Hitachi at MRP 2020: Text-to-Graph-Notation Transducer
This paper presents our proposed parser for the shared task on Meaning Representation Parsing (MRP 2020) at CoNLL, where participant systems were required to parse five types of graphs in different languages. We propose to unify these tasks as a text-to-graph-notation transduction in which we convert an input text into a graph notation. To this end, we designed a novel Plain Graph Notation (PGN) that handles various graphs universally. Then, our parser predicts a PGN-based sequence by leveraging Transformers and biaffine attentions. Notably, our parser can handle any PGN-formatted graphs with fewer framework-specific modifications. As a result, ensemble versions of the parser tied for 1st place in both cross-framework and cross-lingual tracks.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Recognizing Mentions of Adverse Drug Reaction in Social Media Using Knowledge-Infused Recurrent Models
Recognizing mentions of Adverse Drug Reactions (ADR) in social media is challenging: ADR mentions are context-dependent and include long, varied and unconventional descriptions as compared to more formal medical symptom …
Active LearningKnowledge Graph EmbeddingsTowards a morphological transducer and orthography converter for Western Tlacolula Valley Zapotec
This paper presents work towards a morphological transducer and orthography converter for Dizhsa, or San Lucas Quiaviní Zapotec, an endangered Western Tlacolula Valley Zapotec language. The implementation of various aspe…
Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter
Accurate recognition of rare and new words remains a pressing problem for contextualized Automatic Speech Recognition (ASR) systems. Most context-biasing methods involve modification of the ASR model or the beam-search d…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1Powerful and Extensible WFST Framework for RNN-Transducer Losses
This paper presents a framework based on Weighted Finite-State Transducers (WFST) to simplify the development of modifications for RNN-Transducer (RNN-T) loss. Existing implementations of RNN-T use CUDA-related code, whi…