Enerji Harcamalarını Azaltmak için Bulut Monitorü A Cloud Monitor for Reducing Energy Consumption

Ergun Biçici. Enerji Harcamalarını Azaltmak için Bulut Monitorü (A Cloud Monitor for Reducing Energy Consumption). In Proc. of the First Symposium on Cloud Computing and Big Data (B3S17), Antalya, Turkey, pages 117-122, 10 2017. TÜRKİYE BİLİMSEL ve TEKNOLOJİK ARAŞTIRMA KURUMU (TÜBITAK). [WWW] [bibtex-entry]

B3S'17: 1. Ulusal Bulut Bilişim ve Büyük Veri Sempozyumu (http://www.b3s.b3lab.org/)

World class organization at the top touristic place and venue about cloud computing, big data, machine learning, and related applications.

Predicting Translation Performance with Referential Translation Machines

Ergun Biçici. Predicting Translation Performance with Referential Translation Machines. In Proc. of the Second Conference on Statistical Machine Translation (WMT17), Copenhagen, Denmark, September 2017. Association for Computational Linguistics.  [WWW] Keyword(s): Machine Translation, Machine Learning, Performance Prediction.

Referential translation machines achieve top performance in both bilingual and monolingual settings without accessing any task or domain specific information or resource. RTMs achieve the 3rd system results for German to English sentence-level prediction of translation quality and the 2nd system results according to root mean squared error. In addition to the new features about substring distances, punctuation tokens, character n-grams, and alignment crossings, and additional learning models, we average prediction scores from different models using weights based on their training performance for improved results.

RTM Performance Prediction Results

RTM Performance Prediction Results:

http://bicici.github.io/Projects/RTM_prediction_performance.html

RTM at SemEval-2017 Task 1: Referential Translation Machines for Predicting Semantic Similarity

Ergun Biçici. RTM at SemEval-2017 Task 1: Referential Translation Machines for Predicting Semantic Similarity. In SemEval-2017: Semantic Evaluation Exercises - International Workshop on Semantic Evaluation, Vancouver, Canada, August 2017. [WWW] 

We use referential translation machines for predicting the semantic similarity of text in all STS tasks which contain Arabic, English, Spanish, and Turkish this year. RTMs pioneer a language independent approach to semantic similarity and remove the need to access any task or domain specific information or resource. RTMs become 6th out of 52 submissions in Spanish to English STS. We average prediction scores using weights based on the training performance to improve the overall performance.