Learning Language Games through Interaction
This addresses the challenge of building adaptive natural language interfaces for tasks like block manipulation, though it is incremental as it builds on existing semantic parsing and pragmatic modeling approaches.
The paper tackles the problem of enabling computers to learn language from scratch through interactive games with humans, inspired by Wittgenstein's language games, and shows that modeling pragmatics accelerates learning for successful players.
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.