Effect of Word Sense Disambiguation on Neural Machine Translation: A Case Study in Korean

Nguyen, Quang-Phuoc; Vo, Anh-Dung; Shin, Joon-Choul; Ock, Cheol-Young

doi:10.1109/access.2018.2851281

Cited by 25 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nguyen et al [21] built a lexical network to resolve the disambiguation of Korean, same pronunciation on different meaning words. This will be helpful to improve the deep learningbased model by inferring exact meaning of a word from the lexical network.…”

Section: Text Mining For Korean Languagementioning

confidence: 99%

Profane or Not: Improving Korean Profane Detection using Deep Learning

2022

KSII TIIS

View full text Add to dashboard Cite

Abusive behaviors have become a common issue in many online social media platforms. Profanity is common form of abusive behavior in online. Social media platforms operate the filtering system using popular profanity words lists, but this method has drawbacks that it can be bypassed using an altered form and it can detect normal sentences as profanity. Especially in Korean language, the syllable is composed of graphemes and words are composed of multiple syllables, it can be decomposed into graphemes without impairing the transmission of meaning, and the form of a profane word can be seen as a different meaning in a sentence. This work focuses on the problem of filtering system mis-detecting normal phrases with profane phrases. For that, we proposed the deep learning-based framework including grapheme and syllable separation-based word embedding and appropriate CNN structure. The proposed model was evaluated on the chatting contents from the one of the famous online games in South Korea and generated 90.4% accuracy.

show abstract

Section: Text Mining For Korean Languagementioning

confidence: 99%

Profane or Not: Improving Korean Profane Detection using Deep Learning

2022

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…Even advanced methods, such as statistical-based [38], deep learning-based with recurrent neural networks [39], and embedded word space [40] methods, still encounter the missing data problem because of limited training corpora. Knowledge-based approaches can overcome this problem, but they require an accurate and large lexical network [41], [42]. Korean WordNet KorLex [21], which was constructed by translating English WordNet to Korean, is either used as a knowledge base [43] or combined with the Korean monolingual dictionary [44].…”

Section: Sub-word Conditional Probabilitymentioning

confidence: 99%

Korean-Vietnamese Neural Machine Translation System With Korean Morphological Analysis and Word Sense Disambiguation

Nguyen

Shin

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Although deep neural networks have recently led to great achievements in machine translation (MT), various challenges are still encountered during the development of Korean-Vietnamese MT systems. Because Korean is a morphologically rich language and Vietnamese is an analytic language, neither have clear word boundaries. The high rate of homographs in Korean causes word ambiguities, which causes problems in neural MT (NMT). In addition, as a low-resource language pair, there is no freely available, adequate Korean-Vietnamese parallel corpus that can be used to train translation models. In this paper, we manually established a lexical semantic network for the special characteristics of Korean as a knowledge base that was used for developing our Korean morphological analysis and word-sense disambiguation system: UTagger. We also constructed a large Korean-Vietnamese parallel corpus, in which we applied the state-of-the-art Vietnamese word segmentation method RDRsegmenter to Vietnamese texts and UTagger to Korean texts. Finally, we built a bi-directional Korean-Vietnamese NMT system based on the attentionbased encoder-decoder architecture. The experimental results indicated that UTagger and RDRsegmenter could significantly improve the performance of the Korean-Vietnamese NMT system, achieving remarkable results by 27.79 BLEU points and 58.77 TER points in Korean-to-Vietnamese direction and 25.44 BLEU points and 58.72 TER points in the reverse direction. INDEX TERMS Korean-Vietnamese machine translation, Korean-Vietnamese parallel corpus, lexical semantic network, morphological analysis, neural machine translation, word sense disambiguation. I. INTRODUCTION Neural machine translation based on the attention-based encoder-decoder model [1], [2] has emerged as the dominant paradigm in MT. It has achieved state-of-the-art performance in the translation of language pairs that have large amounts of training parallel corpora, such as English-French [3] and English-German [4]. However, it has shown poor translation quality in low-resource language pairs where training parallel corpora are scarce [5], [6]. Korean-Vietnamese is a low-resource language pair, and Korean-Vietnamese MT systems need to be built to serve The associate editor coordinating the review of this manuscript and approving it for publication was Yang Zhen.

show abstract

“…As mentioned before, the global image features( v im ) are defined as the 4096-size vector in the fc7 layer of VGG19. Then, the cell reads the global visual features corresponding to the current caption and incorporates them with the previously encoded source caption per (9).…”

Section: Image Encodingmentioning

confidence: 99%

Multimodal Neural Machine Translation With Weakly Labeled Images

2019

View full text Add to dashboard Cite

Machine translation refers to a fully automated process that translates a user's input text into a target language. To improve the accuracy of machine translation, studies usually exploit not only the input text itself but also various background knowledge related to the text, such as visual information or prior knowledge. Herein, in this paper, we propose a multimodal neural machine translation system that uses both texts and their related images to translate Korean image captions into English. The data in the experiment is a set of unlabeled images only containing bilingual captions. To train the system with a supervised learning approach, we propose a weak-labeling method that selects a keyword from an image caption using feature selection methods. The keywords are used to roughly determine an image label. We also introduce an improved feature selection method using sentence clustering to select keywords that reflect the characteristics of the image captions more accurately. We found that our multimodal system achieves an improved performance compared to a text-only neural machine translation system (baseline). Furthermore, the additional images have positive impacts on addressing the issue of under-translation, where some words in a source sentence are falsely translated or not translated at all. INDEX TERMS Human-computer interaction, multi-layer neural network, natural language processing, image classification, multimodal neural machine translation, weak label.

show abstract

Effect of Word Sense Disambiguation on Neural Machine Translation: A Case Study in Korean

Cited by 25 publications

References 22 publications

Profane or Not: Improving Korean Profane Detection using Deep Learning

Profane or Not: Improving Korean Profane Detection using Deep Learning

Korean-Vietnamese Neural Machine Translation System With Korean Morphological Analysis and Word Sense Disambiguation

Multimodal Neural Machine Translation With Weakly Labeled Images

Contact Info

Product

Resources

About