AMR Parsing using Stack-LSTMs
Miguel Ballesteros, Yaser Al-Onaizan
Abstract
We present a transition-based AMR parser that directly generates AMR parses from plain text. We use Stack-LSTMs to represent our parser state and make decisions greedily. In our experiments, we show that our parser achieves very competitive scores on English using only AMR training data. Adding additional information, such as POS tags and dependency trees, improves the results further.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Semantic Parsing | LDC2014T12 | F1 Full | 63 | Transition-based parser-Stack-LSTM |
| Semantic Parsing | LDC2014T12 | F1 Newswire | 68 | Transition-based parser-Stack-LSTM |
| AMR Parsing | LDC2014T12 | F1 Full | 63 | Transition-based parser-Stack-LSTM |
| AMR Parsing | LDC2014T12 | F1 Newswire | 68 | Transition-based parser-Stack-LSTM |
Related Papers
LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops2025-06-17Hybrid Meta-learners for Estimating Heterogeneous Treatment Effects2025-06-16Private MEV Protection RPCs: Benchmark Stud2025-05-26FiLLM -- A Filipino-optimized Large Language Model based on Southeast Asia Large Language Model (SEALLM)2025-05-25The taggedPBC: Annotating a massive parallel corpus for crosslinguistic investigations2025-05-18Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding2025-05-13A Comparative Analysis of Static Word Embeddings for Hungarian2025-05-12Panoramic Out-of-Distribution Segmentation2025-05-06