Why Neural Translations are the Right Length
نویسندگان
چکیده
We investigate how neural, encoder-decoder translation systems output target strings of appropriate lengths, finding that a collection of hidden units learns to explicitly implement this functionality.
منابع مشابه
Asynchronous translations with recurrent neural nets
In recent years, many researchers have explored the relation between discrete-time recurrent neural networks (DTRNN) and finite-state machines (FSMs) either by showing their computational equivalence or by training them to perform as finite-state recognizers from examples. Most of this work has focussed on the simplest class of deterministic state machines, that is deterministic finite automata...
متن کاملA Neural Network based Approach to Automatic Post-Editing
We present a neural network based automatic post-editing (APE) system to improve raw machine translation (MT) output. Our neural model of APE (NNAPE) is based on a bidirectional recurrent neural network (RNN) model and consists of an encoder that encodes an MT output into a fixed-length vector from which a decoder provides a post-edited (PE) translation. APE translations produced by NNAPE show ...
متن کاملFBK's Participation to the English-to-German News Translation Task of WMT 2017
In this paper we report on FBK’s participation to the English-to-German news translation task of the Second Conference on Machine Translation (WMT’17). The submitted system is based on Neural Machine Translation using byte-pair encoding segmentation on both source and target languages for open-vocabulary translations. Back-translations of news monolingual data are used for improving the transla...
متن کاملWhy Catalan-Spanish Neural Machine Translation? Analysis, comparison and combination with standard Rule and Phrase-based technologies
Catalan and Spanish are two related languages given that both derive from Latin. They share similarities in several linguistic levels including morphology, syntax and semantics. This makes them particularly interesting for the MT task. Given the recent appearance and popularity of neural MT, this paper analyzes the performance of this new approach compared to the well-established rule-based and...
متن کاملA Critical Study of the Views on the Why of Not Mentioning Uli `lamr as the Source of Conflict in the Verse 59 Nias
The present descriptive-analytic research has examined and interpreted the commentators' view on the why of not mentioning Uli `lamr as a source of conflict resolution in the verse 59 of Sura Nisa. In various respects, some have considered lack of innocence as the reason for not mentioning them as a source of dispute resolution, some view the people`s obligation in following the first part of t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016