Related papers: Giving Text Analytics a Boost

The increasing capabilities of machine learning models, such as vision-language and multimodal language models, are placing growing demands on data in automotive systems engineering, making the quality and relevance of collected data…

Traffic prediction is one of the most significant foundations in Intelligent Transportation Systems (ITS). Traditional traffic prediction methods rely only on historical traffic data to predict traffic trends and face two main challenges.…

As LLM applications grow more complex, developers are increasingly adopting multi-agent architectures to decompose workflows into specialized, collaborative components, introducing structure that constrains agent behavior and exposes useful…

We introduce a simple approach that uses a large language model (LLM) to automatically implement a fully interpretable rule-based data-to-text system in pure Python. Experimental evaluation on the WebNLG dataset showed that such a…

Transformer networks have emerged as the state-of-the-art approach for natural language processing tasks and are gaining popularity in other domains such as computer vision and audio processing. However, the efficient hardware acceleration…

Software transactional memory (STM) allows programmers to easily implement concurrent data structures. STMs simplify atomicity. Recent STMs can achieve good performance for some workloads but they have some limitations. In particular, STMs…

Data communication in cloud-based distributed stream data analytics often involves a collection of parallel and pipelined TCP flows. As the standard TCP congestion control mechanism is designed for achieving "fairness" among competing flows…

Transformer-based speech enhancement models yield impressive results. However, their heterogeneous and complex structure restricts model compression potential, resulting in greater complexity and reduced hardware efficiency. Additionally,…

State-of-the-art deep learning systems rely on iterative distributed training to tackle the increasing complexity of models and input data. The iteration time in these communication-heavy systems depends on the computation time,…

Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks suffer from a fundamental limitation: they perform…

Large Language Models (LLMs) have emerged as powerful tools for natural language processing tasks, revolutionizing the field with their ability to understand and generate human-like text. As the demand for more sophisticated LLMs continues…

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on…

Text classification is fundamental in Natural Language Processing (NLP), and the advent of Large Language Models (LLMs) has revolutionized the field. This paper introduces an adaptable and reliable text classification paradigm, which…

Data analysis and monitoring of road networks in terms of reliability and performance are valuable but hard to achieve, especially when the analytical information has to be available to decision makers on time. The gathering and analysis of…

The previous state-of-the-art (SOTA) method achieved a remarkable execution accuracy on the Spider dataset, which is one of the largest and most diverse datasets in the Text-to-SQL domain. However, during our reproduction of the business…

In this paper we analyze the performance issues involved in the generation of auto- mated traffic reports for large IT infrastructures. Such reports allows the IT manager to proactively detect possible abnormal situations and roll out the…

In this paper we propose and implement novel techniques for performance evaluation of web traffic (response time, response code, etc.), with no reassembly of the underlying TCP connection, which severely restricts the traffic analysis…

Parallel dataflow systems are a central part of most analytic pipelines for big data. The iterative nature of many analysis and machine learning algorithms, however, is still a challenge for current systems. While certain types of bulk…

While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i)…

This paper presents a novel data augmentation technique for text-to-speech (TTS), that allows to generate new (text, audio) training examples without requiring any additional data. Our goal is to increase diversity of text conditionings…