Related papers: Parallelization of Maximum Entropy POS Tagging for…

Modern scientific discovery increasingly relies on high-performance computing for complex modeling and simulation. A key challenge in improving parallel program performance is efficiently mapping tasks to processors and data to memory, a…

Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For example, existing methods (like ACE or GEPA) can learn system prompts to…

Most languages lack sufficient data for large-scale monolingual pretraining, creating a "data wall." Multilingual pretraining helps but is limited by language imbalance and the "curse of multilinguality." An alternative is to translate…

An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of the back-translations of the target-side monolingual data. The standard back-translation…

This paper introduces a parallel and asynchronous Transformer framework designed for efficient and accurate multilingual lip synchronization in real-time video conferencing systems. The proposed architecture integrates translation, speech…

The growth of the amount of medical image data produced on a daily basis in modern hospitals forces the adaptation of traditional medical image analysis and indexing approaches towards scalable solutions. The number of images and their…

This study proposes a language-agnostic transformer-based POS tagging framework designed for low-resource languages, using Bangla and Hindi as case studies. With only three lines of framework-specific code, the model was adapted from Bangla…

We developed a flexible parallel algorithm for graph summarization based on vertex-centric programming and parameterized message passing. The base algorithm supports infinitely many structural graph summary models defined in a formal…

The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on zero-shot transfer learning and joint training across…

This paper presents TAG, an automatic system to derive optimized DNN training graph and its deployment onto any device topology, for expedited training in device- and topology- heterogeneous ML clusters. We novelly combine both the DNN…

Lexical normalization, the translation of non-canonical data to standard language, has shown to improve the performance of manynatural language processing tasks on social media. Yet, using multiple languages in one utterance, also called…

Relaxation labelling is an optimization technique used in many fields to solve constraint satisfaction problems. The algorithm finds a combination of values for a set of variables such that satisfies -to the maximum possible degree- a set…

We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…

In this paper, we present MasakhaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these languages using the UD (universal dependencies) guidelines.…

Various parallelism, such as data, tensor, and pipeline parallelism, along with memory optimizations like activation checkpointing, redundancy elimination, and offloading, have been proposed to accelerate distributed training for Large…

Multimodal learning on video and text has seen significant progress, particularly in tasks like text-to-video retrieval, video-to-text retrieval, and video captioning. However, most existing methods and datasets focus exclusively on…

We revisit parallel-innermost term rewriting as a model of parallel computation on inductive data structures and provide a corresponding notion of runtime complexity parametric in the size of the start term. We propose automatic techniques…

We propose InDEX, an Indonesian Idiom and Expression dataset for cloze test. The dataset contains 10438 unique sentences for 289 idioms and expressions for which we generate 15 different types of distractors, resulting in a large…

Traditional syntax models typically leverage part-of-speech (POS) information by constructing features from hand-tuned templates. We demonstrate that a better approach is to utilize POS tags as a regularizer of learned representations. We…

We revisit parallel-innermost term rewriting as a model of parallel computation on inductive data structures and provide a corresponding notion of runtime complexity parametric in the size of the start term. We propose automatic techniques…