We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document. Unlike previous models, we do not collapse the query into a single vector, instead we deploy an iterative alternating attention mechanism that allows a fine-grained exploration of both the query and the document. Our model outperforms state-of...

in this research, it has been tried to survey certain persian sentences and based on the linguists' ideas the existence of the number phrase in definition phrase in the persian language is demonstrated. then it has been attempted to show that the position of the plural morpheme in persian, quite similar to the other languages, is the core of the number phrase. along with surveying the feat...

A significant number of neural architectures for reading comprehension have recently been developed and evaluated on large cloze-style datasets. We present experiments supporting the emergence of “predication structure” in the hidden state vectors of these readers. More specifically, we provide evidence that the hidden state vectors represent atomic formulas Φ[c] where Φ is a semantic property ...

This paper introduces the Syntax Game, a language game for exploring the origins of syntactic structure, specifically phrase structure. We define the game and propose a particular strategy for playing it. We show that this strategy leads to the emergence of a phrase structure grammar through the collective invention, adoption, and alignment of culturally established conventions.

Dependency structures do not have the information of phrase categories in phrase structure grammar. Thus, dependency parsing relies heavily on the lexical information of words. This paper discusses our investigation into the effectiveness of lexicalization in dependency parsing. Specifically, by restricting the degree of lexicalization in the training phase of a parser, we examine the change in...

This paper builds upon and extends certain ideas developed within the framework of Generalized Phrase Structure Grammar (GPSG). ill A new descriptive device, the Category Cooccurrence Restriction (CCR), is introduced in analogy to existing devices of GPSG in order to express constraints on the cooccurrence of categories within local trees (i.e. trees of depth one) which at present are stated wi...

We present a resource-lean neural recognizer for modeling coherence in commonsense stories. Our lightweight system is inspired by successful attempts to modeling discourse relations and stands out due to its simplicity and easy optimization compared to prior approaches to narrative script learning. We evaluate our approach in the Story Cloze Test1 demonstrating an absolute improvement in accura...