World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive narratives, are reinforcement learning environments in which agents perceive and interact with the world using textual natural language. These environments contain long, multi-step puzzles or quests woven through a world that is filled with hundreds of characters, locations, and objects. Our world model learns to simultaneously: (1) predict changes in the world caused by an agent's actions when representing the world as a knowledge graph; and (2) generate the set of contextually relevant natural language actions required to operate in the world. We frame this task as a Set of Sequences generation problem by exploiting the inherent structure of knowledge graphs and actions and introduce both a transformer-based multi-task architecture and a loss function to train it. A zero-shot ablation study on never-before-seen textual worlds shows that our methodology significantly outperforms existing textual world modeling techniques as well as the importance of each of our contributions.
Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Unisound Information Technology Co., Ltd（北京云知声信息技术有限公司）
SEMMA: A Semantic Aware Knowledge Graph Foundation Model
Institute for AI, University of Stuttgart（斯图加特大学人工智能研究所）；IIIT Hyderabad（海得拉巴国家理工学院）；Stanford University（斯坦福大学）；University of Edinburgh（爱丁堡大学）；University of Southampton（南安普顿大学）
Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning
Zhejiang University（浙江大学）；Shopee Pte.Ltd.（Shopee公司）；University of Macau（澳门大学）；Zhejiang Key Laboratory of Big Data Intelligent Computing（浙江大学大数据智能计算重点实验室）
Integrating Knowledge Graph embedding and pretrained Language Models in Hypercomplex Spaces
University of Stuttgart（斯图加特大学）；University of Bonn（波恩大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；TU Dresden（德累斯顿工业大学）；Amazon（亚马逊）；University of Southampton（南安普顿大学）
Universal Preprocessing Operators for Embedding Knowledge Graphs with Literals
Peoples' Friendship University of Russia (RUDN University)（俄罗斯人民友谊大学（卢蒙巴大学））；Joint Institute for Nuclear Research（联合核研究所）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；University of Skövde（舍夫德大学）；University of Mannheim（曼海姆大学）
Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction
Analytic Computing, KI, University of Stuttgart, Stuttgart, Germany（斯图加特大学分析计算研究所）；Bosch Center for Artificial Intelligence, Stuttgart, Germany（博世人工智能中心）；WAIS, University of Southampton, United Kingdom（南安普顿大学WAIS）
Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations
Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly（南洋理工大学-英属哥伦比亚大学联合卓越研究中心（老年人积极生活方向））；Alibaba-NTU Singapore Joint Research Institute（阿里巴巴-南洋理工大学新加坡联合研究院）；Nanyang Technological University（南洋理工大学）
Mention Memory: incorporating textual knowledge into Transformers through entity mention attention
University of Southern California（南加利福尼亚大学）；Google（谷歌）；Google Research（谷歌研究院）
诸如开放域问答之类的自然语言理解任务通常需要从多个源检索和吸收事实信息。我们建议通过将大型文本语料库的半参数表示集成到Transformer模型中作为事实知识的来源来解决这个问题。具体来说，我们的方法表示知识与“提及记忆”，一个表的密集向量表示的每一个实体中提到的语料库。所提出的模型- TOME -是一个Transformer，它通过内部记忆层访问信息，其中输入通道中提到的每个实体都参与提到记忆。这种方法支持在单个Transformer模型中对许多不同的信息源进行合成和推理。在使用1.5亿次维基百科提及的记忆的实验中，TOME在几个开放领域知识密集型任务上实现了强大的性能，包括声明验证基准HoVer和FEVER以及几个基于实体的QA基准。我们还表明，该模型学习参加信息提及没有任何直接的监督。最后，我们证明了该模型可以推广到新的看不见的实体更新的内存，而无需再训练。
What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
School of Information Science and Technology, ShanghaiTech University, Shanghai, China（信息科学与技术学院，上海科技大学，上海，中国）；University of Illinois at Urbana-Champaign, Illinois, United States（伊利诺伊大学厄巴纳-香槟分校，伊利诺伊，美国）
TeKo: Text-Rich Graph Neural Networks with External Knowledge
Tianjin University（天津大学）；Qinghai Nationalities Unversity（青海民族大学）；Tsinghua University（清华大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；JD.COM Silicon Valley Research Center（京东硅谷研究中心）
ECOLA: Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations
University of Oxford（牛津大学）；LMU Munich（慕尼黑大学）；Technical University of Munich（慕尼黑工业大学）；Technical University of Darmstadt（达姆施塔特工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）
