Showing 1–20 of 30 results
/ Date/ Name
Dec 20, 2016Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic OraclesNov 19, 2015Good, Better, Best: Choosing Word Embedding ContextJun 21, 2016Incremental Parsing with Minimal Features Using Bi-Directional LSTMAug 23, 2016Tracking Amendments to Legislation and Other Political Texts with a Novel Minimum-Edit-Distance Algorithm: DocuToadsJul 11, 2016Exploring the Political Agenda of the European Parliament Using a Dynamic Topic Modeling ApproachAug 23, 2020Learn to Talk via Proactive Knowledge TransferJan 15, 2020Non-Autoregressive Machine Translation with Disentangled Context TransformerOct 15, 2021Tricks for Training Sparse Translation ModelsApr 17, 2021XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word AlignmentJun 22, 2021On the Evaluation of Machine Translation for Terminology ConsistencyMar 27, 2026Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text AnnotationSep 17, 2021Classification-based Quality Estimation: Small and Efficient Models for Real-world ApplicationsDec 30, 2020Improving Zero-Shot Translation by Disentangling Positional InformationMar 25, 2022Data Selection Curriculum for Neural Machine TranslationSep 1, 2018Simple Fusion: Return of the Language ModelFeb 7, 2023Efficiently Upgrading Multilingual Machine Translation Models to Support More LanguagesMay 22, 2022Multilingual Machine Translation with Hyper-AdaptersApr 29, 2022How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?Jun 5, 2022Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow DecodersJul 11, 2022No Language Left Behind: Scaling Human-Centered Machine Translation