CAREER: Using Fiction to Improve Real-World Information Systems
职业:利用小说来改进现实世界的信息系统
基本信息
- 批准号:1942591
- 负责人:
- 金额:$ 45万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2020
- 资助国家:美国
- 起止时间:2020-08-01 至 2025-07-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
At a high level, this project aims to design computational methods to reason about the world of fiction, and, in turn, learn from fiction to inform the design of systems in the real world. While much work in artificial intelligence learns about the world from relatively short factual sources like news and Wikipedia, fiction offers a range of affordances for improving existing information systems and innovating new applications altogether. Unlike factual sources like news, fiction captures emotion, everyday action and commonsense, offering a vast source of information to bootstrap knowledge bases that can power question answering systems, conversational agents, and the next generation of artificial intelligence. This project will improve the performance of natural language understanding on fiction as a domain, and use it to explore two case studies: inferring the structure of everyday events in people's lives, including the relation between macro-level events (such as eating breakfast) and low-level micro-events (sitting down at the table, pouring another cup of coffee, putting the dishes in the sink); and learning the relationship between observed actions depicted in text and the broad-coverage mental attitude (such as joy, sadness, and surprise) of their agents. This project aims to draw in students and researchers in the social sciences and humanities, who have historically been underrepresented in computing. While the technical research carried out under this project directly speaks to how expertise in the social sciences and humanities can inform the computational design of information systems, the primary educational plan under this award will investigate one fundamental question: how to enable students outside STEM fields to learn and improve their skills in natural language processing, machine learning and data science. This work will engage researchers in the humanities and social sciences in technical research, teaching skills to students without technical backgrounds, and translating advances in computational methodology to advances in domain knowledge. The fundamental work in this project aims to bridge the gap between computation and the humanities and social sciences by providing two case studies of how learning from a depicted world in fiction can improve systems that reason about the real world. This is a new frontier that can not only teach us about the limitations of current systems for textual entailment and sentiment analysis, but can also open up new areas of research at this intersection. This work will make progress on two tasks enabled by fiction: inferring the sequential and hierarchical order of commonplace actions, in which a single macro-event is comprised of several micro-events, and inferring the latent attitudes of people mentioned in text given observations of their actions. Both case studies draw on fiction as a source of knowledge, and require the development of computational models optimized to bridge the gap between fiction and reality. Concretely, this work will result in the publication of a new dataset of contemporary fiction, labeled for entities and coreference between them (which has the potential to yield a new state of the art for nested entity recognition and coreference resolution for this domain), a knowledge base of everyday actions extracted from fiction, open-source software for modeling hierarchical events and learning mental attitudes from observed actions, and publications at academic venues detailing the methodologies created under the scope of this project.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
在高层次上,该项目旨在设计计算方法来推理小说世界,反过来,从小说中学习,以告知真实的世界中的系统设计。虽然人工智能领域的许多工作都是从相对较短的事实来源(如新闻和维基百科)中了解世界,但小说为改善现有信息系统和创新新应用提供了一系列启示。与新闻等事实来源不同,小说捕捉情感,日常行动和常识,提供了大量的信息来源来引导知识库,这些知识库可以为问答系统,会话代理和下一代人工智能提供动力。本项目将提高自然语言理解在小说领域的表现,并利用它来探索两个案例研究:推断人们生活中日常事件的结构,包括宏观事件之间的关系(比如吃早餐)和低层次的微事件(在桌旁坐下,再倒一杯咖啡,把盘子放进水槽);以及学习文本中描述的观察到的动作与其代理人的广泛心理态度(如喜悦,悲伤和惊讶)之间的关系。该项目旨在吸引社会科学和人文科学的学生和研究人员,他们在历史上在计算方面的代表性不足。虽然该项目下进行的技术研究直接说明了社会科学和人文科学的专业知识如何为信息系统的计算设计提供信息,但该奖项下的主要教育计划将研究一个基本问题:如何使STEM领域以外的学生学习和提高他们在自然语言处理,机器学习和数据科学方面的技能。这项工作将使人文和社会科学的研究人员参与技术研究,向没有技术背景的学生教授技能,并将计算方法的进步转化为领域知识的进步。这个项目的基础工作旨在通过提供两个案例研究来弥合计算与人文和社会科学之间的差距,研究如何从小说中描绘的世界中学习,以改进对真实的世界进行推理的系统。这是一个新的前沿,不仅可以告诉我们当前文本蕴涵和情感分析系统的局限性,而且还可以在这个交叉点上开辟新的研究领域。这项工作将在小说实现的两个任务上取得进展:推断普通行动的顺序和层次顺序,其中一个单一的宏观事件由几个微观事件组成,并推断文本中提到的人的潜在态度,观察他们的行动。这两个案例研究都将虚构作为知识的来源,并需要开发优化的计算模型,以弥合虚构与现实之间的差距。具体地说,这项工作将导致出版一个新的当代小说数据集,标记为实体和它们之间的共指(这有可能为该领域的嵌套实体识别和共指消解产生新的技术水平),从小说中提取的日常行为的知识库,用于建模分层事件和从观察到的行为中学习心理态度的开源软件,该奖项反映了NSF的法定使命,并通过使用基金会的知识价值和更广泛的影响审查标准进行评估,被认为值得支持。
项目成果
期刊论文数量(8)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4
说吧,记忆:ChatGPT/GPT-4 已知书籍考古学
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Chang, Kent K.;Cramer, Mackenzie;Soni, Sandeep;Bamman, David
- 通讯作者:Bamman, David
Dramatic Conversation Disentanglement
- DOI:10.48550/arxiv.2305.16648
- 发表时间:2023-05
- 期刊:
- 影响因子:0
- 作者:Kent K. Chang;Danica Chen;David Bamman
- 通讯作者:Kent K. Chang;Danica Chen;David Bamman
Discovering Differences in the Representation of People using Contextualized Semantic Axes
使用情境化语义轴发现人们表征的差异
- DOI:
- 发表时间:2022
- 期刊:
- 影响因子:0
- 作者:Lucy, Li;Tadimeti, Divya;Bamman, David
- 通讯作者:Bamman, David
Measuring Information Propagation in Literary Social Networks
- DOI:10.18653/v1/2020.emnlp-main.47
- 发表时间:2020-04
- 期刊:
- 影响因子:0
- 作者:Matthew Sims;David Bamman
- 通讯作者:Matthew Sims;David Bamman
Narrative Theory for Computational Narrative Understanding
- DOI:10.18653/v1/2021.emnlp-main.26
- 发表时间:2021
- 期刊:
- 影响因子:0
- 作者:Andrew Piper;R. So;David Bamman
- 通讯作者:Andrew Piper;R. So;David Bamman
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
David Bamman其他文献
Discovering Multilingual Text Reuse in Literary Texts
发现文学文本中的多语言文本重用
- DOI:
- 发表时间:
2012 - 期刊:
- 影响因子:0
- 作者:
David Bamman - 通讯作者:
David Bamman
Natural Language Processing for the Long Tail
- DOI:
- 发表时间:
2017 - 期刊:
- 影响因子:0
- 作者:
David Bamman - 通讯作者:
David Bamman
Improving OCR Accuracy for Classical Critical Editions
提高 Classic Critical 版本的 OCR 准确性
- DOI:
- 发表时间:
2009 - 期刊:
- 影响因子:0
- 作者:
Federico Boschetti;Matteo Romanello;Alison Babeu;David Bamman;G. Crane - 通讯作者:
G. Crane
The Logic and Discovery of Textual Allusion
典故的逻辑与发现
- DOI:
- 发表时间:
2008 - 期刊:
- 影响因子:0
- 作者:
David Bamman;G. Crane - 通讯作者:
G. Crane
Extracting two thousand years of latin from a million book library
从百万图书库中提取两千多年的拉丁语
- DOI:
10.1145/2160165.2160167 - 发表时间:
2012 - 期刊:
- 影响因子:0
- 作者:
David Bamman;David A. Smith - 通讯作者:
David A. Smith
David Bamman的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('David Bamman', 18)}}的其他基金
III: Small: Collaborative Research: Building Subjective Knowledge Bases by Modeling Viewpoints
III:小:协作研究:通过建模观点构建主观知识库
- 批准号:
1813470 - 财政年份:2018
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
EXP: Local Ground: A Contextually Grounded Approach for Learning Data Science Skills
EXP:本地基础:学习数据科学技能的基于上下文的方法
- 批准号:
1319849 - 财政年份:2013
- 资助金额:
$ 45万 - 项目类别:
Standard Grant
相似国自然基金
Molecular Interaction Reconstruction of Rheumatoid Arthritis Therapies Using Clinical Data
- 批准号:31070748
- 批准年份:2010
- 资助金额:34.0 万元
- 项目类别:面上项目
相似海外基金
Developing a 3D printed skin model using a Dextran - Collagen hydrogel to analyse the cellular and epigenetic effects of interleukin-17 inhibitors in
使用右旋糖酐-胶原蛋白水凝胶开发 3D 打印皮肤模型,以分析白细胞介素 17 抑制剂的细胞和表观遗传效应
- 批准号:
2890513 - 财政年份:2027
- 资助金额:
$ 45万 - 项目类别:
Studentship
Impact of Urban Environmental Factors on Momentary Subjective Wellbeing (SWB) using Smartphone-Based Experience Sampling Methods
使用基于智能手机的体验采样方法研究城市环境因素对瞬时主观幸福感 (SWB) 的影响
- 批准号:
2750689 - 财政年份:2025
- 资助金额:
$ 45万 - 项目类别:
Studentship
Design of metal structures of custom composition using additive manufacturing
使用增材制造设计定制成分的金属结构
- 批准号:
2593424 - 财政年份:2025
- 资助金额:
$ 45万 - 项目类别:
Studentship
Scalable indoor power harvesters using halide perovskites
使用卤化物钙钛矿的可扩展室内能量收集器
- 批准号:
MR/Y011686/1 - 财政年份:2025
- 资助金额:
$ 45万 - 项目类别:
Fellowship
Next Generation Glioma Treatments using Direct Light Therapy
使用直接光疗法的下一代神经胶质瘤治疗
- 批准号:
10092859 - 财政年份:2024
- 资助金额:
$ 45万 - 项目类别:
EU-Funded
An innovative platform using ML/AI to analyse farm data and deliver insights to improve farm performance, increasing farm profitability by 5-10%
An%20innovative%20platform%20using%20ML/AI%20to%20analysis%20farm%20data%20and%20deliver%20insights%20to%20improv%20farm%20performance,%20increasing%20farm%20profitability%20by%205-10%
- 批准号:
10093235 - 财政年份:2024
- 资助金额:
$ 45万 - 项目类别:
Collaborative R&D
An innovative international payment collection platform using fintech and FPS technology to support SMBs with international transactions that could cut fees by 83%
An%20innovative%20international%20 payment%20collection%20platform%20using%20fintech%20and%20FPS%20technology%20to%20support%20SMBs%20with%20international%20transactions%20that%20could%20cut%20fees%20by%2083%
- 批准号:
10098770 - 财政年份:2024
- 资助金额:
$ 45万 - 项目类别:
Collaborative R&D
MediMusic: using AI for music therapy in care homes
MediMusic:在疗养院使用人工智能进行音乐治疗
- 批准号:
10107316 - 财政年份:2024
- 资助金额:
$ 45万 - 项目类别:
Collaborative R&D
NEMO - Net zero events using multiple open data sources
NEMO - 使用多个开放数据源的净零事件
- 批准号:
10114096 - 财政年份:2024
- 资助金额:
$ 45万 - 项目类别:
SME Support
Removal of Perfluorinated Chemicals Using New Fluorinated Polymer Sorbents
使用新型氟化聚合物吸附剂去除全氟化化学品
- 批准号:
LP220100036 - 财政年份:2024
- 资助金额:
$ 45万 - 项目类别:
Linkage Projects