arXiv subjects

Mohamed Trabelsi

Publications and source records attributed to Mohamed Trabelsi.

16 recordsLinked to original sources

arXiv2026

Autonomous Research for Open-Ended Problems: A Case Study on Telecom Ticket Retrieval

Recent breakthroughs in LLM-based systems and their abilities in problem solving and coding have allowed progress in the AI for Science paradigm, potentially replacing human roles in machine learning (ML) research. However, while several frameworks of fully autonomous end-to-end ML research have been proposed, successful implementations of them are often limited to problems with narrow search spaces, like language modeling or biomedical ML benchmarks. In this paper, we explore how autonomous research can be adapted to solve open-ended, industry-grade ML problems, by considering a case study: telecom ticket retrieval, an open-ended task with degrees of freedom in representation, architecture, and training data generation. We discover that autonomous research for open-ended problems with commercial and open-source agents shows both promise and limitations: while autonomous research can excel in narrow hyperparameter optimization, it lacks human-like intuition and creativity and requires operational overhead. Even with minimal human supervision, autonomous research can reach $90\%$ of state-of-the-art performance (0.34 vs. 0.38 Recall@1) in a much shorter time period (10 weeks vs. 10 months of human work) at a modest cost (up to \$200 per Cursor campaign). Our empirical evidence recommends that human researchers and autonomous research frameworks work together for best results in ML research.

cs.AI↗

arXiv2026

ASTRA - Agentic System for Ticket Resolution and Analysis

Technical operations teams resolve large volumes of incidents by synthesizing fragmented evidence from ticket text, historical cases, system logs, and technical documentation. Existing automation often relies on monolithic generation without explicit evidence modeling or provenance, making outputs difficult to verify when critical signals are sparse across sources. We propose ASTRA, an agentic system for ticket resolution in which a central orchestrator coordinates three specialist information-gathering agents and drives a judge-orchestrator refinement loop to produce evidence-backed troubleshooting reports. TicketSimilarityAgent retrieves relevant historical precedents through dense retrieval and LLM reranking; LogAgent distills hundreds of thousands of log lines into structured, quote-grounded findings using deterministic filtering and constrained LLM analysis; and DomainKnowledgeAgent retrieves relevant technical knowledge via the Model Context Protocol (MCP). Their outputs are transformed into a claim-evidence representation linking each claim to a verbatim source passage, assigning a support level, and preventing cross-attribution. A JudgeAgent scores the report on five criteria, while the OrchestratorAgent converts low scores into targeted follow-up queries for bounded iterative refinement. Evaluated on 987 real-world telecom fault tickets across seven product lines, ASTRA achieves a mean quality score of 4.13/5.0, with 59.9% of reports identifying the fault area at the component-family level or better. Relevance and Clarity scores are 4.88 and 4.94, respectively, while fabricated technical details remain below 3% of error cases. Stratification by fault type reveals that hardware faults remain substantially harder than software or configuration faults (Cohen's d=0.80), pointing to a fundamental limitation of text-based evidence channels for hardware fault diagnosis.

cs.MA↗

arXiv2026

TeleDoCTR: Domain-Specific and Contextual Troubleshooting for Telecommunications

Ticket troubleshooting refers to the process of analyzing and resolving problems that are reported through a ticketing system. In large organizations offering a wide range of services, this task is highly complex due to the diversity of submitted tickets and the need for specialized domain knowledge. In particular, troubleshooting in telecommunications (telecom) is a very time-consuming task as it requires experts to interpret ticket content, consult documentation, and search historical records to identify appropriate resolutions. This human-intensive approach not only delays issue resolution but also hinders overall operational efficiency. To enhance the effectiveness and efficiency of ticket troubleshooting in telecom, we propose TeleDoCTR, a novel telecom-related, domain-specific, and contextual troubleshooting system tailored for end-to-end ticket resolution in telecom. TeleDoCTR integrates both domain-specific ranking and generative models to automate key steps of the troubleshooting workflow which are: routing tickets to the appropriate expert team responsible for resolving the ticket (classification task), retrieving contextually and semantically similar historical tickets (retrieval task), and generating a detailed fault analysis report outlining the issue, root cause, and potential solutions (generation task). We evaluate TeleDoCTR on a real-world dataset from a telecom infrastructure and demonstrate that it achieves superior performance over existing state-of-the-art methods, significantly enhancing the accuracy and efficiency of the troubleshooting process.

cs.LG↗

arXiv2025

Time Series Language Model for Descriptive Caption Generation

The automatic generation of representative natural language descriptions for observable patterns in time series data enhances interpretability, simplifies analysis and increases cross-domain utility of temporal data. While pre-trained foundation models have made considerable progress in natural language processing (NLP) and computer vision (CV), their application to time series analysis has been hindered by data scarcity. Although several large language model (LLM)-based methods have been proposed for time series forecasting, time series captioning is under-explored in the context of LLMs. In this paper, we introduce TSLM, a novel time series language model designed specifically for time series captioning. TSLM operates as an encoder-decoder model, leveraging both text prompts and time series data representations to capture subtle temporal patterns across multiple phases and generate precise textual descriptions of time series inputs. TSLM addresses the data scarcity problem in time series captioning by first leveraging an in-context prompting synthetic data generation, and second denoising the generated data via a novel cross-modal dense retrieval scoring applied to time series-caption pairs. Experimental findings on various time series captioning datasets demonstrate that TSLM outperforms existing state-of-the-art approaches from multiple data modalities by a significant margin.

cs.CL↗

arXiv2024

Increasing Interpretability of Neural Networks By Approximating Human Visual Saliency

Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets, causing over-fitting and reducing the explainability. Recent advances have shown that guiding models to human-defined regions of saliency within individual images significantly increases performance and interpretability. Human-guided models also exhibit greater generalization capabilities, as coincidental dataset features are avoided. Results show that models trained with saliency incorporation display an increase in interpretability of up to 30% over models trained without saliency information. The collection of this saliency information, however, can be costly, laborious and in some cases infeasible. To address this limitation, we propose a combination strategy of saliency incorporation and active learning to reduce the human annotation data required by 80% while maintaining the interpretability and performance increase from human saliency. Extensive experimentation outlines the effectiveness of the proposed approach across five public datasets and six active learning criteria.

cs.CV↗

arXiv2023

LogGPT: Log Anomaly Detection via GPT

Detecting system anomalies based on log data is important for ensuring the security and reliability of computer systems. Recently, deep learning models have been widely used for log anomaly detection. The core idea is to model the log sequences as natural language and adopt deep sequential models, such as LSTM or Transformer, to encode the normal patterns in log sequences via language modeling. However, there is a gap between language modeling and anomaly detection as the objective of training a sequential model via a language modeling loss is not directly related to anomaly detection. To fill up the gap, we propose LogGPT, a novel framework that employs GPT for log anomaly detection. LogGPT is first trained to predict the next log entry based on the preceding sequence. To further enhance the performance of LogGPT, we propose a novel reinforcement learning strategy to finetune the model specifically for the log anomaly detection task. The experimental results on three datasets show that LogGPT significantly outperforms existing state-of-the-art approaches.

cs.LG↗

arXiv2023

Absformer: Transformer-based Model for Unsupervised Multi-Document Abstractive Summarization

Multi-document summarization (MDS) refers to the task of summarizing the text in multiple documents into a concise summary. The generated summary can save the time of reading many documents by providing the important content in the form of a few sentences. Abstractive MDS aims to generate a coherent and fluent summary for multiple documents using natural language generation techniques. In this paper, we consider the unsupervised abstractive MDS setting where there are only documents with no groundtruh summaries provided, and we propose Absformer, a new Transformer-based method for unsupervised abstractive summary generation. Our method consists of a first step where we pretrain a Transformer-based encoder using the masked language modeling (MLM) objective as the pretraining task in order to cluster the documents into semantically similar groups; and a second step where we train a Transformer-based decoder to generate abstractive summaries for the clusters of documents. To our knowledge, we are the first to successfully incorporate a Transformer-based model to solve the unsupervised abstractive MDS task. We evaluate our approach using three real-world datasets from different domains, and we demonstrate both substantial improvements in terms of evaluation metrics over state-of-the-art abstractive-based methods, and generalization to datasets from different domains.

cs.CL↗

arXiv2022

Time-Frequency Distributions of Heart Sound Signals: A Comparative Study using Convolutional Neural Networks

Time-Frequency Distributions (TFDs) support the heart sound characterisation and classification in early cardiac screening. However, despite the frequent use of TFDs in signal analysis, no study comprehensively compared their performances on deep learning for automatic diagnosis. Furthermore, the combination of signal processing methods as inputs for Convolutional Neural Networks (CNNs) has been proved as a practical approach to increasing signal classification performance. Therefore, this study aimed to investigate the optimal use of TFD/ combined TFDs as input for CNNs. The presented results revealed that: 1) The transformation of the heart sound signal into the TF domain achieves higher classification performance than using of raw signals. Among the TFDs, the difference in the performance was slight for all the CNN models (within $1.3\%$ in average accuracy). However, Continuous wavelet transform (CWT) and Chirplet transform (CT) outperformed the rest. 2) The appropriate increase of the CNN capacity and architecture optimisation can improve the performance, while the network architecture should not be overly complicated. Based on the ResNet or SEResNet family results, the increase in the number of parameters and the depth of the structure do not improve the performance apparently. 3) Combining TFDs as CNN inputs did not significantly improve the classification results. The findings of this study provided the knowledge for selecting TFDs as CNN input and designing CNN architecture for heart sound classification.

eess.SP↗

arXiv2022

DAME: Domain Adaptation for Matching Entities

Entity matching (EM) identifies data records that refer to the same real-world entity. Despite the effort in the past years to improve the performance in EM, the existing methods still require a huge amount of labeled data in each domain during the training phase. These methods treat each domain individually, and capture the specific signals for each dataset in EM, and this leads to overfitting on just one dataset. The knowledge that is learned from one dataset is not utilized to better understand the EM task in order to make predictions on the unseen datasets with fewer labeled samples. In this paper, we propose a new domain adaptation-based method that transfers the task knowledge from multiple source domains to a target domain. Our method presents a new setting for EM where the objective is to capture the task-specific knowledge from pretraining our model using multiple source domains, then testing our model on a target domain. We study the zero-shot learning case on the target domain, and demonstrate that our method learns the EM task and transfers knowledge to the target domain. We extensively study fine-tuning our model on the target dataset from multiple domains, and demonstrate that our model generalizes better than state-of-the-art methods in EM.

cs.LG↗

arXiv2022

StruBERT: Structure-aware BERT for Table Search and Matching

A large amount of information is stored in data tables. Users can search for data tables using a keyword-based query. A table is composed primarily of data values that are organized in rows and columns providing implicit structural information. A table is usually accompanied by secondary information such as the caption, page title, etc., that form the textual information. Understanding the connection between the textual and structural information is an important yet neglected aspect in table retrieval as previous methods treat each source of information independently. In addition, users can search for data tables that are similar to an existing table, and this setting can be seen as a content-based table retrieval. In this paper, we propose StruBERT, a structure-aware BERT model that fuses the textual and structural information of a data table to produce context-aware representations for both textual and tabular content of a data table. StruBERT features are integrated in a new end-to-end neural ranking model to solve three table-related downstream tasks: keyword- and content-based table retrieval, and table similarity. We evaluate our approach using three datasets, and we demonstrate substantial improvements in terms of retrieval and classification metrics over state-of-the-art methods.

cs.IR↗

arXiv2021

Neural ranking models for document retrieval

Ranking models are the main components of information retrieval systems. Several approaches to ranking are based on traditional machine learning algorithms using a set of hand-crafted features. Recently, researchers have leveraged deep learning models in information retrieval. These models are trained end-to-end to extract features from the raw data for ranking tasks, so that they overcome the limitations of hand-crafted features. A variety of deep learning models have been proposed, and each model presents a set of neural network components to extract features that are used for ranking. In this paper, we compare the proposed models in the literature along different dimensions in order to understand the major contributions and limitations of each model. In our discussion of the literature, we analyze the promising neural components, and propose future research directions. We also show the analogy between document retrieval and other retrieval tasks where the items to be ranked are structured documents, answers, images and videos.

cs.IR↗

arXiv2020

Semantic Labeling Using a Deep Contextualized Language Model

Generating schema labels automatically for column values of data tables has many data science applications such as schema matching, and data discovery and linking. For example, automatically extracted tables with missing headers can be filled by the predicted schema labels which significantly minimizes human effort. Furthermore, the predicted labels can reduce the impact of inconsistent names across multiple data tables. Understanding the connection between column values and contextual information is an important yet neglected aspect as previously proposed methods treat each column independently. In this paper, we propose a context-aware semantic labeling method using both the column values and context. Our new method is based on a new setting for semantic labeling, where we sequentially predict labels for an input table with missing headers. We incorporate both the values and context of each data column using the pre-trained contextualized language model, BERT, that has achieved significant improvements in multiple natural language processing tasks. To our knowledge, we are the first to successfully apply BERT to solve the semantic labeling task. We evaluate our approach using two real-world datasets from different domains, and we demonstrate substantial improvements in terms of evaluation metrics over state-of-the-art feature-based methods.

cs.LG↗

arXiv2020

Table Search Using a Deep Contextualized Language Model

Pretrained contextualized language models such as BERT have achieved impressive results on various natural language processing benchmarks. Benefiting from multiple pretraining tasks and large scale training corpora, pretrained models can capture complex syntactic word relations. In this paper, we use the deep contextualized language model BERT for the task of ad hoc table retrieval. We investigate how to encode table content considering the table structure and input length limit of BERT. We also propose an approach that incorporates features from prior literature on table retrieval and jointly trains them with BERT. In experiments on public datasets, we show that our best approach can outperform the previous state-of-the-art method and BERT baselines with a large margin under different evaluation metrics.

cs.IR↗

arXiv2019

PV Power Forecasting Using Weighted Features for Enhanced Ensemble Method

Solar power becomes one of the most promising renewable energy resources in recent years. However, the weather is continuously changing, and this causes a discontinuity of energy generation. PV Power forecasting is a suitable solution to handle sudden disjointedness on energy generation by providing fast dispatching to grid electricity. These methods present a key insight into matchmaking grid electricity and photovoltaic plants. Bootstrap aggregation Ensemble method(Bagging) is classified as one of the most useful machine learning models which are applicable to supervised learning regression tasks. Following this regard, this paper proposes a state-of-art method based on bagging and this method works perfectly for PV power forecasting. The latter had powerful capabilities of tracking the behavior of stochastic problems with good accuracy with the aid of feature importance information. This approach comes to optimize bias/variance using feature weighting vector. Thus, this paper is devoted to present various feature importance techniques for Photovoltaic forecasting parameters. This technique consists of improving the aforementioned ensemble model via contributing the knowledge expertise obtained from features analysis to be directly transformed into the Ensemble model. The proposed model is tested on PV power prediction. Therefore, the benchmarked technique shows an improvement in accuracy in terms of RMSE to 5%.

eess.SP↗

arXiv2019

A Novel Approach Based Deep RNN Using Hybrid NARX-LSTM Model For Solar Power Forecasting

The high variability of weather parameters is making photovoltaic energy generation intermittent and narrowly controllable. Threatened by the sudden discontinuity between the load and the grid, energy management for smart grid systems highly require an accurate PV power forecasting model. In this regard, Nonlinear autoregressive exogenous (NARX) is one of the few potential models that handle time series analysis for long-horizon prediction. This later is efficient and high-performing. However, this model often suffers from the vanishing gradient problem which limits its performances. Thus, this paper discus NARX algorithm for long-range dependencies. However, despite its capabilities, it has been detected that this model has some issues coming especially from the vanishing gradient. For the aim of covering these weaknesses, this study suggests a hybrid technique combining long short-term memory (LSTM) with NARX networks under the umbrella of Evolution of recurrent systems with optimal linear output (EVOLINO). For the sake of illustration, this new approach is applied to PV power forecasting for one year in Australia. The proposed model enhances accuracy. This made the proposed algorithm outperform various benchmarked models.

eess.SP↗

arXiv2019

Enhanced Evolutionary Symbolic Regression Via Genetic Programming for PV Power Forecasting

Solar power becomes one of the most promising renewable energy sources over the years leading up. Nevertheless, the weather is causing periodicity and volatility to photovoltaic (PV) energy production. Thus, Forecasting the PV power is crucial for maintaining sustainability and reliably to grid-connected systems. Anticipating the energy harnessed with prediction models is required to prevent the grid from any damage coming from every slight disturbance. In this direction, various architectures were suggested to predict the ambiguous behavior of meteorological data. Within this vein. Genetic algorithm (GA) presents a robust solution for nonlinear problems. The success of GA presents a source of motivation to scientists and engineers to develop a variety of sub-models that imitate the same Darwinian type-survival of the fittest strategy approach from GA propriety. However, during the training process, the later face an issue with missing the optimal solutions due to the existence of a local minimum. Following that regard, this paper provides an accurate PV power forecasting one month of PV power using a hybrid model combining symbolic regressor via Genetic programming and artificial neural network. The features inputs used in the process are only the solar irradiation and the historical solar power data. The application of the said model on an Australian PV plant of 200 kW offers a low mean absolute error equal to 3.30 and outperforms the state of art models.

eess.SP↗