Commonsense Reasoning in Natural Language Processing
自然语言处理中的常识推理
基本信息
- 批准号:RGPIN-2022-03677
- 负责人:
- 金额:$ 2.48万
- 依托单位:
- 依托单位国家:加拿大
- 项目类别:Discovery Grants Program - Individual
- 财政年份:2022
- 资助国家:加拿大
- 起止时间:2022-01-01 至 2023-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Natural Language Processing (NLP) is concerned with developing computer software that can interact with humans seamlessly in natural language. NLP is now ubiquitous in our everyday life, in products such as search engines, personal assistants, and translation systems. Recent breakthroughs in Deep Learning (DL) contributed to rapid advancement in NLP research, with supervised learning as the main paradigm. Despite significant breakthroughs, current DL-based NLP models are still only able to perform narrow, often domain-specific tasks. They perform well on tasks which involve learning relatively straightforward input-output mappings, such as translation and text classification, but struggle with tasks involving missing information or requiring advanced reasoning. Finally, the limited generalizability of DL models causes unhumanlike errors on examples that even slightly differ from the training distribution. These are major obstacles to broadening the usage of real-world NLP software. The production of many systems is stalled because they are not yet robust enough to be deployed in open-domain settings. Worse still, some of these systems are deployed despite their unpredictable, nonsensical, and potentially dangerous behaviour. The long term goal of my research is to build robust, reliable, and accurate NLP systems that can generalize beyond the training distribution and address unknown inputs consistently with human expectations. The key hypothesis behind my research is that this ability may be achieved by endowing NLP models with humanlike commonsense knowledge and reasoning abilities. In the short term, I will advance towards this goal in 3 research threads addressing core challenges: (1) Automatic acquisition of (often unstated) commonsense knowledge, for machines to reason about; (2) Incorporating commonsense into NLP applications; and (3) Developing benchmarks and evaluation protocols to trace progress on machine commonsense. I will employ a range of tools and approaches including deep learning, linguistic analysis of texts, knowledge bases and symbolic AI methods, crowdsourcing, and learning from multiple modalities. By developing core components for knowledge acquisition, incorporation and reasoning, I will be able to train high-performing and robust NLP systems that can generalize better given fewer training examples. Such components will improve the interpretability of those otherwise black-box neural networks. This research has the potential to improve the applicability of NLP systems across the board, including translation, dialogue, and summarization. Beyond the immediate impact on academia and industry, the proposed research program will train a new generation of first-class experts in NLP, with expertise in adjacent research areas such as machine learning, computer vision, cognitive science, and AI. With the necessary skills and experience, these professionals will contribute to Canadian academia, global and local industry.
自然语言处理(NLP)致力于开发能够以自然语言与人类无缝交互的计算机软件。NLP现在在我们的日常生活中无处不在,在搜索引擎,个人助理和翻译系统等产品中。深度学习(DL)的最新突破有助于NLP研究的快速发展,监督学习是主要范式。 尽管取得了重大突破,但目前基于DL的NLP模型仍然只能执行狭窄的,通常是特定于领域的任务。他们在涉及学习相对简单的输入-输出映射的任务上表现良好,例如翻译和文本分类,但在涉及丢失信息或需要高级推理的任务上表现不佳。最后,深度学习模型的有限推广性会导致在与训练分布略有不同的示例上出现非人性化的错误。这些是扩大现实世界NLP软件使用的主要障碍。许多系统的生产停滞不前,因为它们还不够强大,无法部署在开放域环境中。更糟糕的是,尽管这些系统的行为不可预测、荒谬和潜在的危险,但它们还是被部署了。 我的研究的长期目标是建立强大,可靠和准确的NLP系统,可以推广到训练分布之外,并与人类期望一致地处理未知输入。我的研究背后的关键假设是,这种能力可以通过赋予NLP模型类似人类的常识知识和推理能力来实现。在短期内,我将在解决核心挑战的3个研究主题中实现这一目标:(1)自动获取(通常未说明的)常识知识,供机器推理;(2)将常识扩展到NLP应用程序中;(3)开发基准和评估协议以跟踪机器常识的进展。我将使用一系列工具和方法,包括深度学习,文本的语言分析,知识库和符号人工智能方法,众包和从多种模式中学习。 通过开发用于知识获取、整合和推理的核心组件,我将能够训练出高性能和鲁棒的NLP系统,这些系统可以在较少的训练示例下更好地泛化。这些组件将提高那些黑盒神经网络的可解释性。这项研究有可能全面提高NLP系统的适用性,包括翻译,对话和摘要。除了对学术界和工业界的直接影响外,拟议的研究计划将培养新一代NLP的一流专家,他们在机器学习,计算机视觉,认知科学和人工智能等相邻研究领域具有专业知识。凭借必要的技能和经验,这些专业人士将为加拿大学术界,全球和当地行业做出贡献。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
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 }}
Shwartz, Vered其他文献
Proceedings of the Student Research Workshop
学生研究研讨会论文集
- DOI:
- 发表时间:
2018 - 期刊:
- 影响因子:0
- 作者:
Shwartz, Vered;Tabassum, Jeniya;Voigt, Rob - 通讯作者:
Voigt, Rob
Shwartz, Vered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('Shwartz, Vered', 18)}}的其他基金
Commonsense Reasoning in Natural Language Processing
自然语言处理中的常识推理
- 批准号:
DGECR-2022-00374 - 财政年份:2022
- 资助金额:
$ 2.48万 - 项目类别:
Discovery Launch Supplement
相似海外基金
CAREER: Robust, Fair, and Culturally Aware Commonsense Reasoning in Natural Language
职业:用自然语言进行稳健、公平和具有文化意识的常识推理
- 批准号:
2339746 - 财政年份:2024
- 资助金额:
$ 2.48万 - 项目类别:
Continuing Grant
Modeling the Conceptual Dynamics of College Students' Reasoning about Natural Selection
大学生自然选择推理的概念动态建模
- 批准号:
2300437 - 财政年份:2023
- 资助金额:
$ 2.48万 - 项目类别:
Standard Grant
Reasoning in ZX calculus and quantum natural language processing
ZX 演算和量子自然语言处理中的推理
- 批准号:
2872655 - 财政年份:2023
- 资助金额:
$ 2.48万 - 项目类别:
Studentship
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:
$ 2.48万 - 项目类别:
Discovery Grants Program - Individual
CAREER: Flexible and Robust Reasoning in Natural Language
职业:灵活而稳健的自然语言推理
- 批准号:
2145280 - 财政年份:2022
- 资助金额:
$ 2.48万 - 项目类别:
Continuing Grant
Commonsense Reasoning in Natural Language Processing
自然语言处理中的常识推理
- 批准号:
DGECR-2022-00374 - 财政年份:2022
- 资助金额:
$ 2.48万 - 项目类别:
Discovery Launch Supplement
Analytical Reasoning and Fuzzy Cognitive Maps of Barrier Island Response to Natural and Anthropogenic Forcing
障壁岛对自然和人为强迫响应的分析推理和模糊认知图
- 批准号:
RGPIN-2017-04920 - 财政年份:2022
- 资助金额:
$ 2.48万 - 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:2021
- 资助金额:
$ 2.48万 - 项目类别:
Discovery Grants Program - Individual
Analytical Reasoning and Fuzzy Cognitive Maps of Barrier Island Response to Natural and Anthropogenic Forcing
障壁岛对自然和人为强迫响应的分析推理和模糊认知图
- 批准号:
RGPIN-2017-04920 - 财政年份:2021
- 资助金额:
$ 2.48万 - 项目类别:
Discovery Grants Program - Individual
Analytical Reasoning and Fuzzy Cognitive Maps of Barrier Island Response to Natural and Anthropogenic Forcing
障壁岛对自然和人为强迫响应的分析推理和模糊认知图
- 批准号:
RGPIN-2017-04920 - 财政年份:2020
- 资助金额:
$ 2.48万 - 项目类别:
Discovery Grants Program - Individual