Publications

6 entries · newest first

1. 2026

   Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe

   Gaofei Shen, Martijn Bentum, Tom Lentz, Afra Alishahi, Grzegorz Chrupała

   EMNLP 2026 (accepted)

   • arXiv 2605.00607
   • Code

2. 2026

   Tracking the Emergence of Linguistic Structure in Self-Supervised Models Learning from Speech

   Marianne de Heer Kloots, Martijn Bentum, Hosein Mohebbi, Charlotte Pouw, Gaofei Shen, Willem Zuidema

   arXiv preprint

   • arXiv 2604.02043

3. 2025

   What Do Self-Supervised Speech Models Know about Dutch? Analyzing Advantages of Language-Specific Pre-Training

   Marianne de Heer Kloots, Hosein Mohebbi, Charlotte Pouw, Gaofei Shen, Willem Zuidema, Martijn Bentum

   Interspeech 2025·pp. 256–260

   • DOI
   • arXiv 2506.00981
   • Code

4. 2025

   On the Reliability of Feature Attribution Methods for Speech Classification

   Gaofei Shen, Hosein Mohebbi, Arianna Bisazza, Afra Alishahi, Grzegorz Chrupała

   Interspeech 2025·pp. 266–270

   • DOI
   • arXiv 2505.16406
   • Code

5. 2024

   Encoding of Lexical Tone in Self-Supervised Models of Spoken Language

   Gaofei Shen, Michaela Watkins, Afra Alishahi, Arianna Bisazza, Grzegorz Chrupała

   NAACL-HLT 2024·pp. 4250–4261

   • DOI
   • arXiv 2403.16865
   • Code

6. 2023

   Wave to Syntax: Probing Spoken Language Models for Syntax

   Gaofei Shen, Afra Alishahi, Arianna Bisazza, Grzegorz Chrupała

   Interspeech 2023·pp. 1259–1263

   • DOI
   • arXiv 2305.18957
   • Code