Back to Search
Start Over
Learning Language Games through Interaction
- Source :
- ACL (1)
- Publication Year :
- 2016
- Publisher :
- Association for Computational Linguistics, 2016.
-
Abstract
- We introduce a new language learning setting relevant to building adaptive natural language interfaces. It is inspired by Wittgenstein's language games: a human wishes to accomplish some task (e.g., achieving a certain configuration of blocks), but can only communicate with a computer, who performs the actual actions (e.g., removing all red blocks). The computer initially knows nothing about language and therefore must learn it from scratch through interaction, while the human adapts to the computer's capabilities. We created a game in a blocks world and collected interactions from 100 people playing it. First, we analyze the humans' strategies, showing that using compositionality and avoiding synonyms correlates positively with task performance. Second, we compare computer strategies, showing how to quickly learn a semantic parsing model from scratch, and that modeling pragmatics further accelerates learning for successful players.<br />Comment: 11 pages, ACL 2016
- Subjects :
- FOS: Computer and information sciences
Computer Science - Computation and Language
Parsing
Computer Science - Artificial Intelligence
I.2.6
Computer science
Principle of compositionality
I.2.7
Blocks world
02 engineering and technology
010501 environmental sciences
Pragmatics
computer.software_genre
01 natural sciences
Task (project management)
Constructed language
Artificial Intelligence (cs.AI)
Human–computer interaction
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Computation and Language (cs.CL)
computer
Natural language
0105 earth and related environmental sciences
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Accession number :
- edsair.doi.dedup.....c655ab5e9e5321512ba02dafd7b0cbbd