Related papers: E2E Refined Dataset
End-to-end (E2E) training, optimizing the entire model through error backpropagation, fundamentally supports the advancements of deep learning. Despite its high performance, E2E training faces the problems of memory consumption, parallel…
Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images,…
Recently, end-to-end mispronunciation detection and diagnosis (MD&D) systems has become a popular alternative to greatly simplify the model-building process of conventional hybrid DNN-HMM systems by representing complicated modules with a…
Tokenization is fundamental to how language models represent and process text, yet the behavior of widely used BPE tokenizers has received far less study than model architectures and training. In this paper, we investigate intermediate…
Synthetic translations have been used for a wide range of NLP tasks primarily as a means of data augmentation. This work explores, instead, how synthetic translations can be used to revise potentially imperfect reference translations in…
End-2-end (E2E) models have become increasingly popular in some ASR tasks because of their performance and advantages. These E2E models directly approximate the posterior distribution of tokens given the acoustic inputs. Consequently, the…
Text-to-image diffusion models have achieved remarkable progress in recent years. However, training models for high-resolution image generation remains challenging, particularly when training data and computational resources are limited. In…
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…
Pre-training state-of-the-art large language models (LLMs) requires vast amounts of clean and diverse text data. While the open development of large high-quality English pre-training datasets has seen substantial recent progress, training…
This paper presents the PyEB tool, a Python implementation of the Event-B refinement calculus. The PyEB tool takes a Python program and generates several proof obligations that are then passed into the Z3 solver for verification purposes.…
Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object…
Paraphrase generation, a.k.a. paraphrasing, is a common and important task in natural language processing. Emotional paraphrasing, which changes the emotion embodied in a piece of text while preserving its meaning, has many potential…
The task of Text-to-SQL enables anyone to retrieve information from SQL databases using natural language. While this task has made substantial progress, the two primary evaluation metrics - Execution Accuracy (EXE) and Exact Set Matching…
Despite major advances in machine translation (MT) in recent years, progress remains limited for many low-resource languages that lack large-scale training data and linguistic resources. In this paper, we introduce \dsname, a novel…
End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…
With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…
Event extraction aims to recognize pre-defined event triggers and arguments from texts, which suffer from the lack of high-quality annotations. In most NLP applications, involving a large scale of synthetic training data is a practical and…
This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. The model is trained in a contrastive manner with weak supervision signals from our curated large-scale text pair dataset…
Leveraging visual priors from pre-trained text-to-image (T2I) generative models has shown success in dense prediction. However, dense prediction is inherently an image-to-image task, suggesting that image editing models, rather than T2I…
Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled…