Biography

Hi, I am a PhD student of the Legal Tech Group at the TU Munich, where I am advised by Matthias Grabmair. I am affiliated with the MaiNLP at LMU, and mentored by Barbara Plank. Previous to that, I worked as a speech scientist at Nuance Communications/Cerence. I did my master in Cultural and Cognitive Linguistics at LMU Munich. My research interest is NLP in LegalTech, Computational Social Science and Computational Linguistics.

I am also an organizer of Munich🥨NLP, where I have organized get-together event to support and encourage women in NLP, and am committed to promoting diversity and inclusivity in the field.

Interests
  • Uncertainty-aware NLP
  • Human Label Variation
  • Legal NLP
  • Computational Social Science
Education

  • M.A. in Cultural and Cognitive Linguistics, 2017

    Ludwig Maximilian University of Munich

  • B.A. in General and Indoeuropean Linguistics, 2015

    Ludwig Maximilian University of Munich

News

  • 04/2023: I gave a tallk at Munich🥨NLP. Check out the video recording!
  • 01/2023: I gave a tallk at Schütze Lab @ LMU Munich introduing my work in LegalNLP.
  • 12/2022: I presented our papers (1 main, 1 finding and 1 NLLP workshop) at EMNLP 2022 in Abu Dhabi 🇦🇪.
  • 08/2022: I attended the XAISS eXplainable AI Summer School in Delft 🇳🇱, where I enjoyed the great legictures and amazing socials. During this trip I discovered Ramen Nikkou, best Ramen in Europe, highly recommend. ラーメン、さぼりません 🍜
  • 06/2022: I presented our paper CANLI: an Adversarial Dataset for NLI and a Probing Task at LREC 2022 in Marseille 🇫🇷. My favourite restaurant of the trip is Ourea, an intimate bistro focusing using high quality local Mediterranean fish and vegetables with perfect wine recommendation.

Selected Publications

Shanshan Xu, Leon Staufer, Santosh T.Y.S.S, Oana Ichim, Corina Heri, Matthias Grabmair (2023). VECHR: A Dataset for Explainable and Robust Classification of Vulnerability Type in the European Court of Human Rights. In Accepted to EMNLP 2023.

PDF

Shanshan Xu, Santosh T.Y.S.S, Oana Ichim, Isabella Risini, Barbara Plank, Matthias Grabmair (2023). From Dissonance to Insights: Dissecting Disagreements in Rationale Dataset Construction for Case Outcome Classification. In Accepted to EMNLP 2023.

PDF

Santosh T.Y.S.S, Shanshan Xu, Oana Ichim, Matthias Grabmair (2022). Deconfounding Legal Judgment Prediction towards Better Alignment with Experts for the European Court of Human Rights. In EMNLP 2022 Oral.

PDF

Abhishek Agarwal, Shanshan Xu, Matthias Grabmair (2022). Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance. In Findings of EMNLP 2022.

PDF

Shanshan Xu, Katja Markert (2022). The Chinese Causative-Passive Homonymy Disambiguation: an Adversarial Dataset for NLI and a Probing Task. In LREC 2022.

PDF Cite Dataset