Search Results for author: Wessel Kraaij

Found 8 papers, 5 papers with code

Conversation-Aware Filtering of Online Patient Forum Messages

no code implementations SMM4H (COLING) 2020 Anne Dirkson, Suzan Verberne, Wessel Kraaij

We experiment with two approaches to add conversational context to a BERT model: a sequential CRF layer and manually engineered features.

Retrieval for Extremely Long Queries and Documents with RPRS: a Highly Efficient and Effective Transformer-based Re-Ranker

1 code implementation2 Mar 2023 Arian Askari, Suzan Verberne, Amin Abolghasemi, Wessel Kraaij, Gabriella Pasi

Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data, and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available.

Information Retrieval Retrieval

Injecting the BM25 Score as Text Improves BERT-Based Re-rankers

1 code implementation23 Jan 2023 Arian Askari, Amin Abolghasemi, Gabriella Pasi, Wessel Kraaij, Suzan Verberne

In this paper we propose a novel approach for combining first-stage lexical retrieval models and Transformer-based re-rankers: we inject the relevance score of the lexical model as a token in the middle of the input of the cross-encoder re-ranker.


Breaking BERT: Understanding its Vulnerabilities for Named Entity Recognition through Adversarial Attack

1 code implementation23 Sep 2021 Anne Dirkson, Suzan Verberne, Wessel Kraaij

Experimental results show that BERT models are vulnerable to variation in the entity context with 20. 2 to 45. 0% of entities predicted completely wrong and another 29. 3 to 53. 3% of entities predicted wrong partially.

Adversarial Attack Decision Making +3

TRECVID 2019: An Evaluation Campaign to Benchmark Video Activity Detection, Video Captioning and Matching, and Video Search & Retrieval

no code implementations21 Sep 2020 George Awad, Asad A. Butt, Keith Curtis, Yooyoung Lee, Jonathan Fiscus, Afzal Godil, Andrew Delgado, Jesse Zhang, Eliot Godard, Lukas Diduch, Alan F. Smeaton, Yvette Graham, Wessel Kraaij, Georges Quenot

The TREC Video Retrieval Evaluation (TRECVID) 2019 was a TREC-style video analysis and retrieval evaluation, the goal of which remains to promote progress in research and development of content-based exploitation and retrieval of information from digital video via open, metrics-based evaluation.

Action Detection Activity Detection +5

Lexical Normalization of User-Generated Medical Text

no code implementations WS 2019 Anne Dirkson, Suzan Verberne, Wessel Kraaij

In the medical domain, user-generated social media text is increasingly used as a valuable complementary knowledge source to scientific medical literature.

Lexical Normalization Mistake Detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.