On the String Translations Produced by Multi Bottom--Up Tree Transducers

String-to-Tree Multi Bottom-up Tree Transducers

Recursive prosody is not finite-state

This paper investigates bounds on the generative capacity of prosodic processes, by focusing on the complexity of recursive prosody in coordination contexts in English (Wagner, 2010). Although all phonological processes …

A Neural Verb Lexicon Model with Source-side Syntactic Context for String-to-Tree Machine Translation

String-to-tree MT systems translate verbs without lexical or syntactic context on the source side and with limited target-side context. The lack of context is one reason why verb translation recall is as low as 45.5%. We…

Towards String-to-Tree Neural Machine Translation

We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees. An experiment on the WMT16 …

Dependency Graph-to-String Statistical Machine Translation

We present graph-based translation models which translate source graphs into target strings. Source graphs are constructed from dependency trees with extra links so that non-syntactic phrases are connected. Inspired by p…