相关论文: Semi-Automatic Data Annotation, POS Tagging and Mi…

This paper presents a novel approach to fine-tuning the Qwen2-1.5B model for Arabic language processing using Quantized Low-Rank Adaptation (QLoRA) on a system with only 4GB VRAM. We detail the process of adapting this large language model…

We present an algorithm that automatically learns context constraints using statistical decision trees. We then use the acquired constraints in a flexible POS tagger. The tagger is able to use information of any degree: n-grams,…

Retrieval-Augmented Generation (RAG) compensates for the static knowledge limitations of Large Language Models (LLMs) by integrating external knowledge, producing responses with enhanced factual correctness and query-specific…

Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning…

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing the capabilities of large language models. However, existing RAG evaluation predominantly focuses on text retrieval and relies on opaque, end-to-end…

This paper introduces a new learning paradigm called eXtreme Regression (XR) whose objective is to accurately predict the numerical degrees of relevance of an extremely large number of labels to a data point. XR can provide elegant…

Large Language Models (LLMs) have greatly pushed forward advancements in natural language processing, yet their high memory and computational demands hinder practical deployment. Binarization, as an effective compression technique, can…

Parsing the Arabic language is a difficult task given the specificities of this language and given the scarcity of digital resources (grammars and annotated corpora). In this paper, we suggest a method for Arabic parsing based on supervised…

While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation. To address this, we introduce…

Recognizing textual attributes such as bold, italic, underline and strikeout is essential for understanding text semantics, structure, and visual presentation. These attributes highlight key information, making them crucial for document…

Training a Named Entity Recognition (NER) model often involves fixing a taxonomy of entity types. However, requirements evolve and we might need the NER model to recognize additional entity types. A simple approach is to re-annotate entire…

Large language models (LLMs) exhibit strong semantic understanding, yet struggle when user instructions involve ambiguous or conceptually misaligned terms. We propose the Language Graph Model (LGM) to enhance conceptual clarity by…

While FrameNet is widely regarded as a rich resource of semantics in natural language processing, a major criticism concerns its lack of coverage and the relative paucity of its labeled data compared to other commonly used lexical resources…

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past…

This paper introduces SemRAG, an enhanced Retrieval Augmented Generation (RAG) framework that efficiently integrates domain-specific knowledge using semantic chunking and knowledge graphs without extensive fine-tuning. Integrating…

State-of-the-art face recognition (FR) models often experience a significant performance drop when dealing with facial images in surveillance scenarios where images are in low quality and often corrupted with noise. Leveraging facial…

Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque,…

Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still…

A sufficient amount of annotated data is usually required to fine-tune pre-trained language models for downstream tasks. Unfortunately, attaining labeled data can be costly, especially for multiple language varieties and dialects. We…

The ability to understand and generate languages sets human cognition apart from other known life forms'. We study a way of combing two of the most successful routes to meaning of language--statistical language models and symbolic semantics…