ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing
This paper presents the system used in our submission to the \textit{CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing}. Our system is a graph-based parser which combines an extended pointer-generator network that generates nodes and a second-order mean field variational inference module that predicts edges. Our system achieved \nth{1} and \nth{2} place for the DM and PSD frameworks respectively on the in-framework ranks and achieved \nth{3} place for the DM framework on the cross-framework ranks.
Code (1)
Tasks
Variational InferenceSimilar Papers 제목 키워드 기반
Sequence Transduction with Recurrent Neural Networks
Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, protein secondary structure prediction and …
Machine TranslationPhoneme RecognitionSpeech Recognitiontext-to-speech+2Second Position Clitics and Monadic Second-Order Transduction
AMR Parsing as Sequence-to-Graph Transduction
We propose an attention-based model that treats AMR parsing as sequence-to-graph transduction. Unlike most AMR parsers that rely on pre-trained aligners, external semantic resources, or data augmentation, our proposed pa…
AMR ParsingSemantic ParsingExact Hard Monotonic Attention for Character-Level Transduction
Many common character-level, string-to string transduction tasks, e.g., grapheme-tophoneme conversion and morphological inflection, consist almost exclusively of monotonic transductions. However, neural sequence-to seque…
Hard AttentionInductive BiasMorphological InflectionString Transduction with Target Language Models and Insertion Handling
Many character-level tasks can be framed as sequence-to-sequence transduction, where the target is a word from a natural language. We show that leveraging target language models derived from unannotated target corpora, c…