scholarly journals “Bilingual Expert” Can Find Translation Errors

2019 ◽  
Vol 33 ◽  
pp. 6367-6374 ◽  
Author(s):  
Kai Fan ◽  
Jiayi Wang ◽  
Bo Li ◽  
Fengming Zhou ◽  
Boxing Chen ◽  
...  
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Language Model ◽  
Target Language ◽  
Quality Estimation ◽  
Parallel Corpora ◽  
Translation Quality ◽  
Expert Model ◽  
Parallel Data ◽  
Translation Errors

The performances of machine translation (MT) systems are usually evaluated by the metric BLEU when the golden references are provided. However, in the case of model inference or production deployment, golden references are usually expensively available, such as human annotation with bilingual expertise. In order to address the issue of translation quality estimation (QE) without reference, we propose a general framework for automatic evaluation of the translation output for the QE task in the Conference on Statistical Machine Translation (WMT). We first build a conditional target language model with a novel bidirectional transformer, named neural bilingual expert model, which is pre-trained on large parallel corpora for feature extraction. For QE inference, the bilingual expert model can simultaneously produce the joint latent representation between the source and the translation, and real-valued measurements of possible erroneous tokens based on the prior knowledge learned from parallel data. Subsequently, the features will further be fed into a simple Bi-LSTM predictive model for quality estimation. The experimental results show that our approach achieves the state-of-the-art performance in most public available datasets of WMT 2017/2018 QE task.

Statistical Machine Translation with Scarce Resources Using Morpho-syntactic Information

2004 ◽  
Vol 30 (2) ◽  
pp. 181-204 ◽  
Author(s):  
Sonja Nießen ◽  
Hermann Ney
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Training Data ◽  
Target Language ◽  
Linguistic Knowledge ◽  
Parallel Corpora ◽  
Scarce Resources ◽  
Translation Quality ◽  
Sentence Level ◽  
Statistical Systems

In statistical machine translation, correspondences between the words in the source and the target language are learned from parallel corpora, and often little or no linguistic knowledge is used to structure the underlying models. In particular, existing statistical systems for machine translation often treat different inflected forms of the same lemma as if they were independent of one another. The bilingual training data can be better exploited by explicitly taking into account the interdependencies of related inflected forms. We propose the construction of hierarchical lexicon models on the basis of equivalence classes of words. In addition, we introduce sentence-level restructuring transformations which aim at the assimilation of word order in related sentences. We have systematically investigated the amount of bilingual training data required to maintain an acceptable quality of machine translation. The combination of the suggested methods for improving translation quality in frameworks with scarce resources has been successfully tested: We were able to reduce the amount of bilingual training data to less than 10% of the original corpus, while losing only 1.6% in translation quality. The improvement of the translation results is demonstrated on two German-English corpora taken from the Verbmobil task and the Nespole! task.

Building and using multimodal comparable corpora for machine translation

2016 ◽  
Vol 22 (4) ◽  
pp. 603-625 ◽  
Author(s):  
HAITHEM AFLI ◽  
LOÏC BARRAULT ◽  
HOLGER SCHWENK
Keyword(s):  
Machine Translation ◽  
Web Sites ◽  
Statistical Machine Translation ◽  
Recognition System ◽  
Target Language ◽  
Translation System ◽  
Automatic Speech Recognition System ◽  
Parallel Corpora ◽  
Comparable Corpora ◽  
Parallel Data

AbstractIn recent decades, statistical approaches have significantly advanced the development of machine translation systems. However, the applicability of these methods directly depends on the availability of very large quantities of parallel data. Recent works have demonstrated that a comparable corpus can compensate for the shortage of parallel corpora. In this paper, we propose an alternative to comparable corpora containing text documents as resources for extracting parallel data: a multimodal comparable corpus with audio documents in source language and text document in target language, built fromEuronewsandTEDweb sites. The audio is transcribed by an automatic speech recognition system, and translated with a baseline statistical machine translation system. We then use information retrieval in a large text corpus in the target language in order to extract parallel sentences/phrases. We evaluate the quality of the extracted data on an English to French translation task and show significant improvements over a state-of-the-art baseline.

scholarly journals MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation

2019 ◽  
Vol 28 (3) ◽  
pp. 447-453 ◽  
Author(s):  
Sainik Kumar Mahata ◽  
Dipankar Das ◽  
Sivaji Bandyopadhyay
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Language Model ◽  
Target Language ◽  
Data Sets ◽  
Shared Task ◽  
Automatic Translation ◽  
External Data ◽  
Statistical Mt

Abstract Machine translation (MT) is the automatic translation of the source language to its target language by a computer system. In the current paper, we propose an approach of using recurrent neural networks (RNNs) over traditional statistical MT (SMT). We compare the performance of the phrase table of SMT to the performance of the proposed RNN and in turn improve the quality of the MT output. This work has been done as a part of the shared task problem provided by the MTIL2017. We have constructed the traditional MT model using Moses toolkit and have additionally enriched the language model using external data sets. Thereafter, we have ranked the phrase tables using an RNN encoder-decoder module created originally as a part of the GroundHog project of LISA lab.

Document Alignment for Generation of English-Punjabi Comparable Corpora from Wikipedia

2020 ◽  
Vol 12 (1) ◽  
pp. 42-51
Author(s):  
Vishal Goyal ◽  
Ajit Kumar ◽  
Manpreet Singh Lehal
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Parallel Corpora ◽  
Comparable Corpora ◽  
Potential Source ◽  
Parallel Data

Comparable corpora come as an alternative to parallel corpora for the languages where the parallel corpora is scarce. The efficiency of the models trained on comparable corpora is comparatively less to that of the parallel corpora however it helps to compensate much to the machine translation. In this article, the authors have explored Wikipedia as a potential source and delineated the process of alignment of documents which will be further used for the extraction of parallel data. The parallel data thus extracted will help to enhance the performance of Statistical Machine translation.

scholarly journals Improving Neural Machine Translation by Filtering Synthetic Parallel Data

Entropy ◽  
2019 ◽  
Vol 21 (12) ◽  
pp. 1213
Author(s):  
Guanghao Xu ◽  
Youngjoong Ko ◽  
Jungyun Seo
Keyword(s):  
Machine Translation ◽  
Synthetic Data ◽  
Similarity Score ◽  
Target Language ◽  
Neural Machine Translation ◽  
Novel Approach ◽  
Parallel Data ◽  
Back Translation ◽  
Translation Errors ◽  
Training State

Synthetic data has been shown to be effective in training state-of-the-art neural machine translation (NMT) systems. Because the synthetic data is often generated by back-translating monolingual data from the target language into the source language, it potentially contains a lot of noise—weakly paired sentences or translation errors. In this paper, we propose a novel approach to filter this noise from synthetic data. For each sentence pair of the synthetic data, we compute a semantic similarity score using bilingual word embeddings. By selecting sentence pairs according to these scores, we obtain better synthetic parallel data. Experimental results on the IWSLT 2017 Korean→English translation task show that despite using much less data, our method outperforms the baseline NMT system with back-translation by up to 0.72 and 0.62 Bleu points for tst2016 and tst2017, respectively.

scholarly journals Improving Machine Translation Performance by Exploiting Non-Parallel Corpora

2005 ◽  
Vol 31 (4) ◽  
pp. 477-504 ◽  
Author(s):  
Dragos Stefan Munteanu ◽  
Daniel Marcu
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Translation System ◽  
Parallel Corpora ◽  
Parallel Corpus ◽  
Scarce Resources ◽  
Parallel Data ◽  
Machine Translation System ◽  
Novel Method ◽  
Arabic And English

We present a novel method for discovering parallel sentences in comparable, non-parallel corpora. We train a maximum entropy classifier that, given a pair of sentences, can reliably determine whether or not they are translations of each other. Using this approach, we extract parallel data from large Chinese, Arabic, and English non-parallel newspaper corpora. We evaluate the quality of the extracted data by showing that it improves the performance of a state-of-the-art statistical machine translation system. We also show that a good-quality MT system can be built from scratch by starting with a very small parallel corpus (100,000 words) and exploiting a large non-parallel corpus. Thus, our method can be applied with great benefit to language pairs for which only scarce resources are available.

scholarly journals Predicting and Using a Pragmatic Component of Lexical Aspect

2016 ◽  
Vol 13 ◽  
Author(s):  
Sharid Loáiciga ◽  
Cristina Grisot
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Translation System ◽  
Automatic Annotation ◽  
Parallel Corpora ◽  
Linguistic Data ◽  
Lexical Aspect ◽  
Machine Translation System ◽  
Automatic Systems

This paper proposes a method for improving the results of a statistical Machine Translation system using boundedness, a pragmatic component of the verbal phrase’s lexical aspect. First, the paper presents manual and automatic annotation experiments for lexical aspect in English-French parallel corpora. It will be shown that this aspectual property is identified and classified with ease both by humans and by automatic systems. Second, Statistical Machine Translation experiments using the boundedness annotations are presented. These experiments show that the information regarding lexical aspect is useful to improve the output of a Machine Translation system in terms of better choices of verbal tenses in the target language, as well as better lexical choices. Ultimately, this work aims at providing a method for the automatic annotation of data with boundedness information and at contributing to Machine Translation by taking into account linguistic data.

scholarly journals Topic-Based Dissimilarity and Sensitivity Models for Translation Rule Selection

2014 ◽  
Vol 50 ◽  
pp. 1-30 ◽  
Author(s):  
M. Zhang ◽  
X. Xiao ◽  
D. Xiong ◽  
Q. Liu
Keyword(s):  
Machine Translation ◽  
Topic Model ◽  
Statistical Machine Translation ◽  
Model Space ◽  
Target Language ◽  
Translation Quality ◽  
Rule Selection ◽  
Translation Rule ◽  
Selection Experiments ◽  
Target Side

Translation rule selection is a task of selecting appropriate translation rules for an ambiguous source-language segment. As translation ambiguities are pervasive in statistical machine translation, we introduce two topic-based models for translation rule selection which incorporates global topic information into translation disambiguation. We associate each synchronous translation rule with source- and target-side topic distributions.With these topic distributions, we propose a topic dissimilarity model to select desirable (less dissimilar) rules by imposing penalties for rules with a large value of dissimilarity of their topic distributions to those of given documents. In order to encourage the use of non-topic specific translation rules, we also present a topic sensitivity model to balance translation rule selection between generic rules and topic-specific rules. Furthermore, we project target-side topic distributions onto the source-side topic model space so that we can benefit from topic information of both the source and target language. We integrate the proposed topic dissimilarity and sensitivity model into hierarchical phrase-based machine translation for synchronous translation rule selection. Experiments show that our topic-based translation rule selection model can substantially improve translation quality.

scholarly journals Corpus Augmentation for Neural Machine Translation with Chinese-Japanese Parallel Corpora

2019 ◽  
Vol 9 (10) ◽  
pp. 2036
Author(s):  
Jinyi Zhang ◽  
Tadahiro Matsumoto
Keyword(s):  
Machine Translation ◽  
Scientific Paper ◽  
Training Data ◽  
Word Alignment ◽  
Sentence Pair ◽  
Neural Machine Translation ◽  
Parallel Corpora ◽  
Translation Quality ◽  
Parallel Data ◽  
Source Sentence

The translation quality of Neural Machine Translation (NMT) systems depends strongly on the training data size. Sufficient amounts of parallel data are, however, not available for many language pairs. This paper presents a corpus augmentation method, which has two variations: one is for all language pairs, and the other is for the Chinese-Japanese language pair. The method uses both source and target sentences of the existing parallel corpus and generates multiple pseudo-parallel sentence pairs from a long parallel sentence pair containing punctuation marks as follows: (1) split the sentence pair into parallel partial sentences; (2) back-translate the target partial sentences; and (3) replace each partial sentence in the source sentence with the back-translated target partial sentence to generate pseudo-source sentences. The word alignment information, which is used to determine the split points, is modified with “shared Chinese character rates” in segments of the sentence pairs. The experiment results of the Japanese-Chinese and Chinese-Japanese translation with ASPEC-JC (Asian Scientific Paper Excerpt Corpus, Japanese-Chinese) show that the method substantially improves translation performance. We also supply the code (see Supplementary Materials) that can reproduce our proposed method.

scholarly journals Synthesizing Parallel Data of User-Generated Texts with Zero-Shot Neural Machine Translation

2020 ◽  
Vol 8 ◽  
pp. 710-725
Author(s):  
Benjamin Marie ◽  
Atsushi Fujita
Keyword(s):  
Social Media ◽  
Machine Translation ◽  
Language Model ◽  
The Other ◽  
Neural Machine Translation ◽  
Translation Quality ◽  
Online Social Media ◽  
Parallel Data

Neural machine translation (NMT) systems are usually trained on clean parallel data. They can perform very well for translating clean in-domain texts. However, as demonstrated by previous work, the translation quality significantly worsens when translating noisy texts, such as user-generated texts (UGT) from online social media. Given the lack of parallel data of UGT that can be used to train or adapt NMT systems, we synthesize parallel data of UGT, exploiting monolingual data of UGT through crosslingual language model pre-training and zero-shot NMT systems. This paper presents two different but complementary approaches: One alters given clean parallel data into UGT-like parallel data whereas the other generates translations from monolingual data of UGT. On the MTNT translation tasks, we show that our synthesized parallel data can lead to better NMT systems for UGT while making them more robust in translating texts from various domains and styles.

Sign in / Sign up

Export Citation Format

Share Document