JHU MT Wiki
During Fall 2021, we meet on Mondays at 11:00am in Hackerman 306.
Looking for a paper to present? see here
| Date | Presenter | Topic |
| February 28 | ||
| February 21 | ||
| February 14 | ||
| February 7 | ||
| January 31 | Xuan Zhang | |
| January 24 | Kelly Marchisio | Current Work - GOAT for BLI, and Planned Future Work (GBO Feedback) |
| January 17 | Rachel Wicks | TBD |
| January 10 | Cancelled | - |
| January 3 | Boyuan Zheng | Aditya et al. (ICLR 2021): Long-tail learning via logit adjustment |
(April 30 is the official last day of class)
| Day | Presenter | Topic |
| May 24 | Liz Salesky (my hero) | Practice Talk |
| May 17 | (EMNLP deadline) | |
| May 10 | Matt Post | Clark et al. (arXiv 2021) CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation |
| May 3 | Shuoyang Ding | Some current work |
| April 26 | Kevin Duh | Prato et al. (EMNLP Findings 2020) Fully Quantized Transformer for Machine Translation |
| April 19 | Kelly Marchisio | Recent work: Embedding-Enhanced Giza++ |
| April 12 | Matt Post | Some current work |
| April 5 | Jake Bremerman | Yu et al. (TACL 2020): Better Document-Level Machine Translation with Bayes' Rule |
| March 29 | ||
| March 22 | (spring break) | |
| March 15 | Jeremy Gwinnup | Ive et al. (EACL 2021): Exploring Supervised and Unsupervised Rewards in Machine Translation |
| March 8 | Philipp Koehn | Meng et al. (WMT 2020): WeChat Neural Machine Translation Systems for WMT20 |
| March 1 | Xutai Ma | Practice Talk |
| February 22 | Philipp Koehn | Some highlights from WMT 2020 News Translation Shared Task sumissions |
| February 15 | Rachel Wicks | Pei Zhang, Boxing Chen, Niyu Ge, Kai Fan (EMNLP 2020): Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation |
| February 8 | Amrit Nidhi | Eva Vanmassenhove, Dimitar Shterionov, Matthew Gwilliam : Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation |
| February 1 | Shuoyang Ding | Jiatao Gu, Xiang Kong (arXiv 2020): Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade |
| January 25 | First official day of class; intros | |
| January 18 | Jeremy Gwinnup | Ozan Caglayan, Julia Ive, Veneta Haralampieva, Pranava Madhyastha, Loïc Barrault, Lucia Specia (EMNLP 2020): Simultaneous Machine Translation with Visual Context |
| January 11 | Huda Khayrallah | practice talk |
| Day | Presenter | Topic |
| December 21 | Ankur Kejriwal | Markus Freitag and Orhan Firat(WMT'20):Complete Multilingual Neural Machine Translation |
| December 14 | Ishita Tripathi | Marzieh Fadaee, Christof Monz (NGT @ ACL 2020): The Unreasonable Volatility of Neural Machine Translation Models |
| December 7 | Milind Agarwal | Xinyi Wang, Yulia Tsvetkov, Graham Neubig (ACL 2020): Balancing Training for Multilingual Neural Machine Translation |
| November 30 | Kelly Marchisio | Tasnim Mohiuddin, M Saiful Bari, Shafiq Joty (EMNLP 2020): LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space |
| November 23 | Thanksgiving Break -- no class (also, NAACL deadline) | |
| November 16 | NAACL Paper Clinic | TBD |
| November 9 | Shuoyang Ding | Recent Work |
| November 2 | Jake Bremerman | Marina Fomicheva, Lucia Specia, Francisco Guzmán (ACL 2020): Multi-Hypothesis Machine Translation Evaluation |
| October 26 | practice talks | |
| October 19 | Amrit Nidhi | Jitao XU, Josep Crego, Jean Senellart (ACL 2020): Boosting Neural Machine Translation with Similar Translations |
| October 12 | Practice talks | |
| October 5 | Rachel Wicks | Wei Zou, Shujian Huang, Jun Xie, Xinyu Dai, Jiajun Chen (ACL 2020): A Reinforced Generation of Adversarial Examples for Neural Machine Translation |
| September 28 | Philipp Koehn | Special sneak preview: Findings from WMT 2020 Shared Task on Parallel Sentence Pair Filtering |
| September 21 | Ramchandran Muthukumar | Yong Cheng, Lu Jiang, Wolfgang Macherey, Jacob Eisenstein (ACL 2020): AdvAug: Robust Adversarial Augmentation for Neural Machine Translation |
| September 14 | Xuan Zhang | Aji, Bogoychev, Heafield and Sennrich (ACL 2020): In Neural Machine Translation, What Does Transfer Learning Transfer? |
| September 7 | Labor Day -- no class | |
| August 31 | First day of class -- intros |
| Day | Presenter | Topic |
| August 24 | Matt Post | Tangled up in BLEU (Mathur et al., ACL 2020, Beyond Accuracy: Behavioral Testing of NLP Models with CheckList (Ribeiro et al., ACL 2020) |
| August 17 | Philipp Koehn | Low Resource MT for DARPA LwLL |
| August 10 | Paper Clinic | |
| August 3 | Philipp Koehn | WNGT Shared Task on Efficient Decoding: Overview paper, Edinburgh's submission: |
| July 27 | Liz Salesky | Kasai et al. (arXiv 2020): Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation |
| July 20 | Felicia Koerner | Zenkel et al. (ACL 2020): End-to-End Neural Word Alignment Outperforms GIZA++ |
| July 6 & 13 | ACL Recap | |
| June 29 | Shuoyang Ding | Edunov et al. (ACL 2020): On The Evaluation of Machine Translation Systems Trained With Back-Translation |
| June 22 | Brian Thompson | Practice talk |
| June 15 | ACL Practice talks | |
| June 8 | Matt Post | Bapna & Firat (EMNLP 2019): Simple, Scalable Adaptation for Neural Machine Translation |
| Day | Presenter | Topic |
| Dec 16 | Ankur Kejriwal | A Universal Music Translation Network |
| Dec 9 | - | ACL Deadline -- paper proofreading |
| Dec 6 (friday) | - | ACL paper workshop |
| Dec 2 | - | ACL paper workshop |
| Nov 18 | Yash Kumar Lal | Kim et al. (2019): Pivot-based Transfer Learning for Neural Machine Translation between non-English Languages |
| Nov 11 | Huda Khayrallah | current work |
| Nov 4 | Liz Salesky | Provilkov et al. (2019): BPE-Dropout: Simple and Effective Subword Regularization |
| Oct 28 | Xuan Zhang | practice talk |
| Oct 21 | Pamela Shapiro | Wang et al. (2019): Multilingual Neural Machine Translation With Soft Decoupled Encoding |
| Oct 14 | Brian | practice talk |
| Oct 7 | Rachel Wicks | Guzmán et al. (2019): The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English |
| Sep 30 | Matt Post | Zhang et al. (2018): Bridging the Gap between Training and Inference for Neural Machine Translation |
| Sep 23 | Shuoyang Ding | practice talk |
| Sep 16 | Kelly Marchisio | Artetxe et al. (2019): An Effective Approach to Unsupervised Machine Translation |
| Sep 9 | - | EMNLP / MT summit / WMT recap |
| Day | Presenter | Topic |
| May 20 | - | EMNLP paper workshop at 11am in Hackerman 306 |
| May 13 | - | EMNLP paper workshop |
| May 6 | Vivian Tsai | Godin et al. (2018): Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules? |
| April 29 | Cancelled (faculty meeting) | |
| April 22 | S. Mielke | Cotterell et al. (2018): Are All Languages Equally Hard to Language-Model? / Current research |
| April 15 | - | |
| April 8 | Yash Kumar Lal | Edunov et al (2018): Understanding Backtranslation at Scale |
| April 1 | Kelly Marchisio | Junczys-Dowmunt (2018): How I Learned to Stop Worrying and Love the Data (s Submission to the WMT2018 News Translation Task) |
| March 25 | Huda Khayrallah | Practice talk |
| March 18 | Arya McCarthy | Chen et al. (2018) The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation |
| March 11 | Rebecca Knowles | Fadaee & Monz (2018): Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation |
| March 4 | Note: this is the ACL deadline | |
| February 25 | - | ACL paper workshop (review form) |
| February 18 | Xuan Zhang | Shah et al. (NeurIPS 2018): Generative Neural Machine Translation |
| February 11 | Shuoyang Ding | Zenkel et al. (2018) Adding Interpretable Attention to Neural Translation Models Improves Word Alignment |
| February 4 | Gaurav Kumar | Current Research |
| Day | Presenter | Topic |
| December 17 | Pamela Shapiro | Deng et al. (NeurIPS 2018) Latent Alignment and Variational Attention |
| December 10 | NAACL proofreading | |
| December 3 | NAACL paper workshop (review form) | |
| November 26 | Adi Renduchintala | Cherry et al. (EMNLP 2018) Revisiting Character-Based Neural Machine Translation with Capacity and Compression |
| November 19 | EMNLP recap | |
| November 12 | Xuan Zhang | Lample et al. (ICLR 2018): Unsupervised Machine Translation Using Monolingual Corpora Only |
| October 22 | Huda Khayrallah | |
| October 15 | Brian Thompson | WMT practice talk |
| October 8 | Yash Kumar Lal | Platanios et al (EMNLP2018): Contextual Parameter Generation for Universal Neural Machine Translation |
| October 1 | Kelly Marchisio | Neubig & Hu (EMNLP 2018): Rapid Adaptation of Neural Machine Translation to New Languages |
| September 24 | Rebecca Knowles | Current Research |
| September 17 | Brian Thompson | Kirkpatrick et al. (2017): Overcoming catastrophic forgetting in neural networks |
| September 10 | Introductions |
| Day | Presenter | Topic |
| May 10 | Arya McCarthy | Passban et al. (NAACL 2018): Improving Character-based Decoding Using -Side Morphological Information for Neural Machine Translation |
| May 3 | Pamela Shapiro | Review of Attention Mechanisms |
| Apr 26 | Gaurav Kumar | Qi et al. (NAACL 2018): When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation? |
| Apr 19 | Xutai Ma | Gu, et. al. (AAAI 2018) Search Engine Guided Neural Machine Translation, Zhang, et. al. (NAACL2018) Guiding Neural Machine Translation with Retrieved Translation Pieces |
| Apr 12 | Adi Renduchintala | Yang, et. al. (NAACL2018): https://arxiv.org/pdf/1703.04887.pdf |
| Apr 5 | Rebecca Knowles | Current research |
| Mar 29 | Huda/Brian/Kevin | Current research |
| Mar 22 | no meeting | |
| Mar 15 | Becky Marvin & Steven Shearing | AMTA practice talks |
| Mar 8 | Kevin Duh | Huang, et. al. (ICLR 2018): Towards Neural Phrase-based Machine Translation |
| Mar 1 | Arya McCarthy | Wang et al. (2018): Translating Pro-Drop Languages with Reconstruction Models |
| Feb 22 | Pamela Shapiro | Belinkov and Bisk (2018): Synthetic and Natural Noise Both Break Neural Machine Translation |
| Feb 15 | Shuoyang Ding | Gu et al. (2018): Non-Autoregressive Neural Machine Translation |
| Feb 8 | Juri Ganitkevitch | Juri Ganitkevitch PhD defense (9am, Malone 107): Large-Scale Paraphrasing for Text-to-Text Generation |
| Feb 1 | Gaurav Kumar | Artetxe et al. (2017): Unsupervised Neural Machine Translation |
| Day | Presenter | Topic |
| Dec 13 | Xutai Ma/Shuoyang Ding | Current research |
| Dec 6 | Adi Renduchintala | He et al. (NIPS 2016): Dual Learning for Machine Translation |
| Nov 29 | Philipp Koehn | Ghader and Monz (IJCNLP 2017): What does Attention in Neural Machine Translation Pay Attention to? |
| Nov 22 | No meeting: Thanksgiving break | |
| Nov 15 | Huda Khayrallah | Practice Talk |
| Nov 8 | Pamela Shapiro | Artxetxe et al. (ACL 2017): Learning bilingual word embeddings with (almost) no bilingual data |
| Nov 1 | Becky Marvin | Nguyen and Chiang. (2017). Improving Lexical Choice in Neural Machine Translation |
| Oct 25 | Rebecca Knowles | Carpuat et. al. (2017). Detecting Cross-Lingual Semantic Divergence for Neural Machine Translation |
| Oct 18 | Cancelled | MATERIAL Kickoff meeting |
| Oct 11 | Kevin Duh | Britz. et. al. (2017). Massive Exploration of Neural Machine Translation Architectures |
| Oct 4 | everybody | 5-10 minute research presentations |
| Sep 27 | Shuoyang Ding | Niehues et al. 2017: Analyzing Neural MT Search and Model Performance Freitag and Al-Onaizan 2017: Search Strategies for Neural Machine Translation |
| Sep 20 | Cancelled | |
| Sep 13 | Xutai Ma | Rios et al. 2017: Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings |
| Sep 6 | Gaurav Kumar | Goyal, Dyer and Berg-Kirkpatrick: Differentiable Scheduled Sampling for Credit Assignment |
| Day | Presenter | Topic |
| August 23 | Discussion of WMT & ACL | |
| July 26 | Gaurav Kumar | Dayu Yuan, Ryan Doherty, Julian Richardson, Colin Evans, Eric Altendorf: Word Sense Disambiguation with Neural Language Models |
| July 19 | Adam Poliak | Pado and Lapata (Journal of Artificial Intelligence Research 36 (2009)) Cross-lingual Annotation Projection of Semantic Roles |
| July 12 | Rebecca Knowles | Maarten van Gompel and Antal van den Bosch (ACL 2014): Translation Assistance by Translation of L1 Fragments in an L2 Context and Eva Hasler (SemEval 2014): UEdin: Translating L1 Phrases in L2 Context using Context-Sensitive SMT |
| June 28 | Philipp Koehn | Research update: Neural machine translation and computer aided translation |
| June 14 | Huda Khayrallah | Ke Tran, Arianna Bisazza and Christof Monz (NAACL 2016): Recurrent Memory Networks for Language Modeling |
| June 7 | Huda Khayrallah | Andrej Karpathy, Justin Johnson, Li Fei-Fei (ICLR Workshop 2016): Visualizing and Understanding Recurrent Networks |
| May 24 | Discussion of MT Marathon in the Americas | |
| May 17 | MT Marathon in the Americas |
| Day | Presenter | Topic |
| May 10 | Rebecca Knowles | Marco Turchi, Matteo Negri, Marcello Federico (ACL 2015): MT Quality Estimation for Computer-assisted Translation: Does it Really Help? |
| May 3 | Philipp Koehn | Tips and tricks: living the Unix life and running experiments on the CLSP cluster |
| Apr 26 | Amittai Axelrod | Orhan Firat, Kyunghyun Cho, and Yoshua Bengio (NAACL 2016): Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism |
| April 19 | Kevin Duh | Kai Zhao, Hany Hassan, and Michael Auli (NAACL2015): Learning Translation Models from Monolingual Continuous Representations, Lei Yao and Grzegorz Kondrak (NAACL2015): Joint Generation of Transliterations from Multiple Representations |
| April 12 | Maria Nadejde | Current work |
| April 5 | Adam Poliak | Durrett and DeNero : Supervised Learning of Complete Morphological Paradigms |
| Mar 29 | Adi Renduchintala | Something super interesting (donuts provided) |
| Mar 22 | Huda Khayrallah | Faruqui et al. : Morphological Inflection Generation Using Character Sequence to Sequence Learning |
| Mar 15 | Biman Gujral | Current Research |
| Mar 8 | Matt Post | Current Research |
| Mar 1 | Adi Renduchintala | Grefenstette et al. : Learning to Transduce with Unbounded Memory |
| Feb 23 | Kyunghyun Cho | Seminar Visit |
| Feb 16 | Shuoyang Ding | Sennrich et al. : Improving Neural Machine Translation Models with Monolingual Data |
| Feb 9 | Gaurav Kumar | Shen et al. : Minimum Risk Training for Neural Machine Translation |
| Feb 2 | Rebecca Knowles | Stein, Schmidt, and Ney: Sign Language Machine Translation Overkill |
| Day | Presenter | Topic |
| Dec 8 | Hainan Xu | Taghipour et al. Parallel Corpus Refinement as an Outlier Detection Algorithm |
| Dec 1 | Brian Ho | Luong et al. Effective Approaches to Attention-based Neural Machine Translation |
| Nov 17 | Kevin Duh | Levinboim and Chiang: Supervised Phrase Table Triangulation with Neural Word Embeddings for Low-Resource Languages |
| Nov 10 | Amittai Axelrod | Class-Based N-gram Language Difference Models for Data Selection |
| Nov 3 | Biman Gujral | Tsvetkov et al. Lexicon stratification for translating out-of-vocabulary words |
| Oct 27 | Huda Khayrallah | Sennrich et al. Neural Machine Translation of Rare Words with Subword Units |
| Oct 20 | Matt Post | Pashto speech translation (MT Summit invited keynote preview) |
| Oct 13 | Shuoyang Ding | Yu and Zhu (ACL 2015): Recurrent Neural Network based Rule Sequence Model for Statistical Machine Translation Vaswani et al. (ACL 2011): Rule Markov Models for Fast Tree-to-String Translation |
| Oct 6 | Philipp Koehn | Updates on CommonCrawl project |
| Sep 29 | Gaurav Kumar | Work from the JSALT workshop |
| Sep 15 | Adi Renduchintala | Stanojevic and Sima'an (EMNLP 2015): Reordering Grammar Induction |
| Day | Presenter | Topic |
| Neural Networks | ||
| Dec 16 | Matt Post | Minkov et al. (2007): Generating Complex Morphology for Machine Translation, Toutanova et al. (2008): Applying Morphology Generation Models to Machine Translation |
| Dec 2 | Philipp Koehn | Introduction to Morphology and Machine Translation |
| Nov 18 | Adi Renduchintala | Theano neural network toolkit |
| Nov 11 | Philipp Koehn | Sundermeyer et al. (2014): Translation Modeling with Bidirectional Recurrent Neural Networks |
| Nov 4 | Shuoyang Ding | Lu et al. (2014): Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machine Translation |
| Oct 28 | Adithya Renduchintala | Yang et al. (2013): Word Alignment Modeling with Context Dependent Deep Neural Network |
| Oct 21 | Matt Post | Liu et al. (2014): A Recursive Recurrent Neural Network for Statistical Machine Translation |
| Oct 7 | Adithya Renduchintala | Vaswani et al. (2013): Decoding with Large-Scale NLMs |
| Sep 30 | Adam Lopez | Ammar et al., CRF Autoencoders |
| Sep 23 | Philipp Koehn | Zhang et al (2014): Bilingually-constrained Phrase Embeddings for Machine Translation; Liu et al (2014): A Recursive Recurrent Neural Network for Statistical Machine Translation |
| Sep 16 | Naomi Saphra, Adam Lopez | More AMR workshop results; Auli and Gao (2014): Expected BLEU training of RNNs |
| Sep 9 | Adam Lopez | Kalchbrenner and Blunsom (2013): Recurrent continuous translation models |
| Short Intermission: Semantics | ||
| Aug 26 | Adi Renduchintala | More AMR workshop results based on Flanigan et al. (2014): A Discriminative Graph-Based Parser for the Abstract Meaning Representation |
| Aug 19 | Adam Lopez | Report from the workshop on Cross-Lingual Abstract Meaning Representations (CLAMR) for Machine Translation |
| Neural Networks | ||
| Aug 12 | Dan Povey | Neural network language models in speech recognition |
| Aug 5 | Adam Lopez | Devlin et al. (2014): Fast and Robust Neural Network Joint Models for Statistical Machine Translation, pdf |
| July 29 | Philipp Koehn | Bengio et al. (2003): A Neural Probabilistic Language Model, pdf |
| July 22 | Philipp Koehn | Introduction to Neural Networks, handout |
| Semantics | ||
| July 8 | Matt Post | Anonymous (unpublished): A Variant of CYK+ for Decoding with Large SCFGs |
| July 1 | Adam Lopez | Stephen Clark, Julia Hockenmaier and Mark Steedman (2002): Building Deep Dependency Structures with a Wide-Coverage CCG Parser, pdf |
| June 17 | Philipp Koehn | Abstract Meaning Representations |
| June 10 | Maria Nadejde | State of the Art Syntax-Based Translation, Edinburgh Syntax System at WMT 2014 |
| June 3 | Naomi Saphra | David Chiang et al. (2013): Parsing Graphs with Hyperedge Replacement Grammars, ACL, pdf |
| May 20 | Adam Lopez | Bevan Jones et al. (2013): Semantics-Based Machine Translation with Hyperedge Replacement Grammars, pdf |
| Syntax Decoding | ||
| May 13 | Adam Lopez | Mark Hopkins and Greg Langmead (2009): Cube Pruning as Heuristic Search, ACL, pdf |
| May 6 | Philipp Koehn | Heafield, Kenneth and Koehn, Philipp and Lavie, Alon (2013): Grouping Language Model Boundary Words to Speed K--Best Extraction from Hypergraphs, NAACL, pdf |
| April 29 | Matt Post | DeNero, John and Bansal, Mohit and Pauls, Adam and Klein, Dan (2009): Efficient Parsing for Transducer Grammars, NAACL, pdf |
| April 22 | Philipp Koehn | Hopkins, Mark and Langmead, Greg (2010): SCFG Decoding Without Binarization, EMNLP, pdf |
| April 15 | Philipp Koehn | Syntax-Based Model Decoding, notes |
| March 18 | Adam Lopez | Pushdown Automata in Statistical Machine Translation, Hierarchical Phrase-Based Translation Representations |
| March 6 | Philipp Koehn | Inaugural meeting, notes |