Parser for Abstract Meaning Representation using Learning to Search
This work addresses the problem of semantic parsing for natural language processing researchers and practitioners, representing an incremental advance with specific performance gains.
The authors tackled the problem of parsing English sentences into Abstract Meaning Representation (AMR) by developing a novel technique using SEARN, a Learning to Search approach, which models concept and relation learning in a unified framework. They achieved an absolute improvement of 2% to 6% over the state-of-the-art on multiple datasets from varied domains.
We develop a novel technique to parse English sentences into Abstract Meaning Representation (AMR) using SEARN, a Learning to Search approach, by modeling the concept and the relation learning in a unified framework. We evaluate our parser on multiple datasets from varied domains and show an absolute improvement of 2% to 6% over the state-of-the-art. Additionally we show that using the most frequent concept gives us a baseline that is stronger than the state-of-the-art for concept prediction. We plan to release our parser for public use.