作者: Philip Resnik , Hal Daumé , Yogarshi Vyas , Sudha Rao
DOI:
关键词:
摘要: We develop a novel technique to parse English sentences into Abstract Meaning Representation (AMR) using SEARN, Learning Search approach, by modeling the concept and relation learning in unified framework. evaluate our parser on multiple datasets from varied domains show an absolute improvement of 2% 6% over state-of-the-art. Additionally we that most frequent gives us baseline is stronger than state-of-the-art for prediction. plan release public use.