CL system: Giving instructions by corpus based selection
نویسندگان
چکیده
The CL system uses an algorithm that, given a task-based corpus situated in a virtual world, which contains human instructor’s speech acts and the user’s responses as physical actions, generates a virtual instructor that helps a user achieve a given task in the virtual world. In this report, we explain how this algorithm can be used for generating a virtual instructor for a game-like, task-oriented virtual world such as GIVE’s.
منابع مشابه
Giving instructions in virtual environments by corpus based selection
Instruction giving can be used in several applications, ranging from trainers in simulated worlds to non player characters for virtual games. In this paper we present a novel algorithm for rapidly prototyping virtual instruction-giving agents from human-human corpora without manual annotation. Automatically prototyping full-fledged dialogue systems from corpora is far from being a reality nowad...
متن کاملThe GIVE-2 Corpus of Giving Instructions in Virtual Environments
We present the GIVE-2 Corpus, a new corpus of human instruction giving. The corpus was collected by asking one person in each pair of subjects to guide the other person towards completing a task in a virtual 3D environment with typed instructions. This is the same setting as that of the recent GIVE Challenge, and thus the corpus can serve as a source of data and as a point of comparison for NLG...
متن کاملNatural Language Generation in the Context of Providing Indoor Route Instructions
Modern robotics applications require robots to be able to communicate with humans seamlessly and effectively. We propose a structured algorithm for natural language generation in the context of indoor route instructions that allows a robot to combine metrical, topological and semantic information about the surrounding environment while generating natural language instructions. Our method learns...
متن کاملIdentification of microRNAs in corpus luteum of pregnancy in buffalo (Bubalus bubalis) by deep sequencing
This study was aimed to identify miRNAs of corpus luteum (CL) in buffaloes during pregnancy. For this study, CL (n=2) were collected from gravid uteri of buffalo and RNA was isolated. Following this, the purity and integrity of RNA was checked and used for deep sequencing using Illumina Hiseq 2500 platform. The reads’ quality was checked prior to in silico analyses viz. identification of conser...
متن کاملLearning to Interpret Natural Language Navigation Instructions from Observation
The ability to understand natural-language instructions is critical to building intelligent agents that interact with humans. We present a system that learns to transform natural-language navigation instructions into executable formal plans. Given no prior linguistic knowledge, the system learns by simply observing how humans follow navigation instructions. The system is evaluated in three comp...
متن کامل