• ETRI Journal
• /
• v.43 no.5
• /
• pp.775-786
• /
• 2021

To translate in real time, a simultaneous translation system should determine when to stop reading source tokens and generate target tokens corresponding to a partial source sentence read up to that point. However, conventional attention-based neural machine translation (NMT) models cannot produce translations with adequate latency in online scenarios because they wait until a source sentence is completed to compute alignment between the source and target tokens. To address this issue, we propose a reinforced learning (RL)-based attention mechanism, the reinforced attention mechanism, which allows a neural translation model to jointly train the stopping criterion and a partial translation model. The proposed attention mechanism comprises two modules, one to ensure translation quality and the other to address latency. Different from previous RL-based simultaneous translation systems, which learn the stopping criterion from a fixed NMT model, the modules can be trained jointly with a novel reward function. In our experiments, the proposed model has better translation quality and comparable latency compared to previous models.

• The KIPS Transactions:PartB
• /
• v.19B no.3
• /
• pp.183-188
• /
• 2012

One of the major challenge for retrieval performance is the word mismatch between user's queries and documents in information retrieval. To solve the word mismatch problem, we propose a retrieval model based on the degree of association of query concept and word translation probabilities in translation-based model. The word translation probabilities are calculated based on the set of a sentence and its succeeding sentence pair. To validate the proposed method, we experimented on TREC AP test collection. The experimental results show that the proposed model achieved significant improvement over the language model and outperformed translation-based language model.

• Language and Information
• /
• v.2 no.1
• /
• pp.79-105
• /
• 1998

This paper aims to describe a German-Korean machine translation system for nominal phrases. Besides, we have two subgoals. First, we are going to revea linguistic differences between two languages and propose a language-informational method fo overcome the differences. The method is based on an integrated model of translation knowledge, efficient information structure, and concordance selection. Then, we will show the statistical results about translation experiment and its evaluation as an evidence for the adequacy of our linguistic method and translation system itself.

• Language and Information
• /
• v.2 no.1
• /
• pp.1-41
• /
• 1998

Evaluation of multilingual translation fundamentally involves measurement of meaning equivalences between the formally mapped discourses/texts of SL(source language) and TL(target language) both represented by a metalanguage called IL(interlingua). Unlike a usaal uni-directional MT(machine translation) model(e.g.:SL $\rightarrow$ analysis $\rightarrow$ transfer $\rightarrow$ generation $\rightarrow$ TL), a bi-directional(by 'negotiation') model(i.e.: SL $\rightarrow$ IL/S $\leftrightarrow$ IL $\leftrightarrow$ IL/T \leftarrow TL) is proposed here for the purpose of evaluating multilingual, not merely bilingual, translation. The IL, as conceived of in this study, is an English-based predicate logic represented in the framework of MRS(minimal recursion semantics), an MT-oriented off-shoot of HPSG(Head-driven Phrase Structure Grammar). In addition, a list of semantic and pragmatic checkpoints are set up, some being optional depending on the kind and use of the translation, so sa to have the evaluation of translation fine-grained by computing matching or mismatching of such checkpoints.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1535-1545
• /
• 2022

Sign language has completely different meaning depending on the direction of the hand or the change of facial expression even with the same gesture. In this respect, it is crucial to capture the spatial-temporal structure information of each movement. However, sign language translation studies based on Sign2Gloss2Text only convey comprehensive spatial-temporal information about the entire sign language movement. Consequently, detailed information (facial expression, gestures, and etc.) of each movement that is important for sign language translation is not emphasized. Accordingly, in this paper, we propose Spatial-temporal Keypoints Centered Sign2Gloss2Text Translation, named STKC-Sign2 Gloss2Text, to supplement the sequential and semantic information of keypoints which are the core of recognizing and translating sign language. STKC-Sign2Gloss2Text consists of two steps, Spatial Keypoints Embedding, which extracts 121 major keypoints from each image, and Temporal Keypoints Embedding, which emphasizes sequential information using Bi-GRU for extracted keypoints of sign language. The proposed model outperformed all Bilingual Evaluation Understudy(BLEU) scores in Development(DEV) and Testing(TEST) than Sign2Gloss2Text as the baseline, and in particular, it proved the effectiveness of the proposed methodology by achieving 23.19, an improvement of 1.87 based on TEST BLEU-4.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.32-46
• /
• 2023

Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.327-332
• /
• 2010

Word mismatch is the most significant problem that causes low performance in question classification, whose questions consist of only two or three words that expressed in many different ways. So, it is necessary to apply word association in question classification. In this paper, we propose question classification method using translation-based language model, which use word translation probabilities for question-question pair that is learned in the same category. In the experiment, we prove that translation probabilities of question-question pairs in the same category is more effective than question-answer pairs in total collection.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.27-35
• /
• 2021

Automatic post editing is a research field that aims to automatically correct errors in machine translation results. This research is mainly being focus on high resource language pairs, such as English-German. Recent APE studies are mainly adopting transfer learning based research, where pre-training language models, or translation models generated through self-supervised learning methodologies are utilized. While translation based APE model shows superior performance in recent researches, as such researches are conducted on the high resource languages, the same perspective cannot be directly applied to the low resource languages. In this work, we apply two transfer learning strategies to Korean-English APE studies and show that transfer learning with translation model can significantly improves APE performance.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.245-253
• /
• 2022

Commenced in 1954 by IBM, machine translation has expanded immensely, particularly in this period. Machine translation can be broken into seven main steps namely- token generation, analyzing morphology, lexeme, tagging Part of Speech, chunking, parsing, and disambiguation in words. Morphological analysis plays a major role when translating Indian languages to develop accurate parts of speech taggers and word sense. The paper presents various machine translation methods used by different researchers for Indian languages along with their performance and drawbacks. Further, the paper concentrates on parts of speech (POS) tagging in Marathi dialect using various methods such as rule-based tagging, unigram, bigram, and more. After careful study, it is concluded that for machine translation, parts of speech tagging is a major step. Also, for the Marathi language, the Hidden Markov Model gives the best results for parts of speech tagging with an accuracy of 93% which can be further improved according to the dataset.

• Journal of Advanced Marine Engineering and Technology
• /
• v.36 no.5
• /
• pp.683-693
• /
• 2012

Recently, statistical machine translation (SMT) has received many attention with ease of its implementation and maintenance. The goal of our works is to build bidirectional Korean-Japanese SMT system by using MOSES [1] system. We use Korean-Japanese bilingual corpus which is aligned per sentence to train the translation model and use a large raw corpus in each language to train each language model. The proposed system shows results comparable to those of a rule-based machine translation system. Most of errors are caused by noises occurred in each processing stage.