News

[2025 Feb]

🎉 1 x paper accepted to NAACL 2025 Industry Track

[2025 Jan]

🎉 1 x paper accepted to NAACL 2025 Findings

[2025 Jan]

💼 Start working as NLP Engineer at University of Zurich

[2024 Nov]

👨‍💻 Program Chair of the TSAR Workshop at EMNLP 2024

[2024 Oct]

🎤 Invited talk at PEACH Lab, ETH Zurich

[2024 Oct]

🎤 Invited talk at CL HS24 Colloquium

[2024 May]

🎓 Successfully passed the PhD defense!

[2024 April]

💼 Start working as Research Associate at University of Zurich

[2024 Mar]

🎉 1 x paper accepted at EACL 2024

[2023 Oct]

🥇 1st place in PDF-DQA Challenge of the DocIU Workshop at CIKM 2023!

[2023 Dec]

🎉 1 x paper accepted at EMNLP 2023

...


About Me

My name is 英强 (aka Yingqiang, see here for instructions on how to pronounce Chinese names). Currently I am a Postdoc Researcher working with Prof. Dr. Sarah Ebling at Department of Computational Linguistics of University of Zurich. I am also an NLP Engineer working with Prof. Dr. Gerold Schneider at Linguistic Research Infrastructure of University of Zurich. My Ph.D study was supervised by Prof. Dr. Richard Hahnloser at Institute of Neuroinformatics of ETH Zurich, with a research focus on argument mining in scientific documents, scientific text generation, and information retrieval. My current research interests are applying LLMs to increase information accessibilities to help persons with diverse disabilities, and developing target-group oriented inclusive AI systems. I am a member of Zurich Center for Linguistics and an associated researcher at ETH AI Center. Prior to my roles in Zurich, I did my master's at Technical University of Munich and my bachelor's at Shanghai Tongji University.

foto2024 April Rotterdam Netherlands Flag
Projects
Digitally Supported Analysis of Spontaneous Speech (DigiSpon): Benchmarking NLP-Supported Language Sample Analysis of Swiss Children's Speech
Digitally Supported Analysis of Spontaneous Speech (DigiSpon): Benchmarking NLP-Supported Language Sample Analysis of Swiss Children's Speech

arXiv'25 Preprint

SwissADT: An Audio Description Translation System for Swiss Languages
SwissADT: An Audio Description Translation System for Swiss Languages

NAACL'25 Instrudy Track, Albuquerque, USA

Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies
Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies

NAACL'25 Findings, Albuquerque, USA

PDF
MODOC: A Modular Interface for Flexible Interlinking of Text Retrieval and Text Generation Functions

arXiv'24 Preprint

SciPara: A New Benchmark Dataset for Investigating Paragraph Discourse Structure in Scientific Papers

CODI'24 (co-hosted with EACL'24), St.Julians, Malta

Evaluating Unsupervised Argument Aligners via Generation of Conclusions for Structured Scientific Abstracts

EACL'24, St.Julians, Malta

GreedyCAS: Unsupervised Scientific Abstract Segmentation with Normalized Mutual Information

EMNLP'23, Sentosa, Singapore

MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering

DocIU'23 (co-hosted with CIKM'23), Birmingham, United Kingdom

Do Discourse Indicators Reflect the Main Arguments in Scientific Papers?

ArgMining'22 (co-hosted with COLING'22), Gyeongju, Korea

Local Citation Recommendation with Hierarchical-Attention Text Encoder and SciBERT-Based Reranking

ECIR'22, Stavanger, Norway

Character-Level Translation with Self-attention

ACL'20, Online

© 2025 Yingqiang Gao, all rights reserved. Poem images are generated by AI.