相关论文: Improving Vietnamese Legal Document Retrieval usin…

Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems. However, the evaluation of neural IR has so far been limited to…

Pre-trained multimodal models have achieved significant success in retrieval-based question answering. However, current multimodal retrieval question-answering models face two main challenges. Firstly, utilizing compressed evidence features…

Legal texts routinely use concepts that are difficult to understand. Lawyers elaborate on the meaning of such concepts by, among other things, carefully investigating how have they been used in past. Finding text snippets that mention a…

In tackling the challenge of Multi-Document Summarization (MDS), numerous methods have been proposed, spanning both extractive and abstractive summarization techniques. However, each approach has its own limitations, making it less…

Visual program synthesis is a promising approach to exploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-shot prompting with frozen LLMs to synthesize visual programs.…

Training data plays a crucial role in Large Language Models (LLM) scaling, yet high quality data is of limited supply. Synthetic data techniques offer a potential path toward sidestepping these limitations. We conduct a large-scale…

This paper presents a simple yet efficient ensemble learning framework for Vietnamese scene text spotting. Leveraging the power of ensemble learning, which combines multiple models to yield more accurate predictions, our approach aims to…

The contextual word embedding model, BERT, has proved its ability on downstream tasks with limited quantities of annotated data. BERT and its variants help to reduce the burden of complex annotation work in many interdisciplinary research…

Language models can be viewed as functions that embed text into Euclidean space, where the quality of the embedding vectors directly determines model performance, training such neural networks involves various uncertainties. This paper…

Bidirectional Encoder Representations from Transformers (BERT) have shown to be a promising way to dramatically improve the performance across various Natural Language Processing tasks [Devlin et al., 2019]. Meanwhile, progress made over…

Machine translation for Vietnamese-English in the medical domain is still an under-explored research area. In this paper, we introduce MedEV -- a high-quality Vietnamese-English parallel dataset constructed specifically for the medical…

Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space. However, the limited labeled multimodal data often hinders…

Recent progress in developing general purpose text embedders has been driven by training on ever-growing corpora of synthetic LLM-generated data. Nonetheless, no publicly available synthetic dataset exists, posing a barrier to studying its…

Accurate classification of clinical text often requires fine-tuning pre-trained language models, a process that is costly and time-consuming due to the need for high-quality data and expert annotators. Synthetic data generation offers an…

Encoder-decoder Large Language Models (LLMs), such as BERT and RoBERTa, require that all categories in an annotation task be sufficiently represented in the training data for optimal performance. However, it is often difficult to find…

Training effective dense retrieval models typically relies on hard negative (HN) examples mined from large document corpora using methods such as BM25 or cross-encoders, which require full corpus access and expensive index construction. We…

Recently, the retrieval models based on dense representations have been gradually applied in the first stage of the document retrieval tasks, showing better performance than traditional sparse vector space models. To obtain high efficiency,…

Synthetic data generation has become an increasingly popular way of training models without the need for large, manually labeled datasets. For tasks like text embedding, synthetic data offers diverse and scalable training examples,…

In this paper, the authors propose TriBERTa, a supervised entity resolution system that utilizes a pre-trained large language model and a triplet loss function to learn representations for entity matching. The system consists of two steps:…

Large Language Models (LLMs) with extended context windows promise direct reasoning over long documents, reducing the need for chunking or retrieval. Constructing annotated resources for training and evaluation, however, remains costly.…