Using Implicit Feedback to Improve Question Generation
Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等技术学院）；INESC-ID（葡萄牙信息与通信技术研究院）；Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）
本文提出 GEN 系统，利用用户选择与修正两类隐式反馈迭代生成、评分并排序问题模式，实验表明其在 top 5、10、20 设置下较无学习版本提升至少 10%。
摘要：
问题生成（Question Generation，QG）是自然语言处理（Natural Language Processing，NLP）中的一项任务，旨在从文本中自动生成问题。许多应用都可以从自动生成的问题中受益，但通常有必要对这些问题进行筛选整理，方式包括选择或编辑。这项任务本身具有信息价值，但它通常是在生成之后完成的，因此相关投入被浪费了。此外，大多数现有系统无法轻松地将这种反馈重新纳入自身。在本文中，我们提出了一个名为 GEN 的系统，它能够从此类（隐式）反馈中学习。该系统采用基于模式的方法，以少量句子/问题对作为输入，创建模式，随后将这些模式应用于未见过的新句子。每个生成的问题在经过用户修正后，都会在下一次迭代中作为新的种子使用，因此每次都会创建更多模式。我们还利用用户所做的修正来为模式评分，从而对生成的问题进行排序。结果表明，在考虑排名前 5、前 10 和前 20 的问题时，与不具备学习能力的版本相比，GEN 能够通过从两个层面的隐式反馈中学习而获得改进。根据所使用的指标和策略，提升幅度从 10% 起步，最高可达更高水平。
英文摘要：
Question Generation (QG) is a task of Natural Language Processing (NLP) that aims at automatically generating questions from text. Many applications can benefit from automatically generated questions, but often it is necessary to curate those questions, either by selecting or editing them. This task is informative on its own, but it is typically done post-generation, and, thus, the effort is wasted. In addition, most existing systems cannot incorporate this feedback back into them easily. In this work, we present a system, GEN, that learns from such (implicit) feedback. Following a pattern-based approach, it takes as input a small set of sentence/question pairs and creates patterns which are then applied to new unseen sentences. Each generated question, after being corrected by the user, is used as a new seed in the next iteration, so more patterns are created each time. We also take advantage of the corrections made by the user to score the patterns and therefore rank the generated questions. Results show that GEN is able to improve by learning from both levels of implicit feedback when compared to the version with no learning, considering the top 5, 10, and 20 questions. Improvements go up from 10%, depending on the metric and strategy used.
Improved Personalized Headline Generation via Denoising Fake Interests from Implicit Feedback
Henan Institute of Advanced Technology, Zhengzhou University（河南高级技术研究所，郑州大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Independent Researcher（独立研究者）
Collaborative Filtering with Topic and Social Latent Factors Incorporating Implicit Feedback
Nanjing University（南京大学）；Nanjing University of Science and Technology（南京理工大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）；Florida International University（佛罗里达国际大学）
Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues
Technical University of Darmstadt（达姆施塔特工业大学）；Hessian Center for AI (hessian.AI)（黑森人工智能中心）；Department of Computer Science（计算机科学系）；Ubiquitous Knowledge Processing Lab (UKP Lab)（普适知识处理实验室）
Representation Learning and Pairwise Ranking for Implicit Feedback in Recommendation Systems
Univ. Grenoble Alpes/CNRS（格勒诺布尔阿尔卑斯大学/法国国家科学研究中心）；Center for Energy Systems, Skolkovo Institute of Science（斯科尔科沃科技学院能源系统中心）；T-4 and CNLS, Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室T-4与CNLS）；Center for Energy Systems, Skolkovo Institute of Science and Technology（斯科尔科沃科技学院能源系统中心）
My Words Imply Your Opinion: Reader Agent-based Propagation Enhancement for Personalized Implicit Emotion Analysis
School of Computer and Information Technology, Shanxi University, China（山西大学计算机与信息学院）；Institute of Automation, Chinese Academy of Science, China（中国科学院自动化研究所）；Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, China（教育部计算智能与中文信息处理重点实验室）；Joint Laboratory of Tourism Big Data in Shanxi Province, China（山西省旅游大数据联合实验室）
