I’m a third-year PhD student in Computer Science at JHU advised by Kevin Duh. I’m currently interested in neural machine translation, in particular improving the handling of morphological complexity and dialectal variation.

Recent Activities

  • Presented at CLSP Seminar on Incorporating Morphology into NMT
  • Participated in SCALE 2018 on domain adaptation for NMT

Publications

Character-Aware Decoder for Neural Machine Translation
Adithya Renduchintala*, Pamela Shapiro*, Kevin Duh, and Philipp Koehn
*Equal contribution
arXiv preprint

BPE and CharCNNs for Translation of Morphology: A Cross-Lingual Comparison and Analysis
Pamela Shapiro and Kevin Duh
code
arXiv preprint

Hard Non-Monotonic Attention for Character-Level Transduction
Shijie Wu, Pamela Shapiro, and Ryan Cotterell
EMNLP 2018

Morphological Word Embeddings for Arabic Neural Machine Translation in Low-Resource Settings
Pamela Shapiro and Kevin Duh
NAACL Workshop on Subword and Character-Level Modeling (SCLeM) 2018
Best Paper Award
code
bib

Teaching

I’m passionate about teaching and improving accessibility of computer science, machine learning, and natural language processing. I hope to help expose more students to these topics earlier on and make introductory classes accessible to students without prior exposure.

  • I’m a TA for Mark Dredze’s Machine Learning class, Fall 2018.
  • I help run the JHU chapter of the North American Computational Linguistics Olympiad for middle and high school students. This includes outreach to local schools about the olympiad, teaching them a bit about computational linguistics and the kind of research we do.