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
• 负责人: Dimitra Gkatzia
• 金额: $ 53.11万
• 依托单位: Edinburgh Napier University
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2021
• 资助国家: 英国
• 起止时间: 2021 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FT024917%2F1
• 关键词: Natural; Language; Generation; Low; resource

It is expected that by 2021, Artificial Intelligence (AI) based dialogue systems such as Amazon's Alexa and Apple's Siri will exceed the earth's population [1]. Such interactive technology products have already become prevalent in many aspects of everyday life, offering support for decision making, education, and health as well as entertainment, by effectively communicating in natural language to answer questions, describe or summarise data, and assist in multiple areas. To develop such systems, however, AI requires access to vast amounts of examples of dialogues, which can (1) be hard to attain in many domains due to unavailability; and (2) pose privacy concerns, impacting user uptake [2]. Current response generation techniques are heavily based on pre-specified templates that limit language coverage. Generating naturally fluent responses is heavily dependant on example dialogues, that are scarcely available in many domains. To address these interlinked challenges, the project will firstly develop natural language generation techniques that are able to learn from limited resources by reusing the knowledge learnt in other data-rich domains, similar to the way the human brain learns new skills efficiently by building on prior knowledge. Secondly, we will develop novel privacy-preserving AI methods to address the second important challenge, and eliminate the risk for de-anonymisation of data. Although recent advances in understanding natural language have made it possible to accurately predict the meaning of users' utterances and hence accurately inform the personal assistants' actions, responding in natural language remains a bottleneck for the current generation of dialogue systems and personal assistants. As more interactive systems generating natural language become available, the need for natural variability and novelty in the generated text becomes significant in order to increase end-user satisfaction and engagement. Therefore the project will also develop AI approaches that generate text that shows novelty and variability for enriching the word choice while keeping the semantics of the generated text unchanged. Finally, many real-world applications such as personal assistants (and also chatbots and social robots) that support health or education, will benefit from generated responses that show empathy and adapt to users' psychological state. This requires a deep understanding of emotions from text, therefore, this project will, for the first time, develop and integrate innovative, natural language 'concept' based approaches, to understand user emotions from underlying text, and inform novel text generation approaches. Practical case studies provided by our industrial partners will be used to validate our developed AI approaches, throughout this ambitious project.References:[1] https://ovum.informa.com/resources/product-content/virtual-digital-assistants-to-overtake-world-population-by-2021 [2] https://www.independent.co.uk/life-style/gadgets-and-tech/news/amazon-alexa-echo-listening-spy-security-a8865056.html

预计到2021年，基于人工智能（AI）的对话系统（如亚马逊的Alexa和苹果的Siri）将超过地球人口[1]。这种交互式技术产品已经在日常生活的许多方面变得普遍，通过用自然语言有效地交流来回答问题，描述或总结数据，并在多个领域提供帮助，为决策，教育，健康和娱乐提供支持。然而，为了开发这样的系统，人工智能需要访问大量的对话示例，这可能（1）由于不可用，在许多领域很难实现;（2）造成隐私问题，影响用户的使用[2]。当前的响应生成技术主要基于限制语言覆盖的预先指定的模板。生成自然流畅的响应在很大程度上依赖于示例对话，这在许多领域中几乎不可用。为了解决这些相互关联的挑战，该项目将首先开发自然语言生成技术，这些技术能够通过重用在其他数据丰富的领域中学到的知识来从有限的资源中学习，类似于人类大脑通过建立在先前知识基础上有效学习新技能的方式。其次，我们将开发新的隐私保护人工智能方法来解决第二个重要挑战，并消除数据去匿名化的风险。虽然最近在理解自然语言方面的进展已经使得能够准确地预测用户话语的含义并且因此准确地通知个人助理的动作，但是以自然语言进行响应仍然是当前一代对话系统和个人助理的瓶颈。随着越来越多的生成自然语言的交互式系统变得可用，为了提高最终用户的满意度和参与度，对所生成文本的自然可变性和新奇的需求变得非常重要。因此，该项目还将开发人工智能方法，生成显示新奇和可变性的文本，以丰富单词选择，同时保持生成文本的语义不变。最后，许多支持健康或教育的个人助理（以及聊天机器人和社交机器人）等现实应用程序将受益于生成的反应，这些反应表现出同情心并适应用户的心理状态。这需要从文本中深入理解情感，因此，该项目将首次开发和整合基于自然语言“概念”的创新方法，从底层文本中理解用户情感，并为新的文本生成方法提供信息。在这个雄心勃勃的项目中，我们的工业合作伙伴提供的实际案例研究将用于验证我们开发的人工智能方法。参考资料：[1] https://ovum.informa.com/resources/product-content/virtual-digital-assistants-to-overtake-world-population-by-2021 [2] https://www.independent.co.uk/life-style/gadgets-and-tech/news/amazon-alexa-echo-listening-spy-security-a8865056.html

项目成果

Leveraging label hierarchy using transfer and multi-task learning: A case study on patent classification

• DOI: 10.1016/j.neucom.2021.07.057
• 发表时间: 2021-07
• 期刊: Neurocomputing
• 影响因子: 6
• 作者: S. Aroyehun;Jason Angel;Navonil Majumder;Alexander Gelbukh;A. Hussain

An Enhanced Binary Particle Swarm Optimization (E-BPSO) algorithm for service placement in hybrid cloud platforms

• DOI: 10.1007/s00521-022-07839-5
• 发表时间: 2018-06
• 期刊: Neural Computing and Applications
• 影响因子: 6
• 作者: Wissem Abbes;Zied Kechaou;Amir Hussain;A. Qahtani;Omar Almutiry;Habib Dhahri;A. Alimi

Arabic question answering system: a survey

• DOI: 10.1007/s10462-021-10031-1
• 发表时间: 2021-07-12
• 期刊: ARTIFICIAL INTELLIGENCE REVIEW
• 影响因子: 12
• 作者: Alwaneen, Tahani H.;Azmi, Aqil M.;Hussain, Amir
• 通讯作者: Hussain, Amir

A Novel Homomorphic Encryption and Consortium Blockchain-Based Hybrid Deep Learning Model for Industrial Internet of Medical Things

• DOI: 10.1109/tnse.2023.3285070
• 发表时间: 2023-09-01
• 期刊: IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
• 影响因子: 6.6
• 作者: Ali, Aitizaz;Pasha, Muhammad Fermi;Fortino, Giancarlo
• 通讯作者: Fortino, Giancarlo

Multi3Generation: Multitask, Multilingual, Multimodal Language Generation

Multi3Generation：多任务、多语言、多模式语言生成

• 发表时间: 2022
• 作者: Barreiro A