Lecture 14: Recurrent Neural Nets, Encoder-Decoder 15 Nov.
Presentations
- Slides from lecture 13, from slide 35
- New slides
- Slides on ethics: PDF / PPT
Recordings: here and here
Mandatory reading
- Jurafsky and Martin, Speech and Language Processing, 3. ed. (edition of Sept. 2021!)
- Ch. 9 Deep Learning Architectures for Sequence Processing
- Sec. 9.1-9.5
- Ch. 10 Machine Translation and Encoder-Decoder Models
- Sec. 10.0, 10.2-10.4
- Ch. 9 Deep Learning Architectures for Sequence Processing
- Hovy, D., & Spruit, S. L. (2016). The social impact of natural language processing. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (pp. 591-598).
- Bolukbasi, T., Chang, K. W., Zou, J. Y., Saligrama, V., & Kalai, A. T. (2016). Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In Advances in neural information processing systems (pp. 4349-4357). NB: you can skip the details of the experimental design and evaluation results.
Recommended reading
Jurafsky and Martin, Speech and Language Processing, 3. ed. (edition of Sept. 2021!)
- Ch. 10 Machine Translation and Encoder-Decoder Models
- Sec. 10.1 Language Divergences and Typology
Optional reading:
- Blackburn, S. (2002). Being good: A short introduction to ethics. OUP Oxford.
- Poppy Noor (2018), Wikipedia biases, The Guardian.
- Koenecke, A., Nam, A., Lake, E., Nudell, J., Quartey, M., Mengesha, Z., & Goel, S. (2020). Racial disparities in automated speech recognition. Proceedings of the National Academy of Sciences, 117(14), 7684-7689.
- Joshi, P., Santy, S., Budhiraja, A., Bali, K., & Choudhury, M. (2020). The state and fate of linguistic diversity and inclusion in the NLP world. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp 6282–6293).
- Garg, N., Schiebinger, L., Jurafsky, D., & Zou, J. (2018). Word embeddings quantify 100 years of gender and ethnic stereotypes. Proceedings of the National Academy of Sciences , 115 (16), E3635-E3644.
Lab-session, Thursday 18 November at Sed
- Program
- Exam 2020, exercises 1-3
- Exam 2019, exercises 2-3 (as time permits)