Natural language is structured hierarchically: words are grouped into phrases or constituents, which can be further grouped to form higher-level phrases up to the full sentence. How well do the neural network models trained on language data learn this phrase structure of human language has been a subject of great interest. A flurry of past work have shown that syntax trees can be recovered from recurrent neural network (RNN) and transformer-based models trained on large-scale language corpora (Tenney et al., 2019, Peters et al., 2018, Lin et al., 2019, Wu et al., 2020). While these studies provide useful evidence of the aforementioned phenomenon, they do not shed light on the architectural choices, training paradigms or dataset characteristics that lead models to learn the phrase structure of language. A useful tool to understand these model and dataset specific properties is through the test for hierarchical generalization, i.e., evaluating the capability of a model to generalize to novel syntactic forms, which were unseen during training. A classic problem to test for hierarchical generalization is question formation, where given a declarative sentence, e.g., My walrus does move the dogs that do wait., the task is to transform it into a question: Does my walrus move the dogs that do wait? The task is accomplished by moving one auxiliary verb to the front. The correct choice to move does in this example (rather than do), is predicted both by a hierarchical rule based on the phrase-structure syntax of the sentence, and by a linear rule that says to move the first auxiliary. Hence, as a test for hierarchical generalization, we can ask, for neural networks trained from scratch on data that is consistent with both hierarchical and linear rules (i.e.,

In this paper we develop a Bayes criterion which includes the Rissanen complexity, for inferring regular grammar models. We develop two methods for regular grammar Bayesian inference. The fIrst method is based on treating the regular grammar as a I-dimensional Markov source, and the second is based on the combinatoric characteristics of the regular grammar itself. We apply the resulting Bayes criteria to a particular example in order to show the efficiency of each method.

Simple secood-order recurrent netwoIts are shown to readily learn sman brown regular grammars when trained with positive and negative strings examples. We show that similar methods are appropriate for learning unknown grammars from examples of their strings. TIle training algorithm is an incremental real-time, re(cid:173) current learning (RTRL) method that computes the complete gradient and updates the weights at the end of each string. For many cases the extracted grammar outperforms the neural net from which it was extracted in correctly classifying unseen strings.

Grammatical inference is a classical problem in computational learning theory and a topic of wider influence in natural language processing. We treat grammars as a model of computation and propose a novel neural approach to induction of regular grammars from positive and negative examples. Our model is fully explainable, its intermediate results are directly interpretable as partial parses, and it can be used to learn arbitrary regular grammars when provided with sufficient data. We find that our method consistently attains high recall and precision scores across a range of tests of varying complexity.

The purposeful exchange of information caused by the creation and perception of signals drawn from a shared system of conventional signs is known as communication. Most animals employ signals to convey vital messages: there's food here, there's a predator nearby, approach, recede, and let's mate. Communication can help agents succeed in a partially visible world because they can learn knowledge that others have observed or inferred. Humans are the most talkative of all species, thus computer agents will need to master the language if they are to be useful. Language models for communication are examined in this chapter.

We propose an approach that connects recurrent networks with different orders of hidden interaction with regular grammars of different levels of complexity. We argue that the correspondence between recurrent networks and formal computational models gives understanding to the analysis of the complicated behaviors of recurrent networks. We introduce an entropy value that categorizes all regular grammars into three classes with different levels of complexity, and show that several existing recurrent networks match grammars from either all or partial classes. As such, the differences between regular grammars reveal the different properties of these models. We also provide a unification of all investigated recurrent networks. Our evaluation shows that the unified recurrent network has improved performance in learning grammars, and demonstrates comparable performance on a real-world dataset with more complicated models.

Data samples collected for training machine learning models are typically assumed to be independent and identically distributed (iid). Recent research has demonstrated that this assumption can be problematic as it simplifies the manifold of structured data. This has motivated different research areas such as data poisoning, model improvement, and explanation of machine learning models. In this work, we study the influence of a sample on determining the intrinsic topological features of its underlying manifold. We propose the Shapley Homology framework, which provides a quantitative metric for the influence of a sample of the homology of a simplicial complex. By interpreting the influence as a probability measure, we further define an entropy which reflects the complexity of the data manifold. Our empirical studies show that when using the 0-dimensional homology, on neighboring graphs, samples with higher influence scores have more impact on the accuracy of neural networks for determining the graph connectivity and on several regular grammars whose higher entropy values imply more difficulty in being learned.

We show that similar methods are appropriate for learning unknown grammars from examples of their strings. TIle training algorithm is an incremental real-time, recurrent learning (RTRL) method that computes the complete gradient and updates the weights at the end of each string.

We show that similar methods are appropriate for learning unknown grammars from examples of their strings. TIle training algorithm is an incremental real-time, recurrent learning (RTRL) method that computes the complete gradient and updates the weights at the end of each string.

We show that similar methods are appropriate for learning unknown grammars from examples of their strings. TIle training algorithm is an incremental real-time, recurrent learning(RTRL) method that computes the complete gradient and updates the weights at the end ofeach string.