Extraction Method of Machine Translation Equivalent Pairs in Chinese-English Comparable Corpus based on Text Mining

Author(s):  
Zheng Luo
2020 ◽  
pp. 1686-1704
Author(s):  
Emna Hkiri ◽  
Souheyl Mallat ◽  
Mounir Zrigui

The event extraction task consists in determining and classifying events within an open-domain text. It is very new for the Arabic language, whereas it attained its maturity for some languages such as English and French. Events extraction was also proved to help Natural Language Processing tasks such as Information Retrieval and Question Answering, text mining, machine translation etc… to obtain a higher performance. In this article, we present an ongoing effort to build a system for event extraction from Arabic texts using Gate platform and other tools.


Author(s):  
Qingchao Yang ◽  
Jingjun Lou ◽  
Shuyong Liu ◽  
Aimin Diao

2021 ◽  
Vol 27 (1) ◽  
pp. 55-70
Author(s):  
Frans Sayogie ◽  
Moh. Supardi

Machine translation has the potential to make huge contributions to translation industries, but it seems, for now, that machine translation equivalence has led to a crucial point for literary translation by using machine translation because of the problem of the equivalence itself. This paper, therefore, aimed to see the equivalence degree of literary translation resulted by machine translation, i.e., freeware toolkit AntConc 3.5.0 software 2019. The data were collected from English-Indonesian J.K. Rowling's Harry Potter and The Order of The Phoenix novel by using the software to find the equivalent translation. The collected data were analyzed qualitatively based on the strategy of translation equivalent level proposed by Mona Baker (1992). The analyzed data revealed that the equivalent level of the software mostly occurred in a word level, above word level, and grammatical level. The software was likely difficult to find a textual level and a pragmatic level of translation equivalence because they required a context and still needed human involvement as part of a greater creative project of translation which were not done by the machine translation. After all, Antconc 3.5.0 as Computer Assisted Tool (CAT) brought a huge contribution to translation industry, helped to analyze large corpora particularly to find the degree of translation equivalence in word and above word level.


Terminology ◽  
2000 ◽  
Vol 6 (2) ◽  
pp. 287-311 ◽  
Author(s):  
Jong-Hoon Oh ◽  
Juho Lee ◽  
Kyung-Soon Lee ◽  
Key-Sun Choi

There have been many studies of automatic term recognition (ATR) and they have achieved good results. However, they focus on a mono-lingual term extraction method. Therefore, it is difficult to extract terms from documents in foreign languages. This article describes an automatic term extraction method from documents in foreign languages using a machine translation system. In our method, we translate documents in foreign languages into documents in Korean and extract terms in the translated Korean documents. Finally the terms recognized from the Korean documents are translated into terms in the foreign language. By using our method, one can extract terms for languages, which one does not know.


2020 ◽  
Vol 34 (01) ◽  
pp. 59-66
Author(s):  
Yang Feng ◽  
Wanying Xie ◽  
Shuhao Gu ◽  
Chenze Shao ◽  
Wen Zhang ◽  
...  

Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution. However, the strategy casts all the portion of the distribution to the ground truth word and ignores other words in the target vocabulary even when the ground truth word cannot dominate the distribution. To address the problem of teacher forcing, we propose a method to introduce an evaluation module to guide the distribution of the prediction. The evaluation module accesses each prediction from the perspectives of fluency and faithfulness to encourage the model to generate the word which has a fluent connection with its past and future translation and meanwhile tends to form a translation equivalent in meaning to the source. The experiments on multiple translation tasks show that our method can achieve significant improvements over strong baselines.


Author(s):  
Douglas C. Barker

A number of satisfactory methods are available for the electron microscopy of nicleic acids. These methods concentrated on fragments of nuclear, viral and mitochondrial DNA less than 50 megadaltons, on denaturation and heteroduplex mapping (Davies et al 1971) or on the interaction between proteins and DNA (Brack and Delain 1975). Less attention has been paid to the experimental criteria necessary for spreading and visualisation by dark field electron microscopy of large intact issociations of DNA. This communication will report on those criteria in relation to the ultrastructure of the (approx. 1 x 10-14g) DNA component of the kinetoplast from Trypanosomes. An extraction method has been developed to eliminate native endonucleases and nuclear contamination and to isolate the kinetoplast DNA (KDNA) as a compact network of high molecular weight. In collaboration with Dr. Ch. Brack (Basel [nstitute of Immunology), we studied the conditions necessary to prepare this KDNA Tor dark field electron microscopy using the microdrop spreading technique.


Sign in / Sign up

Export Citation Format

Share Document