A First-Order-Logic Based Model for Grounded Language Learning

Abstract

Abstract. Much is still unknown about how children learn language, but it is clear that they perform "grounded" language learning: they learn the grammar and vocabulary not just from examples of sentences, but from examples of sentences in a particular context. Grounded language learning has been the subject of much research. Most of this work focuses on particular aspects, such as constructing semantic parsers, or on particular types of applications. In this paper, we take a broader view that includes an aspect that has received little attention until now: learning the meaning of phrases from phrase/context pairs in which the phrase's meaning is not explicitly represented. We propose a simple model for this task that uses first-order logic representations for contexts and meanings, including a simple incremental learning algorithm. We experimentally demonstrate that the proposed model can explain the gradual learning of simple concepts and language structure, and that it can easily be used for interpretation, generation, and translation of phrases.

Learning Language Models from Images with ReGLL

“…Due to space limitations we cannot detail the theoretical and algorithmic aspects behind ReGLL, for that purpose, the reader may refer to [1].…”

Anti-Unification and Natural Language Processing

“…In [12], the authors propose a method of learning the meaning of phrases from phrase/context pairs in which the phrase's meaning is not explicitly represented. They aim at modeling the way how children learn language.…”

“…It is related to semantic parsing, mentioned above. According to [12,13], the problem can be formulated as follows: Input consists of example sentences and a context, and the goal is to learn a mapping between n-grams (sequences of n words) and meanings, where meaning stands for whatever is in common among all the contexts in which that n-gram can be used. Both context and meaning are specified in first-order logic.…”