English
Related papers

Related papers: Synthetic continued pretraining

200 papers

In this work, we explore massive pre-training on synthetic word images for enhancing the performance on four benchmark downstream handwriting analysis tasks. To this end, we build a large synthetic dataset of word images rendered in several…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Vittorio Pippi , Silvia Cascianelli , Lorenzo Baraldi , Rita Cucchiara

With the rapid increase in the volume of dialogue data from daily life, there is a growing demand for dialogue summarization. Unfortunately, training a large summarization model is generally infeasible due to the inadequacy of dialogue data…

Computation and Language · Computer Science 2021-09-14 Yicheng Zou , Bolin Zhu , Xingwu Hu , Tao Gui , Qi Zhang

Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While there have been some attempts at utilizing syntactic context…

Computation and Language · Computer Science 2019-07-23 Shikhar Vashishth , Manik Bhandari , Prateek Yadav , Piyush Rai , Chiranjib Bhattacharyya , Partha Talukdar

Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Zhiyue Liu , Jinyuan Liu , Fanrong Ma

Information-seeking conversation, which aims to help users gather information through conversation, has achieved great progress in recent years. However, the research is still stymied by the scarcity of training data. To alleviate this…

Computation and Language · Computer Science 2023-08-15 Siheng Li , Cheng Yang , Yichun Yin , Xinyu Zhu , Zesen Cheng , Lifeng Shang , Xin Jiang , Qun Liu , Yujiu Yang

State-of-the-art face recognition networks are often computationally expensive and cannot be used for mobile applications. Training lightweight face recognition models also requires large identity-labeled datasets. Meanwhile, there are…

Computer Vision and Pattern Recognition · Computer Science 2023-08-30 Hatef Otroshi Shahreza , Anjith George , Sébastien Marcel

In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…

We introduce a novel paraphrastic augmentation strategy based on sentence-level lexically constrained paraphrasing and discriminative span alignment. Our approach allows for the large-scale expansion of existing resources, or the rapid…

Computation and Language · Computer Science 2020-07-02 Ryan Culkin , J. Edward Hu , Elias Stengel-Eskin , Guanghui Qin , Benjamin Van Durme

We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. We model retrieval decisions as…

Computation and Language · Computer Science 2021-12-07 Devendra Singh Sachan , Siva Reddy , William Hamilton , Chris Dyer , Dani Yogatama

Many sensitive domains -- such as the clinical domain -- lack widely available datasets due to privacy risks. The increasing generative capabilities of large language models (LLMs) have made synthetic datasets a viable path forward. In this…

Computation and Language · Computer Science 2025-06-03 Thomas Vakili , Aron Henriksson , Hercules Dalianis

Retrieval Augmented Generation (RAG) is a technique used to augment Large Language Models (LLMs) with contextually relevant, time-critical, or domain-specific information without altering the underlying model parameters. However,…

Information Retrieval · Computer Science 2024-08-20 Laurent Mombaerts , Terry Ding , Adi Banerjee , Florian Felice , Jonathan Taws , Tarik Borogovac

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful…

Computation and Language · Computer Science 2024-10-28 Zhuoqun Li , Xuanang Chen , Haiyang Yu , Hongyu Lin , Yaojie Lu , Qiaoyu Tang , Fei Huang , Xianpei Han , Le Sun , Yongbin Li

Recent advances have indicated the strengths of self-supervised pre-training for improving representation learning on downstream tasks. Existing works often utilize self-supervised pre-trained models by fine-tuning on downstream tasks.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Yuchen Ma , Yanbei Chen , Zeynep Akata

The construction of high-quality datasets is a cornerstone of modern text-to-speech (TTS) systems. However, the increasing scale of available data poses significant challenges, including storage constraints. To address these issues, we…

Sound · Computer Science 2025-07-14 Kentaro Seki , Shinnosuke Takamichi , Takaaki Saeki , Hiroshi Saruwatari

Language models (LMs) increasingly drive real-world applications that require world knowledge. However, the internal processes through which models turn data into representations of knowledge and beliefs about the world, are poorly…

Computation and Language · Computer Science 2025-09-04 Daniela Gottesman , Alon Gilae-Dotan , Ido Cohen , Yoav Gur-Arieh , Marius Mosbach , Ori Yoran , Mor Geva

Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual…

Machine Learning · Statistics 2018-12-10 Alexander J. Ratner , Henry R. Ehrenberg , Zeshan Hussain , Jared Dunnmon , Christopher Ré

In this paper, we present the ``joint pre-training and local re-training'' framework for learning and applying multi-source knowledge graph (KG) embeddings. We are motivated by the fact that different KGs contain complementary information…

Computation and Language · Computer Science 2023-06-06 Zequn Sun , Jiacheng Huang , Jinghao Lin , Xiaozhou Xu , Qijin Chen , Wei Hu

Ontologies are pivotal for structuring knowledge bases to enhance question answering (QA) systems powered by Large Language Models (LLMs). However, traditional ontology creation relies on manual efforts by domain experts, a process that is…

Artificial Intelligence · Computer Science 2025-06-03 Yash Tiwari , Owais Ahmad Lone , Mayukha Pal

With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthetic data is not trivial due to the gap between the synthetic…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-25 Ting-Yao Hu , Mohammadreza Armandpour , Ashish Shrivastava , Jen-Hao Rick Chang , Hema Koppula , Oncel Tuzel

Large language models (LLMs) encode a large amount of world knowledge. However, as such knowledge is frozen at the time of model training, the models become static and limited by the training data at that time. In order to further improve…

Computation and Language · Computer Science 2023-05-25 Junyi Li , Tianyi Tang , Wayne Xin Zhao , Jingyuan Wang , Jian-Yun Nie , Ji-Rong Wen
‹ Prev 1 8 9 10 Next ›