Related papers: Parallelization of Maximum Entropy POS Tagging for…

The parallelism of Transformer-based models comes at the cost of their input max-length. Some studies proposed methods to overcome this limitation, but none of them reported the effectiveness of summarization as an alternative. In this…

Part-of-Speech (POS) tagging is an old and fundamental task in natural language processing. While supervised POS taggers have shown promising accuracy, it is not always feasible to use supervised methods due to lack of labeled data. In this…

Question Answering (QA) has seen significant improvements with the advancement of machine learning models, further studies enhanced this question answering system by retrieving external information, called Retrieval-Augmented Generation…

In a cloud computing job with many parallel tasks, the tasks on the slowest machines (straggling tasks) become the bottleneck in the job completion. Computing frameworks such as MapReduce and Spark tackle this by replicating the straggling…

Modern complex software systems produce a large amount of execution data, often stored in logs. These logs can be analyzed using trace checking techniques to check whether the system complies with its requirements specifications. Often…

We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. More precisely, we improve the translation from a resource-poor source…

As access to high-quality, domain-specific data grows increasingly scarce, multi-epoch training has become a practical strategy for adapting large language models (LLMs). However, autoregressive models often suffer from performance…

We report our development of a simple but fast and efficient inductive unsupervised semantic tagger for Chinese words. A POS hand-tagged corpus of 348,000 words is used. The corpus is being tagged in two steps. First, possible semantic tags…

Long context training is crucial for LLM's context extension. Existing schemes, such as sequence parallelism, incur substantial communication overhead. Pipeline parallelism (PP) reduces this cost, but its effectiveness hinges on…

This paper presents the first benchmark for the task of automatic part-of-speech (POS) tagging for the Tajik language. Despite the existence of multilingual language models demonstrating high effectiveness for many of the world's languages,…

We present a new method for analyzing the running time of parallel evolutionary algorithms with spatially structured populations. Based on the fitness-level method, it yields upper bounds on the expected parallel running time. This allows…

Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy Method (CEM), can yield compelling results even in high-dimensional control tasks and sparse-reward environments. However, their sampling inefficiency…

Automatic speech recognition systems have achieved remarkable performance on fluent speech but continue to degrade significantly when processing stuttered speech, a limitation that is particularly acute for low-resource languages like…

Huge neural network models have shown unprecedented performance in real-world applications. However, due to memory constraints, model parallelism must be utilized to host large models that would otherwise not fit into the memory of a single…

MapReduce is a popular programming paradigm for developing large-scale, data-intensive computation. Many frameworks that implement this paradigm have recently been developed. To leverage these frameworks, however, developers must become…

Regular expression matching is essential for many applications, such as finding patterns in text, exploring substrings in large DNA sequences, or lexical analysis. However, sequential regular expression matching may be time-prohibitive for…

This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…

A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through…

Pretraining large language models (LLMs) with next-token prediction has led to remarkable advances, yet the context-dependent nature of token embeddings in such models results in high intra-class variance and inter-class similarity, thus…

Part-of-speech (POS) tagging is considered as one of the basic but necessary tools which are required for many Natural Language Processing (NLP) applications such as word sense disambiguation, information retrieval, information processing,…