paper-with-me

Papers

Bilingual Dictionary-based Language Model Pretraining for Neural Machine Translation

2021-03-12 · Yusen Lin, Jiayong Lin, Shuaicheng Zhang, Haoying Dai

Recent studies have demonstrated a perceivable improvement on the performance of neural machine translation by applying cross-lingual language model pretraining (Lample and Conneau, 2019), especially the Translation Language Modeling (TLM). To alleviate the need for expensive parallel corpora by TLM, in this work, we incorporate the translation information from dictionaries into the pretraining process and propose a novel Bilingual Dictionary-based Language Model (BDLM). We evaluate our BDLM in Chinese, English, and Romanian. For Chinese-English, we obtained a 55.0 BLEU on WMT-News19 (Tiedemann, 2012) and a 24.3 BLEU on WMT20 news-commentary, outperforming the Vanilla Transformer (Vaswani et al., 2017) by more than 8.4 BLEU and 2.3 BLEU, respectively. According to our results, the BDLM also has advantages on convergence speed and predicting rare words. The increase in BLEU for WMT16 Romanian-English also shows its effectiveness in low-resources language translation.

📄 PDF Abstract BibTeX arXiv:2103.07040

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMachine TranslationTranslation

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
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…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention 설명 없음
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…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences

2020-07-06 · ACL 2020 6 · Xiangyu Duan, Baijun Ji, Hao Jia, Min Tan 외

In this paper, we propose a new task of machine translation (MT), which is based on no parallel sentences but can refer to a ground-truth bilingual dictionary. Motivated by the ability of a monolingual speaker learning t…

Machine TranslationTranslationWord Translation

Dict-NMT: Bilingual Dictionary based NMT for Extremely Low Resource Languages

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Neural Machine Translation (NMT) models have been effective on large bilingual datasets. However, the existing methods and techniques show that the model's performance is highly dependent on the number of examples in tra…

Machine TranslationNMTTranslation

Mining Bilingual Word Pairs from Comparable Corpus using Apache Spark Framework

2021-09-01 · RANLP (BUCC) 2021 9 · Sanjanasri JP, Vijay Krishna Menon, Soman Kp, Krzysztof Wolk

Bilingual dictionaries are essential resources in many areas of natural language processing tasks, but resource-scarce and less popular language pairs rarely have such. Efficient automatic methods for inducting bilingual…

Machine TranslationNMTTranslation

On the Limitations of Unsupervised Bilingual Dictionary Induction

2018-05-09 · ACL 2018 7 · Anders Søgaard, Sebastian Ruder, Ivan Vulić

Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently pr…

Graph SimilarityMachine TranslationTranslationUnsupervised Machine Translation

Bridging Neural Machine Translation and Bilingual Dictionaries

2016-10-24 · Jiajun Zhang, Cheng-qing Zong

Neural Machine Translation (NMT) has become the new state-of-the-art in several language pairs. However, it remains a challenging problem how to integrate NMT with a bilingual dictionary which mainly contains words rarel…

Machine TranslationNMTSentenceTranslation