2018 · 12 citations · 30 references
ComputingComputer ScienceLinguisticsComputational LinguisticsMorphologyNatural Language ProcessingDeep LearningDependency GrammarDependency ParsingGrammarLanguage ModelingText GenerationDependency Structure ModelingLinearizationNeural Language ModelsSequence-to-sequence GenerationSimple SentencesSurface Realization
Surface realization is a nontrivial task as it involves taking structured data and producing grammatically and semantically correct utterances. Many competing grammar-based and statistical models for realization still struggle with relatively simple sentences. For our submission to the 2018 Surface Realization Shared Task, we tackle the shallow task by first generating inflected wordforms with a neural sequence-to-sequence model before incrementally linearizing them. For linearization, we use a global linear model trained using early update that makes use of features that take into account the dependency structure and dependency locality. Using this pipeline sufficed to produce surprisingly strong results in the shared task. In future work, we intend to pursue joint approaches to linearization and morphological inflection and incorporating a neural language model into the linearization choices.
30
ADADELTA: An Adaptive Learning Rate Method
Matthew D. Zeiler · arXiv (Cornell University) · 2012 · 5.5K citations · Full text
Online Passive-Aggressive Algorithms
Koby Crammer, Ofer Dekel, Joseph Keshet et al. · 2006 · 1.5K citations
Online Passive-Aggressive Algorithms
CrammerKoby, DekelOfer, KeshetJoseph et al. · Journal of Machine Learning Research · 2006 · 903 citations