Natural language processing (NLP) aims to enable computers to use human languages – so that people can, for example, interact with computers naturally; or communicate with people who don't speak a common language; or access speech or text data at scales not otherwise possible. The NLP group at Notre Dame is interested in all aspects of NLP, with a focus on machine translation.
Unsupervised multilingual language learning Models and algorithms for translation, word alignment, and bilingual lexicon induction from parallel and non-parallel texts. Sponsored by DARPA LORELEI and a Google Faculty Research Award.
Neural networks for machine translation Models and algorithms for translation and language modeling using neural networks. Sponsored by an Amazon Academic Research Award and a Google Faculty Research Award.
Documenting endangered languages Technologies for large-scale data collection and automatic transcription and word alignment in endangered and unwritten languages. Sponsored by the National Science Foundation.
Top-rank enhanced listwise optimization for statistical machine translation. Huadong Chen, Shujian Huang, David Chiang, Xin-Yu Dai, and Jiajun Chen. CoNLL 2017. [PDF]
Improved neural machine translation with a syntax-aware encoder and decoder. Huadong Chen, Shujian Huang, David Chiang, and Jiajun Chen. ACL 2017. [PDF]
Spoken term discovery for language documentation using translations. Antonis Anastasopoulos, Sameer Bansal, Sharon Goldwater, Adam Lopez, and David Chiang. Workshop on Speech-Centric Natural Language Processing, 2017. [PDF]
Decoding with finite-state transducers on GPUs. Arturo Argueta and David Chiang. EACL 2017. [PDF]
DyNet: The Dynamic Neural Network Toolkit. Graham Neubig et al. 2017. [PDF]
A case study on using speech-to-translation alignments for language documentation. Antonios Anastasopoulos and David Chiang. Second Workshop on Computational Methods for Endangered Languages, 2017. [PDF]
Probabilistic neural programs. Kenton W. Murray and Jayant Krishnamurthy. NIPS Workshop on Neural Abstract Machines and Program Induction, 2016. [PDF]
An unsupervised probability model for speech-to-translation alignment of low-resource languages. Antonios Anastasopoulos, Long Duong, and David Chiang. EMNLP 2016. [PDF]
An attentional model for speech translation without transcription. Long Duong, Antonios Anasatasopoulos, Trevor Cohn, Steven Bird, and David Chiang. NAACL HLT 2016. [PDF]
Auto-sizing neural networks: with applications to n-gram language models. Kenton Murray and David Chiang. EMNLP 2015. [PDF]
Supervised phrase table triangulation with neural word embeddings for low-resource languages. Tomer Levinboim and David Chiang. EMNLP 2015. [PDF]
Multi-task word alignment triangulation for low-resource languages.
Tomer Levinboim and David Chiang. NAACL HLT 2015. [PDF]
Model invertibility regularization: sequence alignment with or without parallel data.
Tomer Levinboim, Ashish Vaswani, David Chiang. NAACL HLT 2015. [PDF][code]