paper-with-me

홈 › Papers

Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation

2019-07-14 · WS 2019 8 · Marcin Junczys-Dowmunt

This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong sentence-level baselines, trained on large-scale data created via data-filtering and noisy back-translation and find that back-translation seems to mainly help with translationese input. We explore fine-tuning techniques, deeper models and different ensembling strategies to counter these effects. Using document boundaries present in the authentic and synthetic parallel data, we create sequences of up to 1000 subword segments and train transformer translation models. We experiment with data augmentation techniques for the smaller authentic data with document-boundaries and for larger authentic data without boundaries. We further explore multi-task training for the incorporation of document-level source language monolingual data via the BERT-objective on the encoder and two-pass decoding for combinations of sentence-level and document-level systems. Based on preliminary human evaluation results, evaluators strongly prefer the document-level systems over our comparable sentence-level system. The document-level systems also seem to score higher than the human references in source-based direct assessment.

📄 PDF Abstract BibTeX arXiv:1907.06170

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationMachine TranslationSentenceTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Detecting Cross-Lingual Plagiarism Using Simulated Word Embeddings

2017-12-29 · Victor Thompson

Cross-lingual plagiarism (CLP) occurs when texts written in one language are translated into a different language and used without acknowledging the original sources. One of the most common methods for detecting CLP requ…

Word Embeddings

Large language models effectively leverage document-level context for literary translation, but critical errors persist

2023-04-06 · Marzena Karpinska, Mohit Iyyer

Large language models (LLMs) are competitive with the state of the art on a wide range of sentence-level translation datasets. However, their ability to translate paragraphs and documents remains unexplored because evalu…

SentenceTranslation

On the Same Page? Comparing Inter-Annotator Agreement in Sentence and Document Level Human Machine Translation Evaluation

2020-11-01 · WMT (EMNLP) 2020 11 · Sheila Castilho

Document-level evaluation of machine translation has raised interest in the community especially since responses to the claims of “human parity” (Toral et al., 2018; Läubli et al., 2018) with document-level human evaluat…

Machine TranslationSentenceTranslation

Automatic Construction of Enterprise Knowledge Base

2021-06-29 · EMNLP (ACL) 2021 11 · Junyi Chai, Yujie He, Homa Hashemi, Bing Li 외

In this paper, we present an automatic knowledge base construction system from large scale enterprise documents with minimal efforts of human intervention. In the design and deployment of such a knowledge mining system f…

Knowledge Base Construction

Static Ranking of Scholarly Papers using Article-Level Eigenfactor (ALEF)

2016-06-28 · Wesley-Smith Ian, Bergstrom Carl T., West Jevin D.

Microsoft Research hosted the 2016 WSDM Cup Challenge based on the Microsoft Academic Graph. The goal was to provide static rankings for the articles that make up the graph, with the rankings to be evaluated against thos…

Articles