paper-with-me

홈 › Papers

Lexical Translation Model Using a Deep Neural Network Architecture

2015-04-28 · Thanh-Le Ha, Jan Niehues, Alex Waibel

In this paper we combine the advantages of a model using global source sentence contexts, the Discriminative Word Lexicon, and neural networks. By using deep neural networks instead of the linear maximum entropy model in the Discriminative Word Lexicon models, we are able to leverage dependencies between different source words due to the non-linearity. Furthermore, the models for different target words can share parameters and therefore data sparsity problems are effectively reduced. By using this approach in a state-of-the-art translation system, we can improve the performance by up to 0.5 BLEU points for three different language pairs on the TED translation task.

📄 PDF Abstract BibTeX arXiv:1504.07395

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceTranslation

Similar Papers 제목 키워드 기반

Neural Machine Translation with Inflected Lexicon

2021-08-01 · MTSummit 2021 8 · Artur Nowakowski, Krzysztof Jassem

The paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language. In particular and we introduce a method and based on constrained decoding and which handles the …

Machine TranslationSentenceTranslation

Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts

2019-06-28 · WS 2019 8 · Denis Emelin, Ivan Titov, Rico Sennrich

The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the firs…

DecoderMachine TranslationTranslation

Addressing the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts

2019-01-24 · Anonymous

The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the firs…

DecoderMachine TranslationTranslation

The UPC RDF-to-Text System at WebNLG Challenge 2020

2020-12-01 · ACL (WebNLG, INLG) 2020 12 · David Bergés, Roser Cantenys, Roger Creus, Oriol Domingo 외

This work describes the end-to-end system architecture presented at WebNLG Challenge 2020. The system follows the traditional Machine Translation (MT) pipeline, based on the Transformer model, applied in most text-totext…

Machine TranslationTranslation

The impact of lexical and grammatical processing on generating code from natural language

2022-02-28 · Findings (ACL) 2022 5 · Nathanaël Beau, Benoît Crabbé

Considering the seq2seq architecture of TranX for natural language to code translation, we identify four key components of importance: grammatical constraints, lexical preprocessing, input representations, and copy mecha…

Code GenerationCode TranslationDecoderTranslation