the reliability of our results. Performance was measured across eight metrics that capture various aspects of similarity. Notably, one of our simpler approaches performed as well as or better than the ASAP method on both the Ericsson project and the open-source projects. Additionally, we performed an ablation study to examine the impact of method names on Javadoc summary generation across our four proposed approaches and the ASAP method. By masking the method names and observing the generated summaries, we found that our approaches were statistically significantly less influenced by the absence of method names compared to the baseline. This suggests that our methods are more robust to variations in method names and may derive summaries more comprehensively from the method body than the ASAP approach., Comment: 16 pages, 6 tables, 4 figures. Accepted at the 2024 International Conference on Software Maintenance and Evolution (ICSME) 2024 - Industry Track

At optical/ultraviolet energies, blazars display an underlying thermal (unpolarized) contribution from the accretion disc, torus and line emitting regions, diluting the polarized emission from the jet-component. Optical polarimetry can be used to disentangle the thermal and non-thermal components, and place constraints on the particle populations and acceleration mechanisms responsible for the non-thermal emission. We present the results of a linear optical spectropolarimetric observing campaign of 18 blazars (6 BLLs and 12 FSRQs) undertaken with the Southern African Large Telescope between 2016 and 2022. This was done to observe these systems during flaring states, as well as long term monitoring of PKS1510-089, AP Lib and PKS 1034-293. The observations traced the frequency dependence of the degree and angle of polarization, as well as changes in the spectral line strengths. We investigated possible correlations between the polarization and other observed characteristics for the sources. While an indication of correlation was found between the frequency dependence and the average level of polarization for some sources, a correlation was not found for the population as a whole. These results highlight that continuous observations and in-depth modelling of polarization and its frequency dependence is required to obtain a more holistic view of TeV blazars., Comment: 17 pages, 21 figures, 3 tables, accepted for publication in MNRAS

Motivated by recent theoretical predictions about the existence of a $ B \bar{B}$ bound state (also denoted as $ X(10550) $), in this work we estimate the production of the $S$-wave $ B^+ B^-$ molecule via $\Upsilon (4S)$ radiative decays. In particular, we make use of effective Lagrangian approach and the compositeness condition to calculate the $ X(10550) $ production rate via $\Upsilon(4S)\rightarrow \gamma X(10550)$ decays employing triangle diagrams. Our results show that the partial decay width of this reaction is of the order of $0.5 - 192 \ \keV $ for a respective binding energy of $1 - 100 $ MeV, corresponding to a branching fraction of $ 10^{-5} - 10^{-3}$. These findings suggest that the existence of the $ X(10550) $ might be checked via the analysis of the mentioned decay in present and future experiments., Comment: 13 pages, 4 figures

Facial expression recognition is a pivotal component in machine learning, facilitating various applications. However, convolutional neural networks (CNNs) are often plagued by catastrophic forgetting, impeding their adaptability. The proposed method, emotion-centered generative replay (ECgr), tackles this challenge by integrating synthetic images from generative adversarial networks. Moreover, ECgr incorporates a quality assurance algorithm to ensure the fidelity of generated images. This dual approach enables CNNs to retain past knowledge while learning new tasks, enhancing their performance in emotion recognition. The experimental results on four diverse facial expression datasets demonstrate that incorporating images generated by our pseudo-rehearsal method enhances training on the targeted dataset and the source dataset while making the CNN retain previously learned knowledge., Comment: 15 pages

The study of human emotions, traditionally a cornerstone in fields like psychology and neuroscience, has been profoundly impacted by the advent of artificial intelligence (AI). Multiple channels, such as speech (voice) and facial expressions (image), are crucial in understanding human emotions. However, AI's journey in multimodal emotion recognition (MER) is marked by substantial technical challenges. One significant hurdle is how AI models manage the absence of a particular modality - a frequent occurrence in real-world situations. This study's central focus is assessing the performance and resilience of two strategies when confronted with the lack of one modality: a novel multimodal dynamic modality and view selection and a cross-attention mechanism. Results on the RECOLA dataset show that dynamic selection-based methods are a promising approach for MER. In the missing modalities scenarios, all dynamic selection-based methods outperformed the baseline. The study concludes by emphasizing the intricate interplay between audio and video modalities in emotion prediction, showcasing the adaptability of dynamic selection methods in handling missing modalities., Comment: 15 pages

The proliferation of textual data on the Internet presents a unique opportunity for institutions and companies to monitor public opinion about their services and products. Given the rapid generation of such data, the text stream mining setting, which handles sequentially arriving, potentially infinite text streams, is often more suitable than traditional batch learning. While pre-trained language models are commonly employed for their high-quality text vectorization capabilities in streaming contexts, they face challenges adapting to concept drift - the phenomenon where the data distribution changes over time, adversely affecting model performance. Addressing the issue of concept drift, this study explores the efficacy of seven text sampling methods designed to selectively fine-tune language models, thereby mitigating performance degradation. We precisely assess the impact of these methods on fine-tuning the SBERT model using four different loss functions. Our evaluation, focused on Macro F1-score and elapsed time, employs two text stream datasets and an incremental SVM classifier to benchmark performance. Our findings indicate that Softmax loss and Batch All Triplets loss are particularly effective for text stream classification, demonstrating that larger sample sizes generally correlate with improved macro F1-scores. Notably, our proposed WordPieceToken ratio sampling method significantly enhances performance with the identified loss functions, surpassing baseline results., Comment: Accepted for presentation at the 27th International Conference on Pattern Recognition (ICPR) 2024

Systems and individuals produce data continuously. On the Internet, people share their knowledge, sentiments, and opinions, provide reviews about services and products, and so on. Automatically learning from these textual data can provide insights to organizations and institutions, thus preventing financial impacts, for example. To learn from textual data over time, the machine learning system must account for concept drift. Concept drift is a frequent phenomenon in real-world datasets and corresponds to changes in data distribution over time. For instance, a concept drift occurs when sentiments change or a word's meaning is adjusted over time. Although concept drift is frequent in real-world applications, benchmark datasets with labeled drifts are rare in the literature. To bridge this gap, this paper provides four textual drift generation methods to ease the production of datasets with labeled drifts. These methods were applied to Yelp and Airbnb datasets and tested using incremental classifiers respecting the stream mining paradigm to evaluate their ability to recover from the drifts. Results show that all methods have their performance degraded right after the drifts, and the incremental SVM is the fastest to run and recover the previous performance levels regarding accuracy and Macro F1-Score.

Background: Modern Code Review (MCR) is a lightweight alternative to traditional code inspections. While secondary studies on MCR exist, it is unknown whether the research community has targeted themes that practitioners consider important. Objectives: The objectives are to provide an overview of MCR research, analyze the practitioners' opinions on the importance of MCR research, investigate the alignment between research and practice, and propose future MCR research avenues. Method: We conducted a systematic mapping study to survey state of the art until and including 2021, employed the Q-Methodology to analyze the practitioners' perception of the relevance of MCR research, and analyzed the primary studies' research impact. Results: We analyzed 244 primary studies, resulting in five themes. As a result of the 1,300 survey data points, we found that the respondents are positive about research investigating the impact of MCR on product quality and MCR process properties. In contrast, they are negative about human factor- and support systems-related research. Conclusion: These results indicate a misalignment between the state of the art and the themes deemed important by most survey respondents. Researchers should focus on solutions that can improve the state of MCR practice. We provide an MCR research agenda that can potentially increase the impact of MCR research.

We review different notions of cuts appearing throughout the literature on scattering amplitudes. Despite similar names, such as unitarity cuts or generalized cuts, they often represent distinct computations and distinct physics. We consolidate this knowledge, summarize how cuts are used in various computational strategies, and explain their relations to other quantities including imaginary parts, discontinuities, and monodromies. Differences and nuances are illustrated on explicit examples., Comment: 23 pages, invited contribution to the Encyclopedia of Mathematical Physics

Background: Modern Code Review (MCR) is a key component for delivering high-quality software and sharing knowledge among developers. Effective reviews require an in-depth understanding of the code and demand from the reviewers to contextualize the change from different perspectives. Aim: While there is a plethora of research on solutions that support developers to understand changed code, we have observed that many provide only narrow, specialized insights and very few aggregate information in a meaningful manner. Therefore, we aim to provide a vision of improving code understanding in MCR. Method: We classified 53 research papers suggesting proposals to improve MCR code understanding. We use this classification, the needs expressed by code reviewers from previous research, and the information we have not found in the literature for extrapolation. Results: We identified four major types of support systems and suggest an environment for contextualized code reviews. Furthermore, we illustrate with a set of scenarios how such an environment would improve the effectiveness of code reviews. Conclusions: Current research focuses mostly on providing narrow support for developers. We outline a vision for how MCR can be improved by using context and reducing the cognitive load on developers. We hope our vision can foster future advancements in development environments., Comment: First IDE Workshop (IDE '24), April 20, 2024, Lisbon, Portugal

Initially supported by Twitter, hashtags are now used on several social media platforms. Hashtags are helpful for tagging, tracking, and grouping posts on similar topics. In this paper, based on a hashtag stream regarding the hashtag #mybodymychoice, we analyze hashtag drifts over time using concepts from graph analysis and textual data streams using the Girvan-Newman method to uncover hashtag communities in annual snapshots between 2018 and 2022. In addition, we offer insights about some correlated hashtags found in the study. Our approach can be useful for monitoring changes over time in opinions and sentiment patterns about an entity on social media. Even though the hashtag #mybodymychoice was initially coupled with women's rights, abortion, and bodily autonomy, we observe that it suffered drifts during the studied period across topics such as drug legalization, vaccination, political protests, war, and civil rights. The year 2021 was the most significant drifting year, in which the communities detected and their respective sizes suggest that #mybodymychoice had a significant drift to vaccination and Covid-19-related topics., Comment: Published in Expert Systems with Applications

In this work, we present simulations of two Open Quantum System models, Collisional and Markovian Reservoir, with noise simulations, the IBM devices ($\textit{ibm_kyoto}$, $\textit{ibm_osaka}$) and the OQC device Lucy. Extending the results of Garc\'ia-P\'erez, et al. [npj Quantum Information 6.1 (2020): 1]. Using the Mitiq toolkit, we apply Zero-Noise extrapolation (ZNE), an error mitigation technique, and analyze their deviation from the theoretical results for the models under study. For both models, by applying ZNE, we were able to reduce the error and overlap it with the theoretical results. All our simulations and experiments were done in the qBraid environment.

Due to the advent and increase in the popularity of the Internet, people have been producing and disseminating textual data in several ways, such as reviews, social media posts, and news articles. As a result, numerous researchers have been working on discovering patterns in textual data, especially because social media posts function as social sensors, indicating peoples' opinions, interests, etc. However, most tasks regarding natural language processing are addressed using traditional machine learning methods and static datasets. This setting can lead to several problems, such as an outdated dataset, which may not correspond to reality, and an outdated model, which has its performance degrading over time. Concept drift is another aspect that emphasizes these issues, which corresponds to data distribution and pattern changes. In a text stream scenario, it is even more challenging due to its characteristics, such as the high speed and data arriving sequentially. In addition, models for this type of scenario must adhere to the constraints mentioned above while learning from the stream by storing texts for a limited time and consuming low memory. In this study, we performed a systematic literature review regarding concept drift adaptation in text stream scenarios. Considering well-defined criteria, we selected 40 papers to unravel aspects such as text drift categories, types of text drift detection, model update mechanism, the addressed stream mining tasks, types of text representations, and text representation update mechanism. In addition, we discussed drift visualization and simulation and listed real-world datasets used in the selected papers. Therefore, this paper comprehensively reviews the concept drift adaptation in text stream mining scenarios., Comment: 49 pages

The rapid advancements in Artificial Intelligence (AI), particularly in generative AI and foundational models (FMs), have ushered in transformative changes across various industries. Large language models (LLMs), a type of FM, have demonstrated their prowess in natural language processing tasks and content generation, revolutionizing how we interact with software products and services. This article explores the integration of FMs in the telecommunications industry, shedding light on the concept of AI native telco, where AI is seamlessly woven into the fabric of telecom products. It delves into the engineering considerations and unique challenges associated with implementing FMs into the software life cycle, emphasizing the need for AI native-first approaches. Despite the enormous potential of FMs, ethical, regulatory, and operational challenges require careful consideration, especially in mission-critical telecom contexts. As the telecom industry seeks to harness the power of AI, a comprehensive understanding of these challenges is vital to thrive in a fiercely competitive market., Comment: 5 pages, 1 figure

In a previous work we computed the thermally-averaged cross sections for the production and absorption of the $\chi_{c1}(4274)$ state in the hot hadron gas formed in heavy ion collisions. In the present work we estimate the final yield of this exotic state in these collisions. We use the coalescence model to fix the initial multiplicities. The state is is treated as a $P-$wave bound state of $D_s\bar D_{s0}$ and also as a compact tetraquark. The Bjorken picture is used to model the hydrodynamic expansion and cooling. Then, the kinetic equation is solved to evaluate the time evolution of the $\chi_{c1}(4274)$ yield during the hot hadron gas phase. Since the $\chi_{c1}(4274)$ decay width is large it might decay inside the hadron gas. Therefore we also include the $chi_{c1}(4274)$ decay and regeneration terms by means of an effective coupling, estimated from the available data. The combined effects of hadronic interactions and the $\chi_{c1}(4274)$ decay have a strong impact on the final yield. Also, predictions of the $\chi_{c1}(4274)$ multiplicity as a function of centrality and of the charged hadron multiplicity (measured at midrapidity) are presented. Finally, we calculate the yield of a proposed $P-$wave molecular state of $D_s \bar{D_{s0}}$, $Y^{\prime}(4274)$, characterized by a smaller width and smaller coupling constant obtained from the Weinberg compositeness condition., Comment: 7 pages, 5 figures

Reviewing source code is a common practice in a modern and collaborative coding environment. In the past few years, the research on modern code reviews has gained interest among practitioners and researchers. The objective of our investigation is to observe the evolution of research related to modern code reviews, identify research gaps and serve as a basis for future research. We use a systematic mapping approach to identify and classify 177 research papers. As preliminary result of our investigation, we present in this paper a classification scheme of the main contributions of modern code review research between 2005 and 2018., Comment: EASE 2019: 340-345