New SOTA added (sebastianruder#558)

* New SOTA added * Update semantic_parsing.md * Update english/semantic_parsing.md Co-authored-by: Sebastian Ruder <[email protected]> Co-authored-by: Sebastian Ruder <[email protected]>
urikz · Jul 5, 2021 · 834063c · 834063c
1 parent a05969e
commit 834063c
Showing 1 changed file with 10 additions and 0 deletions.
diff --git a/english/semantic_parsing.md b/english/semantic_parsing.md
@@ -78,6 +78,7 @@ Models are evaluated based on [smatch](https://amr.isi.edu/smatch-13.pdf).
 
 | Model           | Smatch  |  Paper / Source |
 | ------------- | :-----:| --- |
+| One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline (Bevilacqua et al., 2020) | 84.5 | [One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline](https://ojs.aaai.org/index.php/AAAI/article/view/17489) |
 | AMR Parsing with Sequence-to-Sequence Pre-training (Xu, et al., 2020) | 81.4 | [Improving AMR Parsing with Sequence-to-Sequence Pre-training](https://arxiv.org/pdf/2010.01771.pdf) |
 | Pushing the Limits of AMR Parsing with Self-Learning (Young-Suk Lee et al., 2020) | 81.3 | [Pushing the Limits of AMR Parsing with Self-Learning](https://arxiv.org/abs/2010.10673) |
 | AMR Parsing via Graph-Sequence Iterative Inference (Cai and Lam, 2020)&hearts;&spades; | 80.2 | [AMR Parsing via Graph-Sequence Iterative Inference](https://arxiv.org/pdf/2004.05572.pdf) |
@@ -90,6 +91,15 @@ Models are evaluated based on [smatch](https://amr.isi.edu/smatch-13.pdf).
 | ChSeq + 100K (van Noord and Bos, 2017)&hearts; | 71.0 | [Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations](https://clinjournal.org/clinj/article/view/72/64) |
 | Neural-Pointer (Buys and Blunsom, 2017)&hearts;&spades; | 61.9 | [Oxford at SemEval-2017 Task 9: Neural AMR Parsing with Pointer-Augmented Attention](http://aclweb.org/anthology/S17-2157) |
 
+### LDC2020T02
+The dataset contains 59,255 AMRs split across training, dev, and test partitions.
+
+Models are evaluated based on [smatch](https://amr.isi.edu/smatch-13.pdf).
+| Model           | Smatch  |  Paper / Source |
+| ------------- | :-----:| --- |
+| One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline (Bevilacqua et al., 2020) | 83.0 | [One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline](https://ojs.aaai.org/index.php/AAAI/article/view/17489) |
+
+
 ## DRS parsing
 
 Discourse Representation Structures (DRS) are formal meaning representations introduced by [Discourse Representation Theory](https://en.wikipedia.org/wiki/Discourse_representation_theory). DRS parsing is a complex task, comprising other NLP tasks, such as semantic role labeling, word sense disambiguation, co-reference resolution and named entity tagging. Also, DRSs show explicit scope for certain operators, which allows for a more principled and linguistically motivated treatment of negation, modals and quantification, as has been advocated in formal semantics. Moreover, DRSs can be translated to formal logic, which allows for automatic forms of inference by third parties.