Yan Chen

Yan Chen | CS411 [3 credits] | Fall 2020

In this 3 credit 411 Directed Study, Yan Chen will under the direction of Prof. Jeanna Matthews, read and discuss research literature, collect and analyze data, write research paper submissions and present her results verbally to a wider research team. The work she is conducting and the related work she will be reading is in the high level areas of bias in natual language processing and social media polarization. She will meet Tuesdays from 6-7 as well as frequently at other times with Prof. Matthews and a wider research team. She will produce a web portfolio of her research work. This course is not lecture based. Some of the work Yan does will be group work done in collaboration with other students.

Grading: 50% Participation and Verbal Presentation + 50% Web Portfolio of Research

Objectives: Conduct original research, gain skills in collection and anaysis of data including the production of automated analysis scripts. Read and discuss related work.

Demonstrable Outcomes: Submission of an ACM FAccT paper. Portfolio of scripts written/modified. Portfolio of data collected as well as visualizations and analysis of this data, likely well beyond what can be included in the ACM FAccT paper. Attendance at research group meetings. Oral presentation of research results.

Things accomplished

Submission to ACM FAccT (Fairness, Accountability, and Transparency)
ACM FAccT abstract
Translations for word pairs document
Informal Chinese defining set
Profession words & defining set for 9 languages including Chinese, Spanish, English, Arabic, German, French, Farsi, Urdu, and Wolof Excel sheet
Number of occurrence of each profession word / defining set in all 9 languages
List of Classics in all languages
Helping with the qualitative Social Polarization paper about COVID-19 in different countries across social medias HERE
Weekly big group meeting Tuesdays from 6-7PM
Weekly Human Language sub-group meeting Mondays from 10-11AM
Weekly social polarization meeting Fridays from 5-6PM (Ends at Nov. 5th)
Found a tool for supertopic trending in Sina Weibo HERE
Helped with open house for 2 hours on Nov 7th.

Future plans

Work on the extend report for FAccT
Read related work papers (notes about the paper, link to the paper)

1. Bender, E. M. 2011. On achieving and evaluating language independence in NLP. Linguistic Issues in Language Technology 6(3): 1–26.
2. Conneau, A.; Rinott, R.; Lample, G.; Williams, A.; Bowman, S.; Schwenk, H.; and Stoyanov, V. 2018. XNLI: Evaluating Cross-lingual Sentence Representations. In Proceedings of the 2018 Conference on Empirical Methods in Natual Language Processing, 2475–2485. 
3. Arivazhagan, N.; Bapna, A.; Firat, O.; Lepikhin, D.; Johnson, M.; Krikun, M.; Chen, M. X.; Cao, Y.; Foster, G.; Cherry, C.; et al. 2019. Massively multilingual neural machine translation in the wild: Findings and challenges. arXiv preprint arXiv:1907.05019 . 
4. Liang, Y.; Duan, N.; Gong, Y.; Wu, N.; Guo, F.; Qi, W.; Gong,M.; Shou, L.; Jiang, D.; Cao, G.; et al. 2020. Xglue: A new benchmark dataset for cross-lingual pre-training, understanding and generation. arXiv preprint arXiv:2004.01401
5. Wu, S.; and Dredze, M. 2020. Are All Languages Created Equal in Multilingual BERT? arXiv preprint arXiv:2005.09093 .
6. Pires, T.; Schlinger, E.; and Garrette, D. 2019. How Multilingual is Multilingual BERT? In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 4996–5001. 
7. Hu, J.; Ruder, S.; Siddhant, A.; Neubig, G.; Firat, O.; and Johnson, M. 2020. Xtreme: A massively multilingual multi-task benchmark for evaluating cross-lingual generalization.arXiv preprint arXiv:2003.1108´´0 .