Word Embeddings Evaluation on Indonesian Translation of AI-Quran and Hadiths
نویسندگان
چکیده
منابع مشابه
Translation Invariant Word Embeddings
This work focuses on the task of finding latent vector representations of the words in a corpus. In particular, we address the issue of what to do when there are multiple languages in the corpus. Prior work has, among other techniques, used canonical correlation analysis to project pre-trained vectors in two languages into a common space. We propose a simple and scalable method that is inspired...
متن کاملModifications of Machine Translation Evaluation Metrics by Using Word Embeddings
Traditional machine translation evaluation metrics such as BLEU and WER have been widely used, but these metrics have poor correlations with human judgements because they badly represent word similarity and impose strict identity matching. In this paper, we propose some modifications to the traditional measures based on word embeddings for these two metrics. The evaluation results show that our...
متن کاملthe role of semantic and communicative translation on reading comprehension of scientific texts
the following null hypothesis was proposed: h : there is no significant difference between the use of semantically or communicatively translates scientific texts. to test the null hypothesis, a number of procedures were taken first, two passages were selected form soyrcebooks of food and nutrition industry and gardening deciplines. each, in turn, was following by a number of comprehension quest...
15 صفحه اولThe Meaning of the Word Tamhis in the Holy Quran and in the Hadiths of the Infallibles (a.s.)
Ebtela’ (affliction) and emtehan (examination) are among the divine traditions in the field of Quranic studies, and many verses in the holy Quran deal with them. This research work has been conducted using the analytical-descriptive method and by referring to the commentaries of the Quran and the hadiths of the Infallibles (a.s.), and it aims to find out what the word tamhis conceptually means ...
متن کاملGeographical Evaluation of Word Embeddings
Word embeddings are commonly compared either with human-annotated word similarities or through improvements in natural language processing tasks. We propose a novel principle which compares the information from word embeddings with reality. We implement this principle by comparing the information in the word embeddings with geographical positions of cities. Our evaluation linearly transforms th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IOP Conference Series: Materials Science and Engineering
سال: 2021
ISSN: 1757-8981,1757-899X
DOI: 10.1088/1757-899x/1077/1/012025