Publications

2023:

Handshape-Aware Sign Language Recognition: Extended Datasets and Exploration of Handshape-Inclusive Methods
Xuan Zhang and Kevin Duh
EMNLP'23: Findings of the Assoc. for Computational Linguistics: EMNLP
PDF | BibTeX

Machine Translation with Large Language Models: Prompting, Few-shot Learning, and Fine-tuning with QLoRA
Xuan Zhang, Navid Rajabi, Kevin Duh, Philipp Koehn
WMT'23:Proceedings of the Conference on Machine Translation
PDF | BibTeX

In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models
Suzanna Sia and Kevin Duh
MTSummit'23: Proceedings of Machine Translation Summit XIV (Volume 1: Research Track)
PDF | BibTeX

HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation
Cihan Xiao, Henry Li Xinyuan, Jinyi Yang, Dongji Gao, Matthew Wiesner, Kevin Duh, Sanjeev Khudanpur
Interspeech'23: 24th Annual Conference of the International Speech Communication Association
PDF | BibTeX

A Hyperparameter Optimization Toolkit for Neural Machine Translation Research
Xuan Zhang, Kevin Duh, Paul McNamee
ACL'23 demo: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
PDF | BibTeX | Poster | Demo Video

An Extensive Exploration of Back-Translation in 60 Languages
Paul McNamee and Kevin Duh
ACL'23 Findings: Findings of the Association for Computational Linguistics
PDF | BibTeX

Enhancing Video Translation Context with Object Labels
Jeremy Gwinnup, Tim Anderson, Brian Ore, Eric Hansen, Kevin Duh
IWSLT'23: Proceedings of the 20th International Conference on Spoken Language Translation
PDF | BibTeX

Findings of the 2023 IWSLT Evaluation Campaign
Agarwal, et al.
IWSLT'23: Proceedings of the 20th International Conference on Spoken Language Translation
PDF | BibTeX

2022:

Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport
Kelly Marchisio, Ali Saad-Eldin, Kevin Duh, Carey Priebe, Philipp Koehn
EMNLP'22: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
PDF | BibTeX

IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
Kelly Marchisio, Neha Verma, Kevin Duh, and Philipp Koehn
EMNLP'22: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
PDF | BibTeX

AfriCLIRMatrix: Enabling Cross-Lingual Information Retrieval for African Languages
Odunayo Ogundepo, Xinyu Zhang, Shuo Sun, Kevin Duh, and Jimmy Lin
EMNLP'22: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
PDF | BibTeX

Offer a Different Perspective: Modeling the Belief Alignment of Arguments in Multi-party Debates
Suzanna Sia, Kokil Jaidka, Hansin Ahuja, Niyati Chhaya, Kevin Duh
EMNLP'22: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
PDF | BibTeX

Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines
Kiron Deb, Xuan Zhang, Kevin Duh
BlackboxNLP'22: Proceedings of BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
PDF | BibTeX

The Effects of Language Token Prefixing for Multilingual Machine Translation
Rachel Wicks and Kevin Duh
AACL-IJCNLP'22: Proceedings of the Conference of the Asia-Pacific Chapter of ACL and International Joint Conference on NLP
PDF | BibTeX

Multimedia Curriculum Learning for Language Acquisition
Pengfei Yu, Heng Ji, Shih-fu Chang, Kevin Duh
Journal of Science and Technology on Information and Communications, 2022
PDF | BibTeX

Prefix Embeddings for In-Context Machine Translation
Suzanna Sia and Kevin Duh
AMTA'22: Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas
PDF | BibTeX

Strategies for Adapting Multilingual Pre-training for Domain-Specific Machine Translation
Neha Verma, Kenton Murray, Kevin Duh
AMTA'22: Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas
PDF | BibTeX

The Multilingual Microblog Translation Corpus: Improving and Evaluating Translation of User-Generated Text
Paul McNamee and Kevin Duh
LREC'22: Proceedings of the 13th Conference on Language Resources and Evaluation
PDF | BibTeX

Attention-Focused Adversarial Training for Robust Temporal Reasoning
Lis Kanashiro Pereira, Kevin Duh, Fei Cheng, Masayuki Asahara, Ichiro Kobayashi
LREC'22: Proceedings of the 13th Conference on Language Resources and Evaluation
PDF | BibTeX

Findings of the IWSLT 2022 Evaluation Campaign
Anastasopoulos et. al.
IWSLT'22: Proceedings of the 19th International Conference on Spoken Language Translation
PDF | BibTeX

Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models
Suraj Nair, Eugene Yang, Dawn Lawrie, Kevin Duh, Paul McNamee, Kenton Murray, James Mayfield and Douglas Oard
ECIR'22: Advances in Information Retrieval. Lecture Notes in Computer Science, vol 13185
PDF | BibTeX

2021:

An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction
Kelly Marchisio, Youngser Park, Ali Saad-Eldin, Anton Alyakin, Kevin Duh, Carey Priebe and Philipp Koehn
Findings of the Association for Computational Linguistics: EMNLP 2021
PDF | BibTeX

Data and Parameter Scaling Laws for Neural Machine Translation
Mitchell Gordon, Kevin Duh, Jared Kaplan
EMNLP'21: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
PDF | BibTeX

Approaching Sign Language Gloss Translation as a Low-Resource Machine Translation Task
Xuan Zhang and Kevin Duh
AT4SSL'21: Proceedings of the 1st International Workshop on Automatic Translation for Signed and Spoken Languages
PDF | BibTeX

Sequence Models for Computational Etymology of Borrowings
Winston Wu, Kevin Duh, and David Yarowsky
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021
PDF | BibTeX

Machine Translation Believability
Marianna Martindale, Kevin Duh, Marine Carpuat
HCI-NLP'21: Proceedings of the First Workshop on Bridging Human-Computer Interaction and Natural Language Processing
PDF | BibTeX

Self-Guided Curriculum Learning for Neural Machine Translation
Lei Zhou, Liang Ding, Kevin Duh, Shinji Watanabe, Ryohei Sasano, Koichi Takeda
IWSLT'21: Proceedings of the 18th International Conference on Spoken Language Translation
PDF | BibTeX

Orthros: Non-Autoregressive End-to-End Speech Translation with Dual-Decoder
H. Inaguma, Y. Higuchi, K. Duh, T. Kawahara, S. Watanabe
ICASSP'21:IEEE International Conference on Acoustics, Speech and Signal Processing
PDF | BibTeX

Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yoloxóchitl Mixtec
Jiatong Shi, Jonathan D. Amith, Rey Castillo García, Esteban Guadalupe Sierra, Kevin Duh, Shinji Watanabe
EACL'21: Proceedings of the European Chapter of the Association for Computational Linguistics
PDF | BibTeX

Adaptive Mixed Component LDA for Low Resource Topic Modeling
Suzanna Sia and Kevin Duh
EACL'21: Proceedings of the European Chapter of the Association for Computational Linguistics
PDF | BibTeX

2020:

When Does Unsupervised Translation Work?
Kelly Marchisio, Kevin Duh, Philipp Koehn
WMT'20: Proceedings of the Fifth Conference on Machine Translation
PDF | BibTeX

CLIRMatrix: A massively large collection of bilingual & multilingual datasets for Cross-Lingual Information Retrieval
Shuo Sun and Kevin Duh
EMNLP'20: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing
PDF | BibTeX

Machine Translation System Selection from Bandit Feedback
Jason Naradowksy, Xuan Zhang, Kevin Duh
AMTA'20: Proceedings of the 14th Conference of the Assoc. for Machine Translation in the Americas
PDF | BibTeX

Reproducible and Efficient Benchmarks for Hyperparameter Optimization of Neural Machine Translation Systems
Xuan Zhang and Kevin Duh
TACL'20: Transactions of the Association for Computational Linguistics, vol. 8, 2020
PDF | TACL Link | BibTeX

Automated Development of DNN Based Spoken Language Systems Using Evolutionary Algorithms
Takahiro Shinozaki, Shinji Watanabe, Kevin Duh
Book chapter in ”Deep Neural Evolution: Deep Learning with Evolutionary Computation"
editors: Hitoshi Iba, Nasimul Noman, Springer, pp. 97--129, 2020
Link | BibTeX

ESPnet-ST: All-in-One Speech Translation Toolkit
Hirofumi Inaguma, Shun Kiyono, Kevin Duh, Shigeki Karita, Nelson Yalta, Tomoki Hayashi, Shinji Watanabe
ACL'20-Demo: Proceedings of the Annual Meeting of the Association for Computational Linguistics: System Demonstrations
PDF | BibTeX

CLIReval: Evaluating Machine Translation as a Cross-Lingual Information Retrieval Task
Shuo Sun, Suzanna Sia, Kevin Duh
ACL'20-Demo: Proceedings of the Annual Meeting of the Association for Computational Linguistics: System Demonstrations
PDF | BibTeX

Distill, Adapt, Distill: Training Small, In-Domain Models for Neural Machine Translation
Mitchell A. Gordon and Kevin Duh
WNGT'20: Proceedings of the 4th Workshop on Neural Generation and Translation, 2020
PDF | BibTeX

Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning
Mitchell A. Gordon, Kevin Duh, and Nicholas Andrews
REP4NLP'20: Proceedings of the 5th Workshop on Representation Learning for NLP, 2020
PDF | BibTeX

Modeling Document Interactions for Learning to Rank with Regularized Self-Attention
Shuo Sun and Kevin Duh
arXiv

Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your MT System?
Sorami Hisamoto, Matt Post, Kevin Duh
TACL'20: Transactions of the Association for Computational Linguistics, vol. 8, 2020
PDF | Link | Slides | Dataset | BibTeX

Benchmarking Neural and Statistical Machine Translation on Low-Resource African Languages
Kevin Duh, Paul McNamee, Matt Post, Brian Thompson
LREC'20: Proceedings of the Language Resources and Evaluation Conference
PDF | BibTeX

2019:

Multilingual end-to-end speech translation
Hirofumi Inaguma, Kevin Duh, Tatsuya Kawahara, Shinji Watanabe
ASRU'19: Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop
PDF | BibTeX

HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation
Brian Thompson*, Rebecca Knowles*, Xuan Zhang*, Huda Khayrallah, Kevin Duh and Philipp Koehn (*equal contribution)
EMNLP-IJCNLP'19
PDF | Poster | BibTeX

Broad-Coverage Semantic Parsing as Transduction
Sheng Zhang, Xutai Ma, Kevin Duh and Ben Van Durme
EMNLP-IJCNLP'19
PDF | BibTeX

Comparing Pipelined and Integrated Approaches to Dialectal Arabic Neural Machine Translation
Pamela Shapiro and Kevin Duh
VarDIAL'19 : Proceedings of the 6th Workshop on NLP for Similar Languages, Varieties, and Dialects
PDF | BibTeX

AMR Parsing as Sequence-to-Graph Transduction
Sheng Zhang, Xutai Ma, Kevin Duh and Benjamin Van Durme
ACL'19
PDF | BibTeX

Identifying Fluently Inadequate Output in Neural and Statistical Machine Translation
Marianna J. Martindale, Marine Carpuat, Kevin Duh and Paul McNamee
MT Summit'19: Proceedings of the Machine Translation Summit, 2019
PDF | BibTeX

Character-Aware Decoder for Translation into Morphologically Rich Languages
Adithya Renduchintala*, Pamela Shapiro*, Kevin Duh and Philipp Koehn (* equal contribution)
MT Summit'19: Proceedings of the Machine Translation Summit, 2019
PDF | BibTeX

A Call for Prudent Choice of Subword Merge Operations
Shuoyang Ding, Adithya Renduchintala and Kevin Duh
MT Summit'19: Proceedings of the Machine Translation Summit, 2019
PDF | BibTeX

Robust Document Representations for Cross-Lingual Information Retrieval in Low-Resource Settings
Mahsa Yarmohammadi, et. al.
MT Summit'19: Proceedings of the Machine Translation Summit, 2019
PDF | BibTeX

Curriculum Learning for Domain Adaptation in Neural Machine Translation
Xuan Zhang, Pamela Shapiro, Gaurav Kumar, Paul McNamee, Marine Carpuat and Kevin Duh
NAACL'19
PDF | BibTeX

Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation
Brian Thompson, Jeremy Gwinnup, Huda Khayrallah, Kevin Duh and Philipp Koehn
NAACL'19
PDF | BibTeX

Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition
Takafumi Moriya, Tomohiro Tanaka, Takahiro Shinozaki, Shinji Watanabe, Kevin Duh
IEEE/ACM Transactions on Audio, Speech and Language Processing, 27(1), Jan 2019
PDF link | BibTeX

An Interactive Teaching Tool for Introducing Novices to Machine Translation Huda Khayrallah, Rebecca Knowles, Kevin Duh, Matt Post
SIGCSE'19: Proceedings of the 50th ACM Technical Symposium on Computer Science Education
PDF link | BibTeX | Demo/Code

Query Expansion for Cross-Language Question Re-Ranking
Muhammad Mahbubur Rahman, Sorami Hisamoto, Kevin Duh
arXiv

2018:

Regularized Training Objective for Continued Training for Domain Adaption in Neural Machine Translation
Huda Khayrallah, Brian Thompson, Kevin Duh and Philipp Koehn
NMT'18: Proceedings of the Workshop on Neural Machine Translation and Generation
PDF | BibTeX

Morphological Word Embeddings for Arabic Neural Machine Translation in Low-Resource Settings
Pamela Shapiro and Kevin Duh
SCLeM'18: Proceedings of the Second Workshop on Subword/Character LEvel Models
PDF | BibTeX | BEST PAPER AWARD

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

Stochastic Answer Networks for Machine Reading Comprehension
Xiaodong Liu, Yelong Shen, Kevin Duh, Jianfeng Gao
ACL'18: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics
PDF | BibTeX

Stochastic Answer Networks for Natural Language Inference
Xiaodong Liu, Kevin Duh, Jianfeng Gao
arXiv

Cross-lingual Decompositional Semantic Parsing
Sheng Zhang, Xutai Ma, Rachel Rudinger, Kevin Duh, Ben Van Durme
EMNLP'18: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
PDF | BibTeX

Freezing Subnetworks to Analyze Domain Adaptation in Neural Machine Translation
Brian Thompson, Huda Khayrallah, Antonios Anastasopoulos, Arya D. McCarthy, Kevin Duh, Rebecca Marvin, Paul McNamee, Jeremy Gwinnup, Tim Anderson, Philipp Koehn
WMT'18
PDF | Slides | BibTeX

An Empirical Exploration of Curriculum Learning for Neural Machine Translation
Xuan Zhang, Gaurav Kumar, Huda Khayrallah, Kenton Murray, Jeremy Gwinnup, Marianna Martindale, Paul McNamee, Kevin Duh, Marine Carpuat
arXiv

How Do Source-side Monolingual Word Embeddings Impact Neural Machine Translation?
Shuoyang Ding, Kevin Duh
arXiv

Fine-grained Entity Typing through Increased Discourse Context and Adaptive Classification Thresholds
Sheng Zhang, Kevin Duh and Benjamin Van Durme
*SEM'18: Proceedings of the Joint Conference on Lexical and Computational Semantics
PDF | BibTeX

Halo: Learning Semantics-Aware Representations for Cross-Lingual Information Extraction
Hongyuan Mei, Sheng Zhang, Kevin Duh and Benjamin Van Durme
*SEM'18: Proceedings of the Joint Conference on Lexical and Computational Semantics
PDF | BibTeX

Cross-lingual Learning-to-Rank with Shared Representations
Shota Sasaki, Shuo Sun, Shigehiko Schamoni, Kevin Duh, Kentaro Inui
NAACL'18: Proceedings of Conf. of the North American Chapter of ACL: Human Language Technologies
PDF | BibTeX | Data | Code

Towards a Consistent Segmentation Level across Multiple Chinese Word Segmentation Corpora
Fei Cheng, Kevin Duh, Yuji Matsumoto
Journal of Natural Language Processing, Vol 24(5), pp. 669-686
PDF

Audio-Visual Person Recognition in Multimedia Data from the IARPA JANUS Program
Gregory Sell, Kevin Duh, David Snyder, Dave Etter, Daniel Garcia-Romero
ICASSP'18: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
PDF | BibTeX

2017:

Evolution Strategy Based Automatic Tuning of Neural Machine Translation Systems
Hao Qin, Takahiro Shinozaki, Kevin Duh
IWSLT'17: Proc. of the International Workshop on Spoken Language Translation
PDF

Neural Lattice Search for Domain Adaptation in Machine Translation
Huda Khayrallah, Gaurav Kumar, Kevin Duh, Matt Post and Philipp Koehn
IJCNLP'17: Proc. of the International Joint Conference on Natural Language Processing, Taipei, Taiwan, 2017
PDF | BibTeX | Code

Low-Resource Named Entity Recognition with Cross-lingual, Character-Level Neural Conditional Random Fields
Ryan Cotterell and Kevin Duh
IJCNLP'17: Proc. of the International Joint Conference on Natural Language Processing, Taipei, Taiwan, 2017
PDF | BibTeX

A Multi-task Learning Approach to Adapting Bilingual Word Embeddings for Cross-lingual Named Entity Recognition
Dingquan Wang, Nanyun Peng and Kevin Duh
IJCNLP'17: Proc. of the International Joint Conference on Natural Language Processing, Taipei, Taiwan, 2017
PDF | BibTeX

Selective Decoding for Cross-lingual Open Information Extraction
Sheng Zhang, Kevin Duh and Benjamin Van Durme
IJCNLP'17: Proc. of the International Joint Conference on Natural Language Processing, Taipei, Taiwan, 2017
PDF | BibTeX

Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework
Aaron Steven White, Pushpendre Rastogi, Kevin Duh and Benjamin Van Durme
IJCNLP'17: Proc. of the International Joint Conference on Natural Language Processing, Taipei, Taiwan, 2017
PDF | BibTeX | Data

An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks
Yelong Shen, Xiaodong Liu, Kevin Duh and Jianfeng Gao
IJCNLP'17: Proc. of the International Joint Conference on Natural Language Processing, Taipei, Taiwan, 2017
PDF | BibTeX

Skip-Prop: Representing Sentences with One Vector Per Proposition
Rachel Rudinger, Kevin Duh, Benjamin Van Durme
IWCS'17: Proc. of the International Conference on Computational Semantics, Montpellier, France, 2017
PDF

Ordinal Common-sense Inference
Sheng Zhang, Rachel Rudinger, Kevin Duh, and Ben Van Durme
TACL'17: Transactions of the ACL
PDF | Data | BibTeX

MT/IE: Cross-lingual Open Information Extraction with Neural Sequence-to-Sequence Models
Sheng Zhang, Kevin Duh, and Ben Van Durme
EACL'17: Proceedings of the European Chapter of the Association for Computational Linguistics, Valencia, Spain
PDF | BibTeX

Streaming Word Embeddings with the Space-Saving Algorithm
Chandler May, Kevin Duh, Ben Van Durme, and Ashwin Lall
arXiv link

Robsut Wrod Reocginiton via Semi-Character Recurrent Neural Network
Keisuke Sakaguchi, Kevin Duh, Matt Post, Ben Van Durme
AAAI'17: Proceedings of the AAAI Conference on Artificial Intelligence, San Fransisco, USA
PDF | BibTeX

DyNet: The Dynamic Neural Network Toolkit
Graham Neubig, Chris Dyer, Yoav Goldberg, Austin Matthews, Waleed Ammar, Antonios Anastasopoulos, Miguel Ballesteros, David Chiang, Daniel Clothiaux, Trevor Cohn, Kevin Duh, Manaal Faruqui, Cynthia Gan, Dan Garrette, Yangfeng Ji, Lingpeng Kong, Adhiguna Kuncoro, Gaurav Kumar, Chaitanya Malaviya, Paul Michel, Yusuke Oda, Matthew Richardson, Naomi Saphra, Swabha Swayamdipta, Pengcheng Yin
arXiv link | BibTeX

A Psycholinguistic Model for the Marking of Discourse Relations
Frances Yung, Kevin Duh, Taku Komura, and Yuji Matsumoto
Dialogue and Discourse
PDF link | BibTeX

2016:

Automated structure discovery and parameter tuning of neural network language model based on evolution strategy
Tomohiro Tanaka, Takafumi Moriya, Takahiro Shinozaki, Shinji Watanabe, Takaaki Hori, Kevin Duh
SLT'16: Proceedings of the 2016 IEEE Workshop on Spoken Language Technology, San Diego, USA, Dec 2016
PDF | BibTeX

Modeling the Usage of Discourse Connectives as Rational Speech Acts
Frances Yung, Kevin Duh, Taku Komura, Yuji Matsumoto
CoNLL'16: Proceedings of the Conf. on Natural Language Learning, Berlin, Germany
PDF | BibTeX

Transition-Based Dependency Parsing Exploiting Supertags
Hiroki Ouchi, Kevin Duh, Hiroyuki Shindo, Yuji Matsumoto
IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol.24, Issue 11, pp.2059-2068, November 2016
PDF |Journal link | BibTeX

Modeling the Interpretation of Discourse Connectives by Bayesian Pragmatics
Frances Yung, Kevin Duh, Taku Komura, Yuji Matsumoto
ACL'16: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany
PDF | BibTeX

Dependency Parsing with LSTMs: An Empirical Evaluation
Adhiguna Kuncoro, Yuichiro Sawai, Kevin Duh, Yuji Matsumoto
arXiv

A Generalized Framework for Hierarchical Word Sequence Language Model
Xiaoyi Wu, Kevin Duh and Yuji Matsumoto
PACLIC16: Proc. of the Pacific Asia Conference on Language, Information and Computation, Seoul, S. Korea, Oct 2016
PDF | BibTeX

Non-Linear Similarity Learning for Compositionality
Masashi Tsubaki, Kevin Duh, Masashi Shimbo, and Yuji Matsumoto
AAAI'16: Proceeding of the AAAI Conference on Artificial Intelligence, Pheonix, Arizona, USA
PDF | BibTeX

2015:

Multilingual Topic Models for Bilingual Dictionary Extraction
Xiaodong Liu, Kevin Duh, and Yuji Matsumoto
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Vol. 14, No. 3, June, 2015
PDF | BibTeX

Joint Case Argument Identification for Japanese Predicate Argument Structure Analysis
Hiroki Ouchi, Hiroyuki Shindo, Kevin Duh, Yuji Matsumoto
ACL-IJCNLP'15: Proceedings of Assoc. for Computational Linguistics and Int'l Joint Conf. on NLP , Beijing, China
PDF | BibTeX

Synthetic Word Parsing Improves Chinese Word Segmentation
Fei Cheng, Kevin Duh, Yuji Matsumoto
ACL-IJCNLP'15: Proceedings of Assoc. for Computational Linguistics and Int'l Joint Conf. on NLP, Beijing, China
PDF | BibTeX

Incorporating Both Distributional and Relational Semantics in Word Representations
Daniel Fried and Kevin Duh
ICLR'15: International Conference on Learning Representations (workshop contribution), San Diego, USA
PDF | Long version | BibTeX

Representation Learning using Multi-Task Deep Neural Networks for Semantic Classification & Information Retrieval
Xiaodong Liu, Jianfeng Gao, Xiaodong He, Li Deng, Kevin Duh, and Ye-Yi Wang
NAACL'15: Proceedings of Conf. of North American Chapter of ACL: Human Language Technologies, Denver, USA
PDF | BibTeX

Multi-Target Machine Translation with Multi-Synchronous Context-free Grammar
Graham Neubig, Philip Arthur and Kevin Duh
NAACL'15: Proceedings of Conf. of North American Chapter of ACL: Human Language Technologies, Denver, USA
PDF | Code/Data | BibTeX

Sequential Annotation and Chunking of Chinese Discourse Structure
Frances Yung, Kevin Duh, and Yuji Matsumoto
SIGHAN'15: Proceedings of the Eighth SIGHAN Workshop on Chinese Language Processing, Beijing, China
PDF | Data | BibTeX

Crosslingual Annotation and Analysis of Implicit Discourse Connectives for Machine Translation
Frances Yung, Kevin Duh, and Yuji Matsumoto
DiscoMT'15: Proceedings of EMNLP Workshop on Discourse in Machine Translation, Lisbon, Portugal
PDF | BibTeX

Automation of System Building for State-of-the-art Large Vocabulary Speech Recognition Using Evolution Strategy
Takafumi Moriya, Tomohiro Tanaka, Takahiro Shinozaki, Shinji Watanabe, and Kevin Duh
ASRU'15: Proceedings of the IEEE 2015 Automatic Speech Recognition and Understanding Workshop, Scottsdale, USA
PDF | BibTeX

A Hybrid Ranking Approach to Chinese Spelling Check
Xiaodong Liu, Fei Cheng, Kevin Duh, and Yuji Matsumoto
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Volume 14 Issue 4, Article No.16, pp.17, October 2015
Journal Link

Depth-Gated LSTM
Kaisheng Yao, Trevor Cohn, Katerina Vylomova, Kevin Duh, Chris Dyer
arXiv

2014:

On the Elements of an Accurate Tree-to-String Machine Translation System
Graham Neubig and Kevin Duh
ACL'14: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, USA
PDF | Code/Data | BibTeX

The NAIST-NTT TED Talk Treebank
Graham Neubig, Katsuhito Sudoh, Yusuke Oda, Kevin Duh, Hajime Tsukada, Masaaki Nagata
IWSLT'15: Proceedings of the International Workshop on Spoken Language Translation, Lake Tahoe, USA
PDF | Data | BibTeX

A Framework for Analyzing Semantic Change of Words across Time
Adam Jatowt and Kevin Duh
JCDL/TPDL'14: Proceedings of the Digital Libraries Conference (Joint JCDL/TPDL), London, UK
PDF | BibTeX

Learning Character Representations for Chinese Word Segmentation
Xiaodong Liu, Kevin Duh, Yuji Matsumoto, and Tomoya Iwakura
NIPS 2014 Workshop on Modern Machine Learning and Natural Language Processing, Montreal, Canada
PDF | BibTeX

Creating Stories from Socially Curated Microblog Messages
Akisato Kimura, Kevin Duh, Tsutomu Hirao, Katsuhiko Ishiguro, Tomoharu Iwata, Ching-Man Au Yeung
IEICE TRANSACTIONS on Information and Systems, Vol. E97-D, June, pp. 1557-1566
PDF | BibTeX

Improving Dependency Parsers with Supertags
Hiroki Ouchi, Kevin Duh, Yuji Matsumoto
EACL'14: Proceedings of the 14th Conference of the European Chapter of the ACL, Gothenburg, Sweden
PDF | BibTeX

Analysis and Prediction of Unalignable Words in Parallel Text
Frances Yung , Kevin Duh, Yuji Matsumoto
EACL'14: Proceedings of the 14th Conference of the European Chapter of the ACL, Gothenburg, Sweden
PDF | BibTeX

Parsing Chinese Synthetic Words with a Character-based Dependency Model
Fei Cheng, Kevin Duh, Yuji Matsumoto
LREC'14: Proceedings of the Ninth International Conference on Language Resources and Evaluation, Reykjavik, Iceland
PDF | BibTeX

Identifying collocations using cross-lingual association measures
Lis Pereira, Elga Strafella, Kevin Duh, Yuji Matsumoto
MWE'14: Proceedings of the 10th Workshop on Multiword Expressions, Gothenburg, Sweden
PDF | BibTeX

2013:

Adaptation Data Selection using Neural Language Models: Experiments in Machine Translation
Kevin Duh, Graham Neubig, Katsuhito Sudoh, Hajime Tsukada
ACL'13: Proceedings of the 51th Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria, 2013
PDF | Slides | BibTeX

Managing Information Disparity in Multilingual Document Collections
Kevin Duh, Ching-Man Au Yeung, Tomoharu Iwata, Masaaki Nagata.
ACM Transactions on Speech and Language Processing (TSLP), Volume 10(1), March 2013
Journal Link | Preprint | BibTeX

Modeling and Learning Semantic Co-Compositionality through Prototype Projections and Neural Networks
Masashi Tsubaki, Kevin Duh, Masashi Shimbo, Yuji Matsumoto
EMNLP'13: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, USA, 2013
PDF | Slides | BibTeX

What Information is Helpful for Dependency Based Semantic Role Labeling
Yanyan Luo, Kevin Duh, Yuji Matsumoto
ICJNLP'13: Proceedings of the Sixth International Joint Conference on Natural Language Processing, Nagoya, Japan, 2013
PDF | BibTeX

Topic Models + Word Alignment = A Flexible Framework for Extracting Bilingual Dictionary from Comparable Corpus
Xiaodong Liu, Kevin Duh, Yuji Matsumoto
CoNLL'13: Proceedings of the Conference on Computational Language Learning, Sofia, Bulgaria, 2013
PDF | BibTeX

Hidden Markov Tree Model for Word Alignment
Shuhei Kondo, Kevin Duh, Yuji Matsumoto
WMT'13: Proceedings of the Eighth Workshop on Statistical Machine Translation, Sofia, Bulgaria, 2013
PDF | BibTeX

Multi-metric Optimization using Ensemble Tuning
Baskaran Sankaran, Anoop Sarkar, Kevin Duh
NAACL'13: Proceedings of the Annual Meeting of the North American Chapter of the ACL, Atlanta, USA, 2013
PDF | BibTeX

How Much is Said in a Tweet? A Multilingual, Information-theoretic Perspective
Graham Neubig and Kevin Duh.
AAAI'13 Spring Symposium on Analyzing Microtext, Stanford, USA, 2013
PDF | Poster | BibTeX

Syntax-Based Post-Ordering for Efficient Japanese-to-English Translation
Katsuhito Sudoh, Xianchao Wu, Kevin Duh, Hajime Tsukada, Masaaki Nagata.
ACM Transactions on Asian Language Information Processing (TALIP), Volume 12(3), Aug 2013
Journal Link (PDF) | BibTeX

2012:

Learning to Translate with Multiple Objectives
Kevin Duh, Katsuhito Sudoh, Xianchao Wu, Hajime Tsukada, Masaaki Nagata.
ACL'12: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, Jeju, Korea, 2012
PDF | Slides | BibTeX

Creating Stories: Social Curation of Twitter Messages
Kevin Duh, Tsutomu Hirao, Akisato Kimura, Katsuhiko Ishiguro, Tomoharu Iwata, Ching-Man Au Yeung.
ICWSM'12: Proceedings of the 6th International AAAI Conference on Weblogs and Social Media, Dublin, Ireland, 2012
PDF | BibTeX

Flexible Sample Selection Strategies for Transfer Learning in Ranking
Kevin Duh and Akinori Fujino.
Information Processing and Management Journal, 48(3), pp. 502--512, May 2012
Journal Link | Preprint | BibTeX

A Comparative Study of Target Dependency Structures for Statistical Machine Translation
Xianchao Wu, Katsuhito Sudoh, Kevin Duh, Hajime Tsukada, Masaaki Nagata.
ACL'12: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, Jeju, Korea, 2012
PDF | BibTeX

Bidirectional Semi-Supervised Learning with Graphs
Tomoharu Iwata and Kevin Duh.
ECML/PKDD'12: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Bristol, UK, 2012
PDF | BibTeX

Head Finalization Reordering for Chinese-to-Japanese Machine Translation
Dan Han, Katsuhito Sudoh, Xianchao Wu, Kevin Duh, Hajime Tsukada and Masaaki Nagata.
SSST-6: ACL Workshop on Syntax, Semantics, and Structure in Statistical Translation, Jeju, Korea, 2012
PDF | BibTeX

HPSG-based Preprocessing for English-to-Japanese Translation
Hideki Isozaki, Katsuhito Sudoh, Hajime Tsukada, Kevin Duh.
ACM Transactions on Asian Language Information Processing (TALIP), 11(3), Sept 2012.
PDF | Journal Link | BibTeX

Bilinear Logistic Regression for Factored Diagnosis Problems
Sumit Basu, John Dunagan, Kevin Duh, Kiran-Kumar Munuswamy-Reddy.
Operating Systems Review, 45(3):31-38. Jan 2012 (also presented at SOSP-SLAML 2011)
PDF | Slides BibTeX

2011:

Distributed Learning-to-Rank on Streaming Data using Alternating Direction Method of Multipliers
Kevin Duh, Jun Suzuki, Masaaki Nagata.
NIPS'11 Big Learning Workshop, Sierra Nevada, Spain, 2011
PDF | BibTeX

Alignment Inference and Bayesian Adaptation for Machine Translation
Kevin Duh, Katsuhito Sudoh, Tomoharu Iwata, Hajime Tsukada.
Proceedings of the Machine Translation Summit XIII, Xiamen, China, 2011
PDF | BibTeX

Generalized Minimum Bayes Risk System Combination
Kevin Duh, Katsuhito Sudoh, Xianchao Wu, Hajime Tsukada, Masaaki Nagata.
ICJNLP'11: Proceedings of International Joint Conference on Natural Language Processing, Chiang Mai, Thailand, 2011
PDF | BibTeX

Is Machine Translation Ripe for Cross-lingual Sentiment classification?
Kevin Duh, Akinori Fujino, Masaaki Nagata.
ACL'11: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics Portand, USA, 2011
PDF | BibTeX

Semi-supervised Ranking for Document Retrieval
Kevin Duh and Katrin Kirchhoff.
Computer Speech and Language Journal, vol 25(2), April 2011, pg. 261-281
Journal Link | Preprint | BibTeX

Distributed Minimum Error Rate Training of SMT using Particle Swarm Optimization
Jun Suzuki, Kevin Duh, Masaaki Nagata.
ICJNLP'11: Proceedings of International Joint Conference on Natural Language Processing, Chiang Mai, Thailand, 2011
PDF | BibTeX

Extracting Pre-ordering Rules from Predicate-Argument Structures
Xianchao Wu, Katsuhito Sudoh, Kevin Duh, Hajime Tsukada, Masaaki Nagata.
ICJNLP'11: Proceedings of International Joint Conference on Natural Language Processing, Chiang Mai, Thailand, 2011
PDF | BibTeX [Best Paper Finalist]

Post-ordering in Statistical Machine Translation
Katsuhito Sudoh, Xianchao Wu, Kevin Duh, Hajime Tsukada, Masaaki Nagata.
Proceedings of the Machine Translation Summit XIII, Xiamen, China, 2011
PDF | BibTeX

Extracting Pre-ordering Rules from Chunk-based Dependency Trees for Japanese-to-English Translation
Xianchao Wu, Katsuhito Sudoh, Kevin Duh, Hajime Tsukada, Masaaki Nagata.
Proceedings of the Machine Translation Summit XIII, Xiamen, China, 2011
PDF | BibTeX

Providing Cross-lingual Editing Assistance to Wikipedia Users
Ching-man Au Yeung, Kevin Duh, Masaaki Nagata.
CICLING'11: Proceedings of the 12th International Conference on Intelligent Text Processing and Computational Linguistics, Tokyo, Japan, February, 2011
Springer Link | [Summary @ SIGWEB newsletter] | [Best Presentation Award]

2010:

Analysis of Translation Model Adaptation in SMT
Kevin Duh, Katsuhito Sudoh, and Hajime Tsukada.
IWSLT'10: Proceedings of the International Workshop on Spoken Language Translation, Paris, France, 2010
PDF | Poster | BibTeX

N-best Reranking by Multitask Learning
Kevin Duh, Katsuhito Sudoh, Hajime Tsukada, Hideki Isozaki, and Masaaki Nagata.
WMT'10: Proceedings of the ACL Workshop on Statistical Machine Translation, Uppsala, Sweden, 2010
PDF | Slides | BibTeX

Automatic Evaluation of Translation Quality for Distant Language Pairs
Hideki Isozaki, Tsutomu Hirao, Kevin Duh, Katsuhito Sudoh, Hajime Tsukada.
EMNLP'10: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Boston, USA, 2010
PDF | BibTeX | Code

Head Finalization: A Simple Reordering Rule for SOV Languages
Hideki Isozaki, Hajime Tsukada, Katsuhito Sudoh, and Kevin Duh.
WMT'10: Proceedings of the ACL Workshop on Statistical Machine Translation, Uppsala, Sweden, 2010
PDF BibTeX

Divide and Translate: Improving Long Distance Reordering in Statistical Machine Translation
Katsuhito Sudoh, Kevin Duh, Hajime Tsukada, Tsutomu Hirao, and Masaaki Nagata.
WMT'10: Proceedings of the ACL Workshop on Statistical Machine Translation, Uppsala, Sweden, 2010
PDF BibTeX

Hierarchical Phrase-based Machine Translation with Word-based Reordering Model
Katsuhiko Hayashi, Hajime Tsukada, Katsuhito Sudoh, Kevin Duh, Seiji Yamamoto.
COLING'10: Proceedings of the 23rd International Conference on Computational Linguistics, Beijing, China, 2010
PDF BibTeX

2009:

Learning to Rank with Partially-Labeled Data
Kevin Duh.
PhD Disseration, University of Washington, 2009
PDF | Slides | BibTeX

2008:

Learning to Rank with Partially-Labeled Data
Kevin Duh and Katrin Kirchhoff.
SIGIR'08: ACM SIGIR Conference on Research and Development in Information Retrieval, Singapore, 2008
PDF | PDF@ACM | Slides | BibTeX

Beyond Log-linear Models: Boosted Minimum Error Rate Training for N-best Re-ranking
Kevin Duh and Katrin Kirchhoff.
ACL'08: Proceedings of the ACL: Human Language Technologies, Short Papers, Columbus, USA, 2008
PDF | BibTeX

Ranking vs. Regression in Machine Translation Evaluation
Kevin Duh.
WMT'08: Proceedings of the Third Workshop on Statistical Machine Translation, Columbus, USA, 2008
PDF | BibTeX

Beyond the Search Box: Helping Users find Health information on the Web
Kevin Duh, Shawn Medero, Mike Schultz, and Tom Eng.
HCIR'08: Workshop on Human-Computer Interaction and Information Retrieval, Seattle, USA, 2008
PDF | BibTeX

2006:

Lexicon Acquisition for Dialectal Arabic Using Transductive Learning
Kevin Duh and Katrin Kirchhoff.
EMNLP'06: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Sydney, Australia, 2006
PDF | Slides | BibTeX

Multilingual Dependency Parsing using Bayes Point Machines
Simon Corston-Oliver, Anthony Aue, Kevin Duh, Eric Ringger.
NAACL'06: Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, New York, USA, 2006
PDF | BibTeX | Slides (of a talk I gave at Academia Sinica; refer to paper for updated results)

Morphology-based Language Modeling for Arabic Speech Recognition
Katrin Kirchhoff, Dimitra Vergyri, Jeff Bilmes, Kevin Duh, and Andreas Stolcke.
Computer Speech and Language 20(4), pp.589-608, 2006
Journal Link | BibTeX

2005:

Structured Multi-label Transductive Learning: a Case Study in Lexicon Acquisition
Kevin Duh and Katrin Kirchhoff.
NIPS 2005 Workshop on Advances in Structured Learning for Text and Speech Processing, Whistler, Canada, 2005
PDF | BibTeX

POS Tagging of Dialectal Arabic: A Minimally Supervised Approach
Kevin Duh and Katrin Kirchhoff.
Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages, Ann Arbor, USA, 2005
PDF | BibTeX

Jointly Labeling Multiple Sequences: A Factorial HMM Approach
Kevin Duh.
Proceedings of the ACL Student Research Workshop, Ann Arbor, USA, 2005
PDF | BibTeX

Genetic Triangulation of Graphical Models for Speech and Language Processing
Chris Bartels, Kevin Duh, Jeff Bilmes, Katrin Kirchhoff, and Simon King.
Proceedings of Eurospeech/Interspeech 2005
PDF | BibTeX

2004:

Automatic Learning of Language Model Structure
Kevin Duh and Katrin Kirchhoff.
COLING'04: Proceedings of the 20th International Conference on Computational Linguistics, Geneva, Switzerland, 2004
PDF | Slides | BibTeX

Morphology-Based Language Modeling for Arabic Speech Recognition
Dimitra Vergyri, Katrin Kirchhoff, Kevin Duh, and Andreas Stolcke.
ICSLP/Interspeech'04: Proceedings of International Conference on Spoken Language Processing, Jeju, Korea, 2004
PDF | BibTeX

My fellow co-authors and collaborators

• JHU: Paul McNamee, Ben Van Durme, Matt Post, Philipp Koehn, Sheng Zhang, Rachel Rudinger, Dingquan Wang, Shuoyang Ding, Gaurav Kumar, Huda Khayrallah, Pamela Shapiro, Keisuke Sakaguchi, Mark Dredze, Nanyun (Violet) Peng, Ryan Cotterell David Synder, Chandler May, Adi Renduchintala, Shinji Watanabe
• NAIST: Yuji Matsumoto, Masashi Shimbo, Mamoru Komachi, Satoshi Nakamura, Graham Neubig, Katsuhiko Hayashi, Shuhei Kondo, Xiaodong Liu, Chinh To, Keisuke Sakaguchi, Lis Kanashiro, Fei Cheng, Masashi Tsubaki, Sorami Hisamoto, Frances Yung, Kazuya Kobayashi, Hiroki Ouchi, Daniel Fried,
• NTT: Hajime Tsukada, Katsuhito Sudoh, Masaaki Nagata, Albert Au Yeung, Akinori Fujino, Jun Suzuki, Hideki Isozaki, Xianchao Wu, Tomoharu Iwata, Sanae Fujita, Tsutomu Hirao, Hiroyuki Shindo, Hirotoshi Taira, Akisato Kimura, Katsuhiko Ishiguro
• UW: Katrin Kirchhoff, Jeff Bilmes, Mei Yang, Amittai Axelrod, Chris Bartels
• MSR: Sumit Basu, John Dunagan, Kiran-Kumar Muniswamy-Reddy, Simon Corston-Oliver, Anthony Aue, Eric Ringger Jianfeng Gao
• Other Institutions (Joint Research): Baskaran Sankaran, Anoop Sarkar, Adam Jatowt, Takahiro Shinozaki, Shota Sasaki,