I am currently a PhD student working on Natural Language Processing (NLP).

I joined the the UKP Lab, Techinical University of Darmstadt since Sept. 2020. My supervisors are Dr. Nils Reimers and Prof. Iryna Gurevych.

My research interests mainly include low-resource text representations and open-domain question answering.

I am also responsible for the invited talks at UKP. If interested, please send me an email.

Open-source

• Unsupervised Sentence Embedding Benchmark (USEB)
  Heterogenous, task- and domain-specific benchmark for evaluating unsupervised sentence embeddings used in the TSDAE paper. [Repo]

• Tranformer-based Denoising AutoEncoder (TSDAE)
  Powerful unsupervised text embedding learning for semantic search in the scenarios of (1) no annotation, (2) domain adaptation and (3) few-shot learning. [Repo]

• Easy Elasticsearch
  Using business-level retrieval system (BM25) with Python in just a few lines. [Repo]

Publications

• GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval
  Kexin Wang, Nandan Thakur, Nils Reimers and Iryna Gurevych. NAACL 2022. [code]

• UKP-SQuARE: Software for Question Answering Research
  Tim Baumgärtner, Kexin Wang, Rachneet Singh Sachdeva, Gregor Geigle, Max Eichler, Clifton A. Poth, Hannah Sterz, Haritz Puerto, Leonardo F. R. Ribeiro, Jonas Pfeiffer, Nils Reimers, Gözde Gül Şahin and Iryna Gurevych. Accepted in ACL 2022 System Demonstrations. [code]

• TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning
  Kexin Wang, Nils Reimers and Iryna Gurevych. Findings of the Association for Computational Linguistics: EMNLP 2021. [code] [data]

• Structurally Comparative Hinge Loss for Dependency-Based Neural Text Representation
  Kexin Wang, Yu Zhou, Shaonan Wang, Jiajun Zhang and Chengqing Zong. ACM Transactions on Asian and Low-Resource Language Information Processing, 2020.

• Understanding Memory Modules on Learning Simple Algorithms
  Kexin Wang, Yu Zhou, Shaonan Wang, Jiajun Zhang and Chengqing Zong. IJCAI 2019 Workshop on Explainable Artificial Intelligence, 2019.

Blogs

• What is low-resource NLP?

Life>>research

• Guitar solo: Il Vento D'oro

• Guitar solo: Requiem der Morgenröte