Search Results for author:
Found 15 papers, 2 papers with code
基于注意力的蒙古语说话人特征提取方法(Attention based Mongolian Speaker Feature Extraction)
“说话人特征提取模型提取到的说话人特征之间区分性低, 使得蒙古语声学模型无法学习到区分性信息, 导致模型无法适应不同说话人。提出一种基于注意力的说话人自适应方法, 方法引入神经图灵机进行自适应, 增加记忆模块存放说话人特征, 采用注意力机制计算记忆模块中说话人特征与当前语音说话人特征的相似权重矩阵, 通过权重矩阵重新组合成说话人特征s-vector, 进而提高说话人特征之间的区分性。在IMUT-MCT数据集上, 进行说话人特征提取方法的消融实验、模型自适应实验和案例分析。实验结果表明, 对比不同说话人特征s-vector、i-vector与d-vector, s-vector比其他两种方法的SER和WER分别降低4. 96%、1. 08%;在不同的蒙古语声学模型上进行比较, 提出的方法相对于基线均有性能提升。”
面向 Transformer 模型的蒙古语语音识别词特征编码方法(Researching of the Mongolian word encoding method based on Transformer Mongolian speech recognition)
“针对 Transformer 模型在蒙古语语音识别任务中无法学习到带有控制符的蒙古语词和语音之间的对应关系, 造成模型对蒙古语的不适应问题。提出一种面向 Transformer 模型的蒙古语词编码方法, 方法使用蒙古语字母特征与词特征进行混合编码, 通过结合蒙古语字母信息使 Transformer 模型能够区分带有控制符的蒙古语词, 学习到蒙古语词与语音之间的对应关系。在 IMUT-MC 数据集上, 构建 Transformer 模型并进行了词特征编码方法的消融实验和对比实验。消融实验结果表明, 词特征编码方法在 HWER、WER、SER 上分别降低了 23. 4%、6. 9%、2. 6%;对比实验结果表明, 词特征编码方法领先于所有方法, HWER 和 WER 分别达到 11. 8%、19. 8%。”
BuDDIE: A Business Document Dataset for Multi-task Information Extraction
Several datasets exist for research on specific tasks of VRDU such as document classification (DC), key entity extraction (KEE), entity linking, visual question answering (VQA), inter alia.
TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing
Visually Rich Form Understanding (VRFU) poses a complex research problem due to the documents' highly structured nature and yet highly variable style and content.
DocGraphLM: Documental Graph Language Model for Information Extraction
Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts.
DocLLM: A layout-aware generative language model for multimodal document understanding
Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalities.
Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams
Large Language Models (LLMs) have demonstrated remarkable performance on a wide range of Natural Language Processing (NLP) tasks, often matching or even beating state-of-the-art task-specific models.
Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation
In this paper, we propose an adaptive two-stage knowledge distillation method consisting of hidden layer learning and output layer learning.
Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving
Reinforcement learning (RL) is an effective approach to motion planning in autonomous driving, where an optimal driving policy can be automatically learned using the interaction data with the environment.
Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks
The most recent large language models(LLMs) such as ChatGPT and GPT-4 have shown exceptional capabilities of generalist models, achieving state-of-the-art performance on a wide range of NLP tasks with little or no adaptation.
Ranked #1 on
Question Answering
on ConvFinQA
ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering
With the recent advance in large pre-trained language models, researchers have achieved record performances in NLP tasks that mostly focus on language pattern matching.
Ranked #2 on
Question Answering
on ConvFinQA
Towards Earnings Call and Stock Price Movement
Earnings calls are hosted by management of public companies to discuss the company's financial performance with analysts and investors.
SPot: A tool for identifying operating segments in financial tables
In this paper we present SPot, an automated tool for detecting operating segments and their related performance indicators from earnings reports.
Empirical Study on Detecting Controversy in Social Media
Companies and financial investors are paying increasing attention to social consciousness in developing their corporate strategies and making investment decisions to support a sustainable economy for the future.
The USTC-NEL Speech Translation system at IWSLT 2018
This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018.
