Výsledky vyhledávání - "Biçici, Ergun"

Report

Predicting Word Similarity in Context with Referential Translation Machines

Autor: Biçici, Ergun

We identify the similarity between two words in English by casting the task as machine translation performance prediction (MTPP) between the words given the context and the distance between their similarities. We use referential translation machines

Externí odkaz: http://arxiv.org/abs/2407.06230

Zobrazit plný text záznamu

Report

Identifying Intensity of the Structure and Content in Tweets and the Discriminative Power of Attributes in Context with Referential Translation Machines

Autor: Biçici, Ergun

We use referential translation machines (RTMs) to identify the similarity between an attribute and two words in English by casting the task as machine translation performance prediction (MTPP) between the words and the attribute word and the distance

Externí odkaz: http://arxiv.org/abs/2407.05154

Zobrazit plný text záznamu

Report

Automatic Prediction of the Performance of Every Parser

Autor: Biçici, Ergun

We present a new parser performance prediction (PPP) model using machine translation performance prediction system (MTPPS), statistically independent of any language or parser, relying only on extrinsic and novel features based on textual, link struc

Externí odkaz: http://arxiv.org/abs/2407.05116

Zobrazit plný text záznamu

Report

Sparse Regression for Machine Translation

Autor: Biçici, Ergun

We use transductive regression techniques to learn mappings between source and target features of given parallel corpora and use these mappings to generate machine translation outputs. We show the effectiveness of $L_1$ regularized regression (\texti

Externí odkaz: http://arxiv.org/abs/2406.19478

Zobrazit plný text záznamu

Report

Extreme Learning Machines for Fast Training of Click-Through Rate Prediction Models

Autor: Biçici, Ergun

Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities. Its theoretical basis shows its universal approximation capability.

Externí odkaz: http://arxiv.org/abs/2406.17828

Zobrazit plný text záznamu