论文标题
非本体忠实的非玩家角色对话
Ontologically Faithful Generation of Non-Player Character Dialogues
论文作者
论文摘要
我们介绍了以流行的视频游戏环境为基础的语言生成任务。 Knudge（知识限制的用户-NPC对话生成）要求模型在视频游戏角色之间产生对话的树，这些视频游戏角色准确地反映了自然语言所述的任务和实体规范。 Knudge是由直接从黑曜石娱乐的《外在世界》的游戏数据中绘制而来的侧面任务对话，从而导致了一代现实世界中的复杂性：（1）对话是分支的树木，而不是讲话的线性链； （2）话语必须忠于游戏知识 - 角色角色，背景故事和实体关系； （3）对话必须准确地向人类玩家揭示新的任务细节。我们使用监督和文化学习技术报告了一组神经生成模型的结果；我们发现了能力的表现，但是未来工作的空间解决了创建现实的游戏质量对话的挑战。
We introduce a language generation task grounded in a popular video game environment. KNUDGE (KNowledge Constrained User-NPC Dialogue GEneration) requires models to produce trees of dialogue between video game characters that accurately reflect quest and entity specifications stated in natural language. KNUDGE is constructed from side quest dialogues drawn directly from game data of Obsidian Entertainment's The Outer Worlds, leading to real-world complexities in generation: (1) dialogues are branching trees as opposed to linear chains of utterances; (2) utterances must remain faithful to the game lore -- character personas, backstories, and entity relationships; and (3) a dialogue must accurately reveal new quest details to the human player. We report results for a set of neural generation models using supervised and in-context learning techniques; we find competent performance but room for future work addressing the challenges of creating realistic, game-quality dialogues.
