Machine Translation: Phrase-Based, Rule-Based and Neural Approaches with Linguistic Evaluation

Macketanz, Vivien; Avramidis, Eleftherios; Burchardt, Aljoscha; Helcl, Jindřich; Srivastava, Ankit

doi:10.1515/cait-2017-0014

Cited by 17 publications

(17 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, when tested in the reverse translation direction (i.e., English-to-German), a commercial NMT engine becomes the winner as far as term translation is concerned. In a similar experimental setup, Macketanz et al [28] reported that their PB-SMT system outperformed NMT on terminology translation on both in-domain (IT domain) and general domain test suites in an English-to-German translation task. Specia et al [29] carried out an error annotation process using the multidimensional quality metrics (MQM) error annotation framework [30] in an MT post-editing environment.…”

Section: Terminology Translation In Pb-smt and Nmtmentioning

confidence: 98%

“…For example, Huang et al [36] investigated term translation in a PB-SMT task and observed that more than 10% of high-frequency terms were incorrectly translated by their PB-SMT decoder, although the system's BLEU score was quite high, i.e., 63.0 BLEU. One common event in the above papers [27][28][29]31,32,35,36] was that the authors carried out a human evaluation in order to measure terminology translation quality in MT, which, as mentioned earlier, is subjective and a slow and expensive process. In this paper, we present a faster and less-expensive evaluation strategy for preparing a gold standard, based on which our metric, TermEval, can measure terminology translation quality in MT.…”

Section: Terminology Translation In Pb-smt and Nmtmentioning

confidence: 99%

See 1 more Smart Citation

Terminology Translation in Low-Resource Scenarios

2019

View full text Add to dashboard Cite

Term translation quality in machine translation (MT), which is usually measured by domain experts, is a time-consuming and expensive task. In fact, this is unimaginable in an industrial setting where customised MT systems often need to be updated for many reasons (e.g., availability of new training data, leading MT techniques). To the best of our knowledge, as of yet, there is no publicly-available solution to evaluate terminology translation in MT automatically. Hence, there is a genuine need to have a faster and less-expensive solution to this problem, which could help end-users to identify term translation problems in MT instantly. This study presents a faster and less expensive strategy for evaluating terminology translation in MT. High correlations of our evaluation results with human judgements demonstrate the effectiveness of the proposed solution. The paper also introduces a classification framework, TermCat, that can automatically classify term translation-related errors and expose specific problems in relation to terminology translation in MT. We carried out our experiments with a low resource language pair, English–Hindi, and found that our classifier, whose accuracy varies across the translation directions, error classes, the morphological nature of the languages, and MT models, generally performs competently in the terminology translation classification task.

show abstract

Section: Terminology Translation In Pb-smt and Nmtmentioning

confidence: 98%

Section: Terminology Translation In Pb-smt and Nmtmentioning

confidence: 99%

Terminology Translation in Low-Resource Scenarios

2019

View full text Add to dashboard Cite

show abstract

“…The machine Translation process can be broadly classified into the following approaches Machine Translation process can be broadly classified into Rule-based [5] [6] [7], Statisticalbased [8][9] [10] and Neural-based approaches [5] [11] [12]. For these approaches, the translation system is trained with a bilingual text corpus to get the desired output.…”

Section: Figure 1 Processing Of Rule-based Approachesmentioning

confidence: 99%

Towards a Context-Free Machine Universal Grammar (CF-MUG) in Natural Language Processing

Yang

Qin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In natural language processing, semantic document exchange ensures unambiguity and shares the same meaning for documents sender and receiver cross different natural languages (e.g., English to Chinese), this difference makes the translation between natural languages becomes complex and inaccurate. This paper proposed a novel framework of Context-Free Machine Universal Grammar which consists of local mode (sender and receiver) and mediation mode (Machine Universal Language) based on the concept of collaboration, the framework improves semantic unambiguity and accuracy in crossing language document, meanwhile makes document computer-readable through unique ID for each word or phrase. More importantly, inspired by grammatical case in linguistics, a novel Machine Universal Grammar provides a universal grammar that accepts all coming languages and improves semantic accuracy in natural language processing.

show abstract

“…The advantages of NMT and its challenges have been investigated from different angles in recent work (Koehn and Knowles, 2017;Toral and Sánchez-Cartagena, 2017;Farajian et al, 2017;Macketanz et al, 2017;Castilho et al, 2017a;Klubička et al, 2017;Bentivogli et al, 2018;Isabelle et al, 2017;Popović, 2017;Forcada, 2017;Castilho et al, 2017b;Junczys-Dowmunt et al, 2016;Klubička et al, 2018;Shterionov et al, 2017;Burchardt et al, 2017, inter alia), however, studies on interactive NMT, especially user studies involving human post-edits of NMT outputs, have so far not been presented.…”

Section: Related Workmentioning

confidence: 99%

A user-study on online adaptation of neural machine translation to human post-edits

Karimova

Simianer

Riezler

2018

Machine Translation

View full text Add to dashboard Cite

The advantages of neural machine translation (NMT) have been extensively validated for offline translation of several language pairs for different domains of spoken and written language. However, research on interactive learning of NMT by adaptation to human post-edits has so far been confined to simulation experiments. We present the first user study on online adaptation of NMT to user post-edits in the domain of patent translation. Our study involves 29 human subjects (translation students) whose post-editing effort and translation quality were measured on about 4,500 interactions of a human post-editor and a machine translation system integrating an online adaptive learning algorithm. Our experimental results show a significant reduction of human post-editing effort due to online adaptation in NMT according to several evaluation metrics, including hTER, hBLEU, and KSMR. Furthermore, we found significant improvements in BLEU/TER between NMT outputs and professional translations in granted patents, providing further evidence for the advantages of online adaptive NMT in an interactive setup.

show abstract

Machine Translation: Phrase-Based, Rule-Based and Neural Approaches with Linguistic Evaluation

Cited by 17 publications

References 15 publications

Terminology Translation in Low-Resource Scenarios

Terminology Translation in Low-Resource Scenarios

Towards a Context-Free Machine Universal Grammar (CF-MUG) in Natural Language Processing

A user-study on online adaptation of neural machine translation to human post-edits

Contact Info

Product

Resources

About