arXiv:1805.09007
공식 코드 · Papers with Code
A Transition-based Algorithm for Unrestricted AMR Parsing
원문 초록
Non-projective parsing can be useful to handle cycles and reentrancy in AMR graphs. We explore this idea and introduce a greedy left-to-right non-projective transition-based parser. At each parsing configuration, an oracle decides whether to create a concept or whether to connect a pair of existing concepts. The algorithm handles reentrancy and arbitrary cycles natively, i.e. within the transition system itself. The model is evaluated on the LDC2015E86 corpus, obtaining results close to the state of the art, including a Smatch of 64%, and showing good behavior on reentrant edges.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding
Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsing
AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation Suite
AMR Parsing with Causal Hierarchical Attention and Pointers
Guiding AMR Parsing with Reverse Graph Linearization
Incorporating Graph Information in Transformer-based AMR Parsing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.