Post

Today we will present our poster on Query Variation Robustness of Transformer Models at #EMNLP2024. You can find us at the Information Retrieval and Text Mining 3 poster session at #EMNLP2024.

We find that simply scaling up the transformer architecture still leads to significant effectiveness drops in face of typos, keywords, ordering, and paraphrasing. We further highlight the need for more elaborate query variation datasets, which should retain the queries' semantics.