Research

Projects

Birch

Document retrieval system based on sentence modeling with BERT

Sparksolrini

Apache Solr integration with Apache Spark for scalable text analytical applications

Tardis

Framework for distributed ensembles of seq2seq models with Keras and PySpark

Multimodal Shared Latent Space

Deep neural architecture to construct a shared latent space for three modalities (text, speech and video) and perform inference on an unseen modality from the aligned vector


Publications

[1] Zeynep Akkalyoncu Yilmaz, Wei Yang, Haotian Zhang, Jimmy Lin. 2019. Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval. (EMNLP-ICJNLP ‘19).

[2] Zeynep Akkalyoncu Yilmaz, Shengjin Wang, Wei Yang, Haotian Zhang, Jimmy Lin. 2019. Applying BERT to Document Retrieval with Birch. (EMNLP-ICJNLP ‘19)

[3] Ryan Clancy, Jaejun Lee, Zeynep Akkalyoncu Yilmaz, and Jimmy Lin. 2019. Information Retrieval Meets Scalable Text Analytics: Solr Integration with Spark. (SIGIR ’19).