Human languages use a wide range of grammatical categories to constrain which
words or phrases can fill certain slots in grammatical patterns and to express
additional meanings, such as tense or aspect, through morpho-syntactic means.
These grammatical categories, which are most often language-specific and
changing over time, are difficult to define and learn. This paper raises the
question how these categories can be acquired and where they have come from. We
explore a usage-based approach. This means that categories and grammatical
constructions are selected and aligned by their success in language
interactions. We report on a multi-agent experiment in which agents are endowed
with mechanisms for understanding and producing utterances as well as
mechanisms for expanding their inventories using a meta-level learning process
based on pro- and anti-unification. We show that a categorial type network
which has scores based on the success in a language interaction leads to the
spontaneous formation of grammatical categories in tandem with the formation of
grammatical patterns.

通过一系列代理实验证明，基于习惯和互动的选取和对齐方式，能够推动语言交互更自然的语法范畴与语法模式的形成。

基于语用的语法类别学习

Usage-based learning of grammatical categories

We consider the problem of fully unsupervised learning of grammatical
(part-of-speech) categories from unlabeled text. The standard
maximum-likelihood hidden Markov model for this task performs poorly, because
of its weak inductive bias and large model capacity. We address this problem by
refining the model and modifying the learning objective to control its capacity
via para- metric and non-parametric constraints. Our approach enforces
word-category association sparsity, adds morphological and orthographic
features, and eliminates hard-to-estimate parameters for rare words. We develop
an efficient learning algorithm that is not much more computationally intensive
than standard training. We also provide an open-source implementation of the
algorithm. Our experiments on five diverse languages (Bulgarian, Danish,
English, Portuguese, Spanish) achieve significant improvements compared with
previous methods for the same task.

该研究针对无标注文本完全无监督学习语法 (词性) 类别的问题，通过参数和非参数约束对标准的最大似然隐马尔可夫模型进行优化和修改和达到了在多种语言上显著提高的效果。