Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work aims to answer two questions: 1) Does explicitly modeling target language syntax help NMT? 2) Is tight integration of words and syntax better than multitask tra...

Streszczenie. This paper presents a formal syntax framework of natural languages for computational linguistics. The abstract syntax of natural languages, particularly English, and their formal manipulations are described. On the basis of the abstract syntax, a universal language processing model and the deductive grammar of English are developed toward the formalization of Chomsky’s universal g...

In The proper treatment of quantification in ordimny Englim tk rQ) (Montague, 1973), Richard Montague presents the syntax and semantics of a fragment of English. His objective is to support the contention that “there is . . . no important theoretical difference between natural languages and the artificial languages of logicians” and that it is “possible to comprehend the syntax given in PTQ con...

recent research in the area of second language acquisition has proposed that bilinguals and l2 learners show syntactic indeterminacy when syntactic properties interface with other cognitive domains. most of the research in this area has focused on the pragmatic use of syntactic properties while the investigation of compliance with a grammatical rule at syntax-related interfaces has not received...

This paper investigates how syntactic knowledge interfaces with other cognitive systems by analysing the production of postverbal subjects, V(erb)–S(ubject) order, in an L1 Spanish–L2 English corpus and a comparable English native corpus. VS order in both native and L2 English is shown to be constrained by properties operating at three interfaces: (i) LEXICON–SYNTAX: the verb is unaccusative (U...

David Gil has argued that Riau Indonesian (Sumatra. Indonesia) has no syntax, or at least not much. This controversial analysis undermines all current models of grammar, especially those describing acquisition and on-line processing. To test the strength of this analysis, we computed the information gain holding between unigram and bigram models of regular and randomized samples of English and ...

Reordering is a difficult task in translating between widely different languages such as Japanese and English. We employ the postordering framework proposed by (Sudoh et al., 2011b) for Japanese to English translation and improve upon the reordering method. The existing post-ordering method reorders a sequence of target language words in a source language word order via SMT, while our method re...