CiViL: Common-sense- and Visually-enhanced natural Language generation

CiViL:常识和视觉增强的自然语言生成

基本信息

  • 批准号:
    EP/T014598/1
  • 负责人:
  • 金额:
    $ 35.69万
  • 依托单位:
  • 依托单位国家:
    英国
  • 项目类别:
    Research Grant
  • 财政年份:
    2020
  • 资助国家:
    英国
  • 起止时间:
    2020 至 无数据
  • 项目状态:
    已结题

项目摘要

One of the most compelling problems in Artificial Intelligence is to create computational agents capable of interacting in real-world environments using natural language. Computational agents such as robots can offer multiple benefits to society, for instance, they can be used to look after the ageing population, act as companions, can be used for skills training or even provide assistance in public spaces. These are extremely challenging tasks due to their complex interdisciplinary nature, which spans across several fields including Natural Language Generation, engineering, computer vision, and robotics. Communication through language is the most vital and natural way of interaction. Humans are able to effectively communicate with each other using natural language, utilising common-sense knowledge and by making inferences about other people's backgrounds based on previous interactions with them. At the same time, they can successfully describe their surroundings, even when encountering unknown entities and object. For decades, researchers have tried to recreate the way humans communicate through natural language and although there are major breakthroughs during recent years (such as Apple's Siri or Amazon's Alexa), Natural Language Generation systems still lack the ability to reason, exploit common-sense knowledge, and utilise multi-modal information from a variety of sources such as knowledge bases, images, and videos. This project aims to develop a framework for common-sense- and visually- enhanced Natural Language Generation that can enable natural real-time communication between humans and artificial agents such as robots to enable effective collaboration between humans and robots. Human-Robot Interaction poses additional challenges to Natural Language Generation due to uncertainty derived from the dynamic environments and the non-deterministic fashion of interaction. For instance, the viewpoint of a situated robot will change when the robot moves and hence its representation of the world, which will result in failure of current state-of-art methods, which are not able to adapt to changing environments. The project aims to investigate methods for linking various modalities, taking into account their dynamic nature. To achieve natural, efficient and intuitive communication capabilities, agents will also need to acquire human-like abilities in synthesising knowledge and expression. The conditions under which external knowledge bases (such as Wikipedia) can be used to enhance natural language generation still have to be explored as well as whether existing knowledge bases are useful for language generation. The novel ways to integrate multi-modal data for language generation will lead to more robust and efficient interactions and will have an impact on natural language generation, social robotics, computer vision, and related fields. This might, in turn, spawn entirely novel applications, such as explaining exact procedures for e-health treatments and enhance tutoring systems for educational purposes.
人工智能中最引人注目的问题之一是创建能够使用自然语言在真实世界环境中进行交互的计算代理。机器人等计算代理可以为社会提供多种好处,例如,它们可以用来照顾老龄人口,充当同伴,可以用于技能培训,甚至可以在公共场所提供帮助。这些都是极具挑战性的任务,因为它们具有复杂的跨学科性质,跨越多个领域,包括自然语言生成,工程,计算机视觉和机器人技术。通过语言进行交流是最有生命力和最自然的互动方式。人类能够使用自然语言,利用常识知识,并根据先前与他们的互动对其他人的背景进行推断,从而有效地相互交流。与此同时,他们可以成功地描述他们的周围环境,即使遇到未知的实体和对象。几十年来,研究人员一直试图通过自然语言重建人类交流的方式,尽管近年来取得了重大突破(如苹果的Siri或亚马逊的Alexa),但自然语言生成系统仍然缺乏推理能力,利用常识知识,并利用来自知识库,图像和视频等各种来源的多模态信息。该项目旨在开发一个用于常识和视觉增强的自然语言生成的框架,该框架可以实现人类与机器人等人工智能体之间的自然实时通信,从而实现人类与机器人之间的有效协作。由于动态环境的不确定性和交互方式的非确定性,人机交互对自然语言生成提出了新的挑战。例如,当机器人移动时,所处位置的机器人的视点会改变,因此其对世界的表示也会改变,这将导致当前最先进的方法失败,这些方法不能适应不断变化的环境。该项目的目的是研究将各种模式联系起来的方法,同时考虑到它们的动态性质。为了实现自然、高效和直观的通信能力,智能体还需要获得类似人类的综合知识和表达能力。外部知识库(如维基百科)可用于增强自然语言生成的条件仍然需要探索,以及现有的知识库是否对语言生成有用。整合多模态数据用于语言生成的新方法将带来更强大、更高效的交互,并将对自然语言生成、社交机器人、计算机视觉和相关领域产生影响。反过来,这可能会产生全新的应用程序,例如解释电子健康治疗的确切程序,并加强教育目的的辅导系统。

项目成果

期刊论文数量(10)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Twenty Years of Confusion in Human Evaluation: NLG Needs Evaluation Sheets and Standardised Definitions
  • DOI:
    10.18653/v1/2020.inlg-1.23
  • 发表时间:
    2020
  • 期刊:
  • 影响因子:
    0
  • 作者:
    David M. Howcroft;Anya Belz;Miruna Clinciu;Dimitra Gkatzia;Sadid A. Hasan;Saad Mahamood;Simon Mille;Emiel van Miltenburg;Sashank Santhanam;Verena Rieser
  • 通讯作者:
    David M. Howcroft;Anya Belz;Miruna Clinciu;Dimitra Gkatzia;Sadid A. Hasan;Saad Mahamood;Simon Mille;Emiel van Miltenburg;Sashank Santhanam;Verena Rieser
Second Workshop on Natural Language Generation for Human-Robot Interaction
第二届人机交互自然语言生成研讨会
  • DOI:
    10.1145/3371382.3374853
  • 发表时间:
    2020
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Buschmeier H
  • 通讯作者:
    Buschmeier H
It’s Commonsense, isn’t it? Demystifying Human Evaluations in Commonsense-Enhanced NLG Systems
  • DOI:
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Miruna Clinciu;Dimitra Gkatzia;Saad Mahamood
  • 通讯作者:
    Miruna Clinciu;Dimitra Gkatzia;Saad Mahamood
"What's this?" Comparing Active learning Strategies for Concept Acquisition in HRI
“这是什么?”
  • DOI:
    10.1145/3434074.3447160
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Gkatzia D
  • 通讯作者:
    Gkatzia D
Improving the Naturalness and Diversity of Referring Expression Generation models using Minimum Risk Training
  • DOI:
    10.18653/v1/2020.inlg-1.7
  • 发表时间:
    2020
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Nikolaos Panagiaris;E. Hart;Dimitra Gkatzia
  • 通讯作者:
    Nikolaos Panagiaris;E. Hart;Dimitra Gkatzia
{{ 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 }}

Dimitra Gkatzia其他文献

Finding middle ground? Multi-objective Natural Language Generation from time-series data
寻找中间立场?
CAPE: Context-Aware Private Embeddings for Private Language Learning
CAPE:用于私人语言学习的上下文感知私人嵌入
enunlg: a Python library for reproducible neural data-to-text experimentation
enunlg:用于可重复的神经数据到文本实验的 Python 库
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    David M. Howcroft;Dimitra Gkatzia
  • 通讯作者:
    Dimitra Gkatzia
Inflection Generation for Spanish Verbs using Supervised Learning
使用监督学习生成西班牙语动词的变形
  • DOI:
    10.18653/v1/w17-4120
  • 发表时间:
    2017
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Cristina Barros;Dimitra Gkatzia;Elena Lloret
  • 通讯作者:
    Elena Lloret
Content Selection in Data-to-Text Systems: A Survey
  • DOI:
  • 发表时间:
    2016-10
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Dimitra Gkatzia
  • 通讯作者:
    Dimitra Gkatzia

Dimitra Gkatzia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('Dimitra Gkatzia', 18)}}的其他基金

Natural Language Generation for Low-resource Domains
低资源领域的自然语言生成
  • 批准号:
    EP/T024917/1
  • 财政年份:
    2021
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Research Grant

相似国自然基金

青藏高原高寒植物酚类物质分配格局的研究:基于“Common garden”实验
  • 批准号:
    31200306
  • 批准年份:
    2012
  • 资助金额:
    23.0 万元
  • 项目类别:
    青年科学基金项目

相似海外基金

"Common Sense" and flexible learning in AI agents: Do current AI agents possess the "basic skills" necessary for them to enter the workforce?
AI智能体的“常识”和灵活学习:当前的AI智能体是否具备进入劳动力市场所需的“基本技能”?
  • 批准号:
    2884814
  • 财政年份:
    2023
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Studentship
AppliCom – Application of Common Sense, Good Practice approaches to Asset information
AppliCom — 将常识、良好实践方法应用于资产信息
  • 批准号:
    10025073
  • 财政年份:
    2022
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Collaborative R&D
Can Machines Learn Common-Sense Reasoning?
机器可以学习常识推理吗?
  • 批准号:
    RGPIN-2022-05109
  • 财政年份:
    2022
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Discovery Grants Program - Individual
Enabling Common Sense Reasoning in Natural Language Processing Systems
在自然语言处理系统中实现常识推理
  • 批准号:
    RGPIN-2020-04871
  • 财政年份:
    2022
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Discovery Grants Program - Individual
Can Machines Learn Common-Sense Reasoning?
机器可以学习常识推理吗?
  • 批准号:
    DGECR-2022-00423
  • 财政年份:
    2022
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Discovery Launch Supplement
CRII: III: Robust and Explainable AI Agents with Common Sense
CRII:III:具有常识的鲁棒且可解释的人工智能代理
  • 批准号:
    2153546
  • 财政年份:
    2022
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Standard Grant
Error Inclusive Programming and Common-Sense Oriented Feature Extraction for Dynamic Acquisition and Correction of Robotic Actions
错误包容编程和面向常识的特征提取,用于机器人动作的动态获取和校正
  • 批准号:
    21J10800
  • 财政年份:
    2021
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Grant-in-Aid for JSPS Fellows
Enabling Common Sense Reasoning in Natural Language Processing Systems
在自然语言处理系统中实现常识推理
  • 批准号:
    RGPIN-2020-04871
  • 财政年份:
    2021
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Discovery Grants Program - Individual
CAREER: Harnessing Interpersonal Common Sense for Social Grounding in Natural Language Processing
职业:利用人际常识来实现自然语言处理的社会基础
  • 批准号:
    2047232
  • 财政年份:
    2021
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Continuing Grant
Enabling Common Sense Reasoning in Natural Language Processing Systems
在自然语言处理系统中实现常识推理
  • 批准号:
    RGPIN-2020-04871
  • 财政年份:
    2020
  • 资助金额:
    $ 35.69万
  • 项目类别:
    Discovery Grants Program - Individual
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了