Automatic personalized corrective feedback can help language learners from different backgrounds better acquire a new language. This paper introduces a learner English dataset in which learner errors are accompanied by information about possible erro
r sources. This dataset contains manually annotated error causes for learner writing errors. These causes tie learner mistakes to structures from their first languages, when the rules in English and in the first language diverge. This new dataset will enable second language acquisition researchers to computationally analyze a large quantity of learner errors that are related to language transfer from the learners' first language. The dataset can also be applied in personalizing grammatical error correction systems according to the learners' first language and in providing feedback that is informed by the cause of an error.
Text-based games simulate worlds and interact with players using natural language. Recent work has used them as a testbed for autonomous language-understanding agents, with the motivation being that understanding the meanings of words or semantics is
a key component of how humans understand, reason, and act in these worlds. However, it remains unclear to what extent artificial agents utilize semantic understanding of the text. To this end, we perform experiments to systematically reduce the amount of semantic information available to a learning agent. Surprisingly, we find that an agent is capable of achieving high scores even in the complete absence of language semantics, indicating that the currently popular experimental setup and models may be poorly designed to understand and leverage game texts. To remedy this deficiency, we propose an inverse dynamics decoder to regularize the representation space and encourage exploration, which shows improved performance on several games including Zork I. We discuss the implications of our findings for designing future agents with stronger semantic understanding.
