Reducing Grounded Learning Tasks To Grammatical Inference
نویسندگان
چکیده
It is often assumed that ‘grounded’ learning tasks are beyond the scope of grammatical inference techniques. In this paper, we show that the grounded task of learning a semantic parser from ambiguous training data as discussed in Kim and Mooney (2010) can be reduced to a Probabilistic Context-Free Grammar learning task in a way that gives state of the art results. We further show that additionally letting our model learn the language’s canonical word order improves its performance and leads to the highest semantic parsing f-scores previously reported in the literature.1
منابع مشابه
An Introduction to Inference and Learning in Bayesian Networks
Bayesian networks (BNs) are modern tools for modeling phenomena in dynamic and static systems and are used in different subjects such as disease diagnosis, weather forecasting, decision making and clustering. A BN is a graphical-probabilistic model which represents causal relations among random variables and consists of a directed acyclic graph and a set of conditional probabilities. Structure...
متن کاملTrodden and Untrodden Paths: A Study of Cognitive Processes in Oral Responding and Questioning
The present study was an attempt to provide a psycholinguistic account of cognitive processes underlying responding and questioning. It also strived to identify the potential differences between responding and questioning cognitive processes in Target Language Use Situation tasks. To accomplish the objectives, 65 Iranian general IELTS applicants from two foreign language learning instit...
متن کاملAn EM Approach to Grammatical Inference: Input/Output HMMs
We propose a modular recurrent connectionist architecture for adaptive temporal processing. The model is given a probabilistic interpretation and is trained using the EM algorithm. This model can also be seen as an Input/Output Hidden Markov Model. The focus of this paper is on sequence classiication tasks. We demonstrate that EM supervised learning is well suited for solving grammatical infere...
متن کاملEffect of Input vs. Collaborative Output Tasks on Iranian Intermediate EFL Learners’ Grammatical Accuracy and Willingness to Communicate
This study explored the effect of input vs. collaborative output tasks on Iranian EFL learners’ grammatical accuracy and their willingness to communicate (WTC). In so doing, the study utilized 3 input (i.e., textual enhancement, processing instruction, and discourse) and 3 collaborative output (i.e., dictogloss, reconstruction cloze task, and jigsaw) tasks and compared their effects on 5 Englis...
متن کاملExploiting social information in grounded language learning via grammatical reductions
This paper uses an unsupervised model of grounded language acquisition to study the role that social cues play in language acquisition. The input to the model consists of (orthographically transcribed) child-directed utterances accompanied by the set of objects present in the non-linguistic context. Each object is annotated by social cues, indicating e.g., whether the caregiver is looking at or...
متن کامل