Papers by Ohad Rozen

2 papers
Answering Product-Questions by Utilizing Questions from Other Contextually Similar Products (2021.naacl-main)

Copied to clipboard

Challenge: Existing approaches to predict product-related questions fail for new or unpopular products . product-specific question answering is a popular service provided by many e-commerce websites .
Approach: They propose a framework for predicting the answer to product-related questions based on the answers of similar products.
Outcome: The proposed model outperforms baselines on some segments of product-related questions.
Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference (2021.starsem-1)

Copied to clipboard

Challenge: InferBERT is a method to enhance transformer-based inference models with relevant relational knowledge.
Approach: They propose to enhance transformer-based inference models with relevant relational knowledge by injecting relevant facts at test time into the model.
Outcome: The proposed method outperforms existing models on the challenge datasets while outperforming existing models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations