| Overcoming a Theoretical Limitation of Self-Attention | 0 | 0.34 | 2022 |
| Learning Hierarchical Structures with Differentiable Nondeterministic Stacks | 0 | 0.34 | 2022 |
| Measuring Human Perception to Improve Handwritten Document Transcription | 0 | 0.34 | 2022 |
| Syntax-Based Attention Masking for Neural Machine Translation | 0 | 0.34 | 2021 |
| Data Augmentation By Concatenation For Low-Resource Translation: A Mystery And A Solution | 0 | 0.34 | 2021 |
| Representing Unordered Data Using Complex-Weighted Multiset Automata. | 0 | 0.34 | 2020 |
| Factor Graph Grammars | 0 | 0.34 | 2020 |
| Look It Up: Bilingual and Monolingual Dictionaries Improve Neural Machine Translation | 0 | 0.34 | 2020 |
| Learning Context-Free Languages with Nondeterministic Stack RNNs | 0 | 0.34 | 2020 |
| Learning Hyperedge Replacement Grammars for Graph Generation. | 0 | 0.34 | 2019 |
| Efficiency through Auto-Sizing - Notre Dame NLP's Submission to the WNGT 2019 Efficiency Task. | 0 | 0.34 | 2019 |
| Auto-Sizing the Transformer Network - Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation. | 0 | 0.34 | 2019 |
| Growing Better Graphs With Latent-Variable Probabilistic Graph Grammars. | 0 | 0.34 | 2018 |
| Neural Machine Translation of Text from Non-Native Speakers. | 0 | 0.34 | 2018 |
| Improving Lexical Choice in Neural Machine Translation. | 4 | 0.41 | 2018 |
| Weighted DAG Automata for Semantic Graphs. | 1 | 0.36 | 2018 |
| Composing Finite State Transducers on GPUs. | 0 | 0.34 | 2018 |
| Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention. | 1 | 0.34 | 2018 |
| Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource. | 0 | 0.34 | 2018 |
| Tied Multitask Learning for Neural Speech Translation. | 8 | 0.46 | 2018 |
| Correcting Length Bias in Neural Machine Translation. | 2 | 0.37 | 2018 |
| Composing Finite State Transducers On Gpus | 0 | 0.34 | 2018 |
| Incident-Driven Machine Translation and Name Tagging for Low-resource Languages. | 0 | 0.34 | 2018 |
| A case study on using speech-to-translation alignments for language documentation. | 4 | 0.49 | 2017 |
| Improved Neural Machine Translation With A Syntax-Aware Encoder And Decoder | 25 | 0.73 | 2017 |
| Spoken Term Discovery for Language Documentation using Translations. | 0 | 0.34 | 2017 |
| Top-Rank Enhanced Listwise Optimization for Statistical Machine Translation. | 0 | 0.34 | 2017 |
| Decoding with Finite-State Transducers on GPUs. | 0 | 0.34 | 2017 |
| DyNet: The Dynamic Neural Network Toolkit. | 76 | 2.35 | 2017 |
| Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation. | 4 | 0.41 | 2017 |
| Decoding with Finite-State Transducers on GPUs. | 0 | 0.34 | 2017 |
| An Attentional Model for Speech Translation Without Transcription. | 12 | 0.62 | 2016 |
| Growing Graphs from Hyperedge Replacement Graph Grammars | 3 | 0.37 | 2016 |
| An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages. | 3 | 0.43 | 2016 |
| Supervised Phrase Table Triangulation with Neural Word Embeddings for Low-Resource Languages | 0 | 0.34 | 2015 |
| Auto-Sizing Neural Networks: With Applications to n-gram Language Models | 5 | 0.45 | 2015 |
| Model Invertibility Regularization: Sequence Alignment With or Without Parallel Data. | 4 | 0.49 | 2015 |
| Multi-Task Word Alignment Triangulation for Low-Resource Languages. | 2 | 0.39 | 2015 |
| Kneser-Ney Smoothing On Expected Counts | 9 | 0.48 | 2014 |
| Parsing Graphs with Hyperedge Replacement Grammars. | 28 | 1.53 | 2013 |
| Decoding with Large-Scale Neural Language Models Improves Translation. | 94 | 5.39 | 2013 |
| Machine Translation for Language Preservation. | 3 | 0.42 | 2012 |
| Soft syntactic constraints for Arabic---English hierarchical phrase-based translation | 7 | 0.43 | 2012 |
| Smaller alignment models for better translations: unsupervised word alignment with the l0-norm | 0 | 0.34 | 2012 |
| An exploration of forest-to-string translation: does translation help or hurt parsing? | 1 | 0.35 | 2012 |
| Hope and fear for discriminative training of statistical translation models | 20 | 0.68 | 2012 |
| Two easy improvements to lexical weighting | 15 | 0.64 | 2011 |
| Rule Markov models for fast tree-to-string translation | 10 | 0.56 | 2011 |
| Models and training for unsupervised preposition sense disambiguation | 4 | 0.41 | 2011 |
| Language-independent parsing with empty elements | 27 | 1.00 | 2011 |
