III: Small: Exploiting the Massive User Generated Utterances for Intent Mining under Scarce Annotations

III：小：利用大量用户生成的话语进行稀缺注释下的意图挖掘

• 批准号: 1909323
• 负责人: Philip Yu
• 金额: $ 50万
• 依托单位: University of Illinois at Chicago
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1909323&HistoricalAwards=false
• 关键词: III; Small; Exploiting; Massive; User

With the advance of artificial intelligence and machine learning technology, users interact with computational devices through spoken language to search information or accomplish tasks, as is evident by voice-based personal assistance products in smart home, automobile, education, healthcare, retail, and telecommunications environments. This project studies user intent mining that aims to understand the underlying goals or purposes from user-generated utterances. For example, by asking the personal assistance system "should I bring an umbrella tomorrow?", a user reveals the intention of getting weather information. Intent mining has been an elusive goal for information search due to diverse, implicit expressions in questions, and it is even harder for task accomplishment in conversational systems. For example, by giving a voice command "book a restaurant near me", the system shall learn to follow up with date or dietary preferences questions and refine the task goal, i.e., the intent, according to the user response. This project explores new computational techniques to understand user-generated utterances while addressing the scarcity of annotation data available for intent mining. The research findings and insights are expected to lead to better natural language understanding, dialogue management with reduced requirements on human annotation efforts. The proposed research will be applicable to the design of new question/conservation understanding systems that improve service, user satisfaction with reduced annotation cost. The research projects will engage graduate and undergraduate students to participate in. Research findings will be incorporated into course curriculum. The proposed project provides major advancements to the foundation of intent mining from user-generated utterances, by formulating four fundamental intent mining tasks that cover the discovery, annotation, unsupervised learning and sequential modeling phase in mining user intentions. The research tasks are proposed with a specific and consistent focus on dealing with the labeling scarcity issue as it is time-consuming and labor-intensive to obtain a large scale labeled data where user intents are accurately defined and correctly annotated from diverse and noise utterances. The project will include developments of principles, models and algorithms for intent discovery, joint intent and slot annotation, unsupervised intent learning and intent evolvement modeling. Abundant learning schemas such as zero-shot learning, reinforcement learning, generative modeling, and multi-modal learning will be introduced for the ever-intensive scenario where there is not enough annotation data for current learning rationales to succeed out-of-the-box. The research team plans to share results, including datasets and software, with the research community to facilitate future studies.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.

随着人工智能和机器学习技术的进步，用户通过口语与计算设备交互以搜索信息或完成任务，智能家居、汽车、教育、医疗保健、零售和电信中基于语音的个人辅助产品就是证明环境。该项目研究用户意图挖掘，旨在从用户生成的话语中了解潜在的目标或目的。例如，通过询问个人辅助系统“明天我应该带伞吗？”，用户表达了获取天气信息的意图。由于问题的表达方式多种多样、隐含，意图挖掘一直是信息搜索的一个难以实现的目标，而在会话系统中完成任务则更加困难。例如，通过发出语音命令“预订我附近的餐厅”，系统应学习跟进日期或饮食偏好问题，并根据用户响应细化任务目标，即意图。该项目探索新的计算技术来理解用户生成的话语，同时解决可用于意图挖掘的注释数据的稀缺问题。研究结果和见解预计将带来更好的自然语言理解和对话管理，同时减少对人类注释工作的要求。拟议的研究将适用于设计新的问题/保护理解系统，以提高服务、用户满意度并降低注释成本。研究项目将吸引研究生和本科生参与。研究成果将纳入课程内容。该项目通过制定四个基本意图挖掘任务，涵盖挖掘用户意图的发现、注释、无监督学习和顺序建模阶段，为从用户生成的话语中进行意图挖掘的基础提供了重大进展。提出的研究任务的重点是处理标签稀缺问题，因为获取大规模标签数据是耗时且费力的，其中用户意图被准确定义并从不同的噪声话语中正确注释。该项目将包括意图发现、联合意图和槽位注释、无监督意图学习和意图演化建模的原理、模型和算法的开发。针对当前学习原理没有足够的注释数据来实现开箱即用的日益密集的场景，将引入丰富的学习模式，例如零样本学习、强化学习、生成建模和多模态学习。研究团队计划与研究界分享结果，包括数据集和软件，以促进未来的研究。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力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

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning

• DOI: 10.18653/v1/2021.emnlp-main.144
• 发表时间: 2021-09
• 作者: Jianguo Zhang;Trung Bui;Seunghyun Yoon;Xiang Chen;Zhiwei Liu;Congying Xia;Quan Hung Tran;Walter Chang;P. Yu

SelfLRE: Self-refining Representation Learning for Low-resource Relation Extraction

• DOI: 10.1145/3539618.3592058
• 发表时间: 2023-07
• 期刊: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval
• 作者: Xuming Hu;Junzhe Chen;Shiao Meng;Lijie Wen;Philip S. Yu

Dense Hierarchical Retrieval for Open-domain Question Answering

开放域问答的密集层次检索

• 发表时间: 2021
• 期刊: EMNLP (Findings
• 作者: Liu, Y.;Hashimoto, K.;Zhou, Y.;Yavuz, S.;Xiong, C.;Yu, P.S.
• 通讯作者: Yu, P.S.

Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System

• DOI: 10.1145/3357384.3358046
• 发表时间: 2019-08
• 期刊: Proceedings of the 28th ACM International Conference on Information and Knowledge Management
• 作者: Ye Liu;Chenwei Zhang;Xiaohui Yan;Yi Chang;Philip S. Yu

BasConv: Aggregating Heterogeneous Interactions for Basket Recommendation with Graph Convolutional Neural Network

• DOI: 10.1137/1.9781611976236.8
• 发表时间: 2020-01
• 期刊: ArXiv
• 作者: Zhiwei Liu;Mengting Wan;Stephen D. Guo;Kannan Achan;Philip S. Yu