6 papers
Mitigating Early Training Collapse in CTR Models
Ergun Biçici, Erkan Çetinyamaç
Deep neural models for click-through rate prediction often exhibit a sharp decline in validation performance immediately after the first training epoch despite continued improvemen…
Predicting Word Similarity in Context with Referential Translation Machines
Ergun Biçici
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 distanc…
Identifying Intensity of the Structure and Content in Tweets and the Discriminative Power of Attributes in Context with Referential Translation Machines
Ergun Biçici
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 predi…
Automatic Prediction of the Performance of Every Parser
Ergun Biçici
We present a new parser performance prediction (PPP) model using machine translation performance prediction system (MTPPS), statistically independent of any language or parser, rel…
Sparse Regression for Machine Translation
Ergun Biçici
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 outp…
Extreme Learning Machines for Fast Training of Click-Through Rate Prediction Models
Ergun Biçici
Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities…