首页/论文/2004.02002

arXiv 2004.020022020-04cs.CLcs.AI

Talk to Papers: Bringing Neural Question Answering to Academic Search

SOCO AI

Tianchang Zhao, Kyusong Lee

备注：: demo paper accepted at ACL 2020

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

We introduce Talk to Papers, which exploits the recent open-domain question answering (QA) techniques to improve the current experience of academic search. It's designed to enable researchers to use natural language queries to find precise answers and extract insights from a massive amount of academic papers. We present a large improvement over classic search engine baseline on several standard QA datasets and provide the community a collaborative data collection tool to curate the first natural language processing research QA dataset via a community effort.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

We Need to Talk About Data: The Importance of Data Readiness in Natural Language Processing

RISE, Research Institutes of Sweden（瑞典RISE研究院（瑞典国家研究院））；Gavagai（Gavagai公司）；AI Sweden（AI Sweden机构）

In this paper, we identify the state of data as being an important reason for failure in applied Natural Language Processing (NLP) projects. We argue that there is a gap between academic research in NLP and its application to problems outside academia, and that this gap is rooted in poor mutual understanding between academic researchers and their non-academic peers who seek to apply research results to their operations. To foster transfer of research results from academia to non-academic settings, and the corresponding influx of requirements back to academia, we propose a method for improving …

2021-10-11cs.AIcs.CLcs.CY

What Would a Teacher Do? Predicting Future Talk Moves

University of Colorado Boulder（科罗拉多大学博尔德分校）

Recent advances in natural language processing (NLP) have the ability to transform how classroom learning takes place. Combined with the increasing integration of technology in today's classrooms, NLP systems leveraging question answering and dialog processing techniques can serve as private tutors or participants in classroom discussions to increase student engagement and learning. To progress towards this goal, we use the classroom discourse framework of academically productive talk (APT) to learn strategies that make for the best learning experience. In this paper, we introduce a new task, …

2021-06-09cs.CL

大语言模型能够根据多样化指令在多说话人场景中转录语音

Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions

The Chinese University of Hong Kong（香港中文大学）

本研究提出MT-LLM系统，利用WavLM和Whisper编码器提取语音表示，并通过LoRA微调LLM，使其能根据多样化指令在多说话人环境中进行语音转录，在鸡尾酒会场景中表现优异。

2025-04-02cs.AIcs.CLcs.SD

大语言模型时代的文档智能：综述

Document Intelligence in the Era of Large Language Models: A Survey

SAP, Singapore（新加坡SAP）

本文综述大语言模型对文档智能的变革，涵盖多模态、多语言及检索增强进展，并提出智能体与文档专用基础模型等未来方向。

2025-10-15cs.AIcs.CL

从教材到谈bot：面向高等教育的希腊语基于检索增强生成的聊天机器人案例研究

From Textbook to Talkbot: A Case Study of a Greek-Language RAG-Based Chatbot in Higher Education

International Hellenic University（国际希腊大学）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）

本研究开发了一个基于RAG框架的希腊语AI聊天机器人，用于高等教育中的教学支持，旨在提升教育实践和AI技术在语言教育中的应用。

2025-12-23cs.AIcs.CLcs.CY

如果来源能说话：评估大型语言模型在历史研究辅助中的作用

If the Sources Could Talk: Evaluating Large Language Models for Research Assistance in History

Concordia University（康考迪亚大学）；University of British Columbia（不列颠哥伦比亚大学）

该研究通过向量嵌入增强大型语言模型，使其能辅助历史学家分析定制语料库，在问答和数据提取任务上优于传统搜索界面，且可处理训练数据之外的档案。

2023-10-16cs.AIcs.IR

更多相关论文收起更多论文

Bringing Stories Alive: Generating Interactive Fiction Worlds

Georgia Institute of Technology（佐治亚理工学院）

World building forms the foundation of any task that requires narrative intelligence. In this work, we focus on procedurally generating interactive fiction worlds---text-based worlds that players "see" and "talk to" using natural language. Generating these worlds requires referencing everyday and thematic commonsense priors in addition to being semantically consistent, interesting, and coherent throughout. Using existing story plots as inspiration, we present a method that first extracts a partial knowledge graph encoding basic information regarding world structure such as locations and object…

2020-01-28cs.AIcs.CL

基于大语言模型的特征型AI智能体

Characteristic AI Agents via Large Language Models

School of Computer Science and Technology, Shandong University（山东大学计算机科学与技术学院）

本研究针对大语言模型构建特征型AI智能体的研究空白，创建了包含数据集、技术和评估指标的基准，并构建了Character100数据集，通过全面评估揭示了提升LLMs角色扮演能力的潜在方向。

2024-03-19cs.AIcs.CL

通过课堂教学话语增强数学辅导中的对话动作分析

Enhancing Talk Moves Analysis in Mathematics Tutoring through Classroom Teaching Discourse

School of Computer Science, University of Oklahoma（俄克拉荷马大学计算机科学学院）；Institute of Cognitive Science, University of Colorado Boulder（科罗拉多大学博尔德分校认知科学研究所）

本研究提出紧凑数据集SAGA22，利用课堂数据预训练及上下文与说话者信息，提升数学辅导中对话动作分析的模型性能。

2024-12-18cs.AIcs.CLcs.HC

Talk2Nav: Long-Range Vision-and-Language Navigation with Dual Attention and Spatial Memory

ETH Zurich（苏黎世联邦理工学院）；K.U Leuven（鲁汶大学）

The role of robots in society keeps expanding, bringing with it the necessity of interacting and communicating with humans. In order to keep such interaction intuitive, we provide automatic wayfinding based on verbal navigational instructions. Our first contribution is the creation of a large-scale dataset with verbal navigation instructions. To this end, we have developed an interactive visual navigation environment based on Google Street View; we further design an annotation method to highlight mined anchor landmarks and local directions between them in order to help annotators formulate typ…

2020-10-22cs.CLcs.CVcs.RO

Mini-DALLE3：通过提示大型语言模型实现交互式文生图

Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models

Shanghai AI Laboratory（上海人工智能实验室）；CUHK（香港中文大学）；Beijing Institute of Technology（北京理工大学）；Tsinghua University（清华大学）

本文提出一种通过提示技术和现成T2I模型增强LLM的简单方法，实现无需训练的交互式文生图（iT2I），支持图像生成、编辑与问答，并在多种LLM上验证了其有效性和低代价。

2023-10-12cs.AI

Open-TI：基于增强语言模型的开放交通智能

Open-TI: Open Traffic Intelligence with Augmented Language Model

School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）；School of Sustainable Engineering and the Built Environment, Arizona State University（亚利桑那州立大学可持续工程与建筑环境学院）

本文提出 Open-TI，通过增强 LLM 调用交通分析工具，实现从地图获取、仿真执行到 TSC 训练与需求优化的端到端交通智能，并设计与 ChatZero 的智能体通信机制。

2024-12-04cs.AI

Mini-Omni：语言模型可以在流式思考的同时听和说

Mini-Omni: Language Models Can Hear, Talk While Thinking in Streaming

Inspirai（因思派科技）；Tsinghua University（清华大学）

本文提出Mini-Omni，首个开源端到端实时语音交互模型，通过文本指导语音生成和批量并行推理实现流式对话，并引入VoiceAssistant-400K数据集，以最小退化保留语言能力。

2024-11-05cs.AIcs.CLcs.HC

Loquacious Set：供研究与商业使用的25,000小时转录且多样化的英语语音识别数据

Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use

AI Center Cambridge（剑桥人工智能中心）；Samsung（三星）

针对现有ASR数据集在许可限制、数据质量或规模上的不足，本研究提出包含25,000小时可商用英语语音的Loquacious Set，涵盖多样口音与语音类型，供学术界与工业界在真实场景中构建ASR系统。

2025-05-27cs.CLcs.SDeess.AS