---
title: "Neural Semantic Parsing by Character-based — Noord 2017"
description: "The paper asks how far a purely character-level sequence-to-sequence model can go in semantic parsing, specifically in producing Abstract Meaning…"
authors: ["Rik van Noord", "Johan Bos"]
year: 2017
venue: "arXiv:1705.09980"
source: "https://arxiv.org/abs/1705.09980"
doi: "10.48550/arxiv.1705.09980"
arxiv: "1705.09980"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/noord-2017-neural-semantic-parsing-character-based/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/noord-2017-neural-semantic-parsing-character-based/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2017](https://md.research.elamur.ai/free/papers/2017/page/2/) / Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations

# Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations

**Authors:** [Rik van Noord](https://md.research.elamur.ai/free/authors/rik-van-noord/), [Johan Bos](https://md.research.elamur.ai/free/authors/johan-bos/) · **Year:** 2017 · **Venue:** arXiv:1705.09980 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1705.09980) · [PDF](https://arxiv.org/pdf/1705.09980) · [DOI 10.48550/arxiv.1705.09980](https://doi.org/10.48550/arxiv.1705.09980) · [arXiv 1705.09980](https://arxiv.org/abs/1705.09980) · [OpenAlex](https://openalex.org/W2619249607)

**Citations:** 71 citations (openalex-snapshot · 2026-10-14) · [66](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
The paper asks how far a purely character-level sequence-to-sequence model can go in semantic parsing, specifically in producing Abstract Meaning Representations (AMRs) from English sentences. The authors start by reproducing the approach of Barzdins and Gosko (2016). They train an OpenNMT model with a bidirectional encoder and attention on the LDC2016E25 AMR release. AMRs are linearised as plain strings, with variables and wiki links removed beforehand and restored afterwards by heuristics. This baseline gets 53.1 Smatch F-score. They then test five improvements separately:
- reordering AMR branches to follow the sentence's word order
- adding automatic POS tags to the input
- merging frequent character sequences into "super characters"
- pre-training plus model averaging
- adding silver-standard AMRs produced by existing parsers

Silver data helps most. All techniques together reach 71.0 F, which was the best published AMR parsing score at the time. This matters because a simple, feature-light neural translation setup matched or beat heavily engineered traditional parsers. It also shows that linguistic signals like POS tags still help neural models.

## Key points
- **Data:** LDC2016E25 provides 36,521 training, 1,368 dev and 1,371 test AMRs. Evaluation uses Smatch triple matching.
- **Score progression on the test set:**
  - baseline: 53.1
  - branch reordering: 58.3
  - POS tags: 57.2
  - super characters: 57.4
  - pre-training/averaging: 58.7
  - silver data: 64.0
  - all combined: 71.0
- **Word-level input fails:** word-based variants of their model never exceeded 30.0 F, while character-level input avoids this problem.
- **Smaller training set:** trained on the older LDC2015E86 (16,833 gold instances), the system still scores 68.5. Only Foland and Martin (2017), at 70.7, beat that.
- **Fine-grained evaluation (Damonte et al. 2017 metrics):**
  - Precision is higher than recall on every metric.
  - The system beats CAMR, JAMR-16 and AMR-eager on five of eight sub-metrics.
  - It is weaker on concepts, named entities and wikification.

## Interesting ideas
- **Strip arbitrary symbols from the target.** Variable names, co-reference markers and wiki links carry no learnable meaning, so they are removed and reconstructed in post-processing. Hiding such tokens from a generator could help any structured-output task, such as code, SQL or graph generation.
- **Reorder the output to mirror the input.** When the order of sibling elements in the target structure does not matter, sorting them to follow the source sentence makes the mapping more monotone for attention. This is a cheap trick for other tree- or graph-to-text alignments.
- **Super characters as a middle ground.** Frequent character sequences are collapsed into single symbols, which shortens sequences while keeping character-level robustness. This could suit morphologically rich languages like Ukrainian, where pure word vocabularies become sparse.
- **Prune duplicated output after decoding.** Seq2seq decoders tend to repeat material, which hurts precision. Removing repeated leaf nodes is a simple post-hoc fix that raised the dev baseline from 54.8 to 55.5 F, and it applies to other generation tasks with the same issue.
- **Bootstrap with silver data from existing parsers.** Training on large automatically parsed corpora gave the biggest single gain. This is attractive for low-resource settings where a decent conventional parser exists but gold annotation is scarce.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Machine translation](https://md.research.elamur.ai/free/shelves/machine-translation/)

Topics: [Part-of-speech tagging](https://md.research.elamur.ai/free/topics/part-of-speech-tagging/)

## Cited by

Cited by

66 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 61 not yet.

- [The First Shared Task on Discourse Representation Structure Parsing](https://md.research.elamur.ai/free/papers/abzianidze-2019-first-shared-task-discourse-representation/)
- [AMR Parsing via Graph-Sequence Iterative Inference](https://md.research.elamur.ai/free/papers/cai-2020-amr-parsing-graph-sequence-iterative/)
- [ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation](https://md.research.elamur.ai/free/papers/huang-2023-paraamr-large-scale-syntactically-diverse/)
- [Dealing with Co-reference in Neural Semantic Parsing](https://md.research.elamur.ai/free/papers/noord-2017-dealing-co-reference-neural-semantic/)
- [A Structured Syntax-Semantics Interface for English-AMR Alignment](https://md.research.elamur.ai/free/papers/szubert-2018-structured-syntax-semantics-interface-english/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{noord2017neural,
  title = {{Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations}},
  author = {Noord, Rik van and Bos, Johan},
  year = {2017},
  doi = {10.48550/arxiv.1705.09980},
  eprint = {1705.09980},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1705.09980}
}
```

- [← previous Neural Net Models of Open-domain Discourse Coherence](https://md.research.elamur.ai/free/papers/li-2017-neural-net-models-open-domain/)
- [next → Neural-based Context Representation Learning for Dialog Act Classification](https://md.research.elamur.ai/free/papers/ortega-2017-neural-based-context-representation-learning/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/papers/2017/page/2/)

## References

39 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abzianidze, Lasha, Johannes Bjerva, Kilian Evang, Hessel Haagsma, Rik van Noord, Pierre Ludmann, Duc-Duy Nguyen, and Johan Bos (2017), The Parallel Meaning Bank: Towards a Multilingual Corpus of Translations Annotated with Compositional Meaning Representations, Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, Association for Computational Linguistics, Valencia, Spain, pp. 242–247. [find](https://scholar.google.com/scholar?q=Abzianidze%2C+Lasha%2C+Johannes+Bjerva%2C+Kilian+Evang%2C+Hessel+Haagsma%2C+Rik+van+Noord%2C+Pierre+Ludmann%2C+Duc%2DDuy+Nguyen%2C+and+Johan+Bos+%282017%29%2C+The+Parallel+Meaning+Bank%3A+Towards+a+Multilingual+Corpus+of+Trans) [our card](https://md.research.elamur.ai/free/papers/abzianidze-2017-parallel-meaning-bank-multilingual-corpus/)
2. Artzi, Yoav, Kenton Lee, and Luke Zettlemoyer (2015), Broad-coverage CCG Semantic Parsing with AMR, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Lisbon, Portugal, pp. 1699–1710. [find](https://scholar.google.com/scholar?q=Artzi%2C+Yoav%2C+Kenton+Lee%2C+and+Luke+Zettlemoyer+%282015%29%2C+Broad%2Dcoverage+CCG+Semantic+Parsing+with+AMR%2C+Proceedings+of+the+2015+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+Association+)
3. Banarescu, Laura, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf H̃ermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider (2013a), Abstract Meaning Representation for Sembanking, Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, Sofia, Bulgaria, pp. 178–186. http://www.aclweb.org/anthology/W13-2322. [↗](https://aclanthology.org/W13-2322/) [our card](https://md.research.elamur.ai/free/papers/banarescu-2013-abstract-meaning-representation-sembanking/)
4. Banarescu, Laura, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider (2013b), Abstract Meaning Representation for Sembanking, Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, Association for Computational Linguistics, Sofia, Bulgaria, pp. 178–186. [find](https://scholar.google.com/scholar?q=Banarescu%2C+Laura%2C+Claire+Bonial%2C+Shu+Cai%2C+Madalina+Georgescu%2C+Kira+Griffitt%2C+Ulf+Hermjakob%2C+Kevin+Knight%2C+Philipp+Koehn%2C+Martha+Palmer%2C+and+Nathan+Schneider+%282013b%29%2C+Abstract+Meaning+Representation+fo) [our card](https://md.research.elamur.ai/free/papers/banarescu-2013-abstract-meaning-representation-sembanking/)
5. Barzdins, Guntis and Didzis Gosko (2016), RIGA at SemEval-2016 Task 8: Impact of Smatch Extensions and Character-Level Neural Translation on AMR Parsing Accuracy, Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), Association for Computational Linguistics, San Diego, California. [find](https://scholar.google.com/scholar?q=Barzdins%2C+Guntis+and+Didzis+Gosko+%282016%29%2C+RIGA+at+SemEval%2D2016+Task+8%3A+Impact+of+Smatch+Extensions+and+Character%2DLevel+Neural+Translation+on+AMR+Parsing+Accuracy%2C+Proceedings+of+the+10th+International)
6. Basile, Valerio, Johan Bos, Kilian Evang, and Noortje Venhuizen (2012), Developing a large semantically annotated corpus, Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC 2012), Istanbul, Turkey, pp. 3196–3200. [find](https://scholar.google.com/scholar?q=Basile%2C+Valerio%2C+Johan+Bos%2C+Kilian+Evang%2C+and+Noortje+Venhuizen+%282012%29%2C+Developing+a+large+semantically+annotated+corpus%2C+Proceedings+of+the+Eighth+International+Conference+on+Language+Resources+and+E) [our card](https://md.research.elamur.ai/free/papers/basile-2012-developing-large-semantically-annotated-corpus/)
7. Bjerva, Johannes, Johan Bos, and Hessel Haagsma (2016), The Meaning Factory at SemEval-2016 Task 8: Producing AMRs with Boxer, Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), Association for Computational Linguistics, San Diego, California, pp. 1179–1184. [find](https://scholar.google.com/scholar?q=Bjerva%2C+Johannes%2C+Johan+Bos%2C+and+Hessel+Haagsma+%282016%29%2C+The+Meaning+Factory+at+SemEval%2D2016+Task+8%3A+Producing+AMRs+with+Boxer%2C+Proceedings+of+the+10th+International+Workshop+on+Semantic+Evaluation+%28Se)
8. Bos, Johan (2015), Open-Domain Semantic Parsing with Boxer, in Megyesi, Beáta, editor, Proceedings of the 20th Nordic Conference of Computational Linguistics (NODALIDA 2015), pp. 301– 304. [find](https://scholar.google.com/scholar?q=Bos%2C+Johan+%282015%29%2C+Open%2DDomain+Semantic+Parsing+with+Boxer%2C+in+Megyesi%2C+Bea%CC%81ta%2C+editor%2C+Proceedings+of+the+20th+Nordic+Conference+of+Computational+Linguistics+%28NODALIDA+2015%29%2C+pp%2E+301%E2%80%93+304%2E)
9. Bos, Johan, Stephen Clark, Mark Steedman, James R. Curran, and Julia Hockenmaier (2004), Wide-Coverage Semantic Representations from a CCG Parser, Proceedings of the 20th International Conference on Computational Linguistics (COLING ’04), Geneva, Switzerland, pp. 1240–1246. [find](https://scholar.google.com/scholar?q=Bos%2C+Johan%2C+Stephen+Clark%2C+Mark+Steedman%2C+James+R%2E+Curran%2C+and+Julia+Hockenmaier+%282004%29%2C+Wide%2DCoverage+Semantic+Representations+from+a+CCG+Parser%2C+Proceedings+of+the+20th+International+Conference+on+C)
10. Bos, Johan, Valerio Basile, Kilian Evang, Noortje Venhuizen, and Johannes Bjerva (2017), The Groningen Meaning Bank, in Ide, Nancy and James Pustejovsky, editors, Handbook of Linguistic Annotation, Vol. 2, Springer, pp. 463–496. [find](https://scholar.google.com/scholar?q=Bos%2C+Johan%2C+Valerio+Basile%2C+Kilian+Evang%2C+Noortje+Venhuizen%2C+and+Johannes+Bjerva+%282017%29%2C+The+Groningen+Meaning+Bank%2C+in+Ide%2C+Nancy+and+James+Pustejovsky%2C+editors%2C+Handbook+of+Linguistic+Annotation%2C+Vo)
11. Butler, Alastair (2010), The Semantics of Grammatical Dependencies, Vol. 23, Emerald Group Publishing Limited. [find](https://scholar.google.com/scholar?q=Butler%2C+Alastair+%282010%29%2C+The+Semantics+of+Grammatical+Dependencies%2C+Vol%2E+23%2C+Emerald+Group+Publishing+Limited%2E)
12. Cai, Shu and Kevin Knight (2013), Smatch: an Evaluation Metric for Semantic Feature Structures, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Association for Computational Linguistics, Sofia, Bulgaria, pp. 748–752. [find](https://scholar.google.com/scholar?q=Cai%2C+Shu+and+Kevin+Knight+%282013%29%2C+Smatch%3A+an+Evaluation+Metric+for+Semantic+Feature+Structures%2C+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+2%3A+Short)
13. Chung, Junyoung, Kyunghyun Cho, and Yoshua Bengio (2016), NYU-MILA Neural Machine Translation Systems for WMT16, Proceedings of the First Conference on Machine Translation, Association for Computational Linguistics, Berlin, Germany, pp. 268–271. [find](https://scholar.google.com/scholar?q=Chung%2C+Junyoung%2C+Kyunghyun+Cho%2C+and+Yoshua+Bengio+%282016%29%2C+NYU%2DMILA+Neural+Machine+Translation+Systems+for+WMT16%2C+Proceedings+of+the+First+Conference+on+Machine+Translation%2C+Association+for+Computation)
14. Clark, Stephen, James R Curran, and Miles Osborne (2003), Bootstrapping POS taggers using unlabelled data, Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003-Volume 4, Association for Computational Linguistics, pp. 49–55. [find](https://scholar.google.com/scholar?q=Clark%2C+Stephen%2C+James+R+Curran%2C+and+Miles+Osborne+%282003%29%2C+Bootstrapping+POS+taggers+using+unlabelled+data%2C+Proceedings+of+the+seventh+conference+on+Natural+language+learning+at+HLT%2DNAACL+2003%2DVolume+4)
15. Collins, Michael, Philipp Koehn, and Ivona Kučerová (2005), Clause restructuring for statistical machine translation, Proceedings of the 43rd annual meeting on association for computational linguistics, Association for Computational Linguistics, pp. 531–540. [find](https://scholar.google.com/scholar?q=Collins%2C+Michael%2C+Philipp+Koehn%2C+and+Ivona+Kuc%CC%8Cerova%CC%81+%282005%29%2C+Clause+restructuring+for+statistical+machine+translation%2C+Proceedings+of+the+43rd+annual+meeting+on+association+for+computational+linguist) [our card](https://md.research.elamur.ai/free/papers/collins-2005-clause-restructuring-statistical-machine-translation/)
16. Copestake, Ann, Dan Flickinger, Ivan Sag, and Carl Pollard (2005), Minimal Recursion Semantics: An introduction, Journal of Research on Language and Computation 3 (2–3), pp. 281–332. [find](https://scholar.google.com/scholar?q=Copestake%2C+Ann%2C+Dan+Flickinger%2C+Ivan+Sag%2C+and+Carl+Pollard+%282005%29%2C+Minimal+Recursion+Semantics%3A+An+introduction%2C+Journal+of+Research+on+Language+and+Computation+3+%282%E2%80%933%29%2C+pp%2E+281%E2%80%93332%2E)
17. Daiber, Joachim, Max Jakob, Chris Hokamp, and Pablo N. Mendes (2013), Improving Efficiency and Accuracy in Multilingual Entity Extraction, Proceedings of the 9th International Conference on Semantic Systems (I-Semantics). [find](https://scholar.google.com/scholar?q=Daiber%2C+Joachim%2C+Max+Jakob%2C+Chris+Hokamp%2C+and+Pablo+N%2E+Mendes+%282013%29%2C+Improving+Efficiency+and+Accuracy+in+Multilingual+Entity+Extraction%2C+Proceedings+of+the+9th+International+Conference+on+Semantic+S)
18. Damonte, Marco, Shay B. Cohen, and Giorgio Satta (2017), An Incremental Parser for Abstract Meaning Representation, Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, Association for Computational Linguistics, Valencia, Spain, pp. 536–546. [find](https://scholar.google.com/scholar?q=Damonte%2C+Marco%2C+Shay+B%2E+Cohen%2C+and+Giorgio+Satta+%282017%29%2C+An+Incremental+Parser+for+Abstract+Meaning+Representation%2C+Proceedings+of+the+15th+Conference+of+the+European+Chapter+of+the+Association+for+Co) [our card](https://md.research.elamur.ai/free/papers/damonte-2017-incremental-parser-abstract-meaning-representation/)
19. Denkowski, Michael and Graham Neubig (2017), Stronger Baselines for Trustable Results in Neural Machine Translation, Proceedings of the First Workshop on Neural Machine Translation, Association for Computational Linguistics, Vancouver, pp. 18–27. [find](https://scholar.google.com/scholar?q=Denkowski%2C+Michael+and+Graham+Neubig+%282017%29%2C+Stronger+Baselines+for+Trustable+Results+in+Neural+Machine+Translation%2C+Proceedings+of+the+First+Workshop+on+Neural+Machine+Translation%2C+Association+for+Co) [our card](https://md.research.elamur.ai/free/papers/denkowski-2017-stronger-baselines-trustable-results-neural/)
20. Dong, Li and Mirella Lapata (2016), Language to Logical Form with Neural Attention, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Berlin, Germany, pp. 33–43. [find](https://scholar.google.com/scholar?q=Dong%2C+Li+and+Mirella+Lapata+%282016%29%2C+Language+to+Logical+Form+with+Neural+Attention%2C+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+Ass)
21. Flanigan, Jeffrey, Chris Dyer, Noah A Smith, and Jaime Carbonell (2016), CMU at SemEval-2016 task 8: Graph-based AMR parsing with infinite ramp loss, Proceedings of SemEval pp. 1202– 1206. [find](https://scholar.google.com/scholar?q=Flanigan%2C+Jeffrey%2C+Chris+Dyer%2C+Noah+A+Smith%2C+and+Jaime+Carbonell+%282016%29%2C+CMU+at+SemEval%2D2016+task+8%3A+Graph%2Dbased+AMR+parsing+with+infinite+ramp+loss%2C+Proceedings+of+SemEval+pp%2E+1202%E2%80%93+1206%2E)
22. Flanigan, Jeffrey, Sam Thomson, Jaime Carbonell, Chris Dyer, and Noah A. Smith (2014), A Discriminative Graph-Based Parser for the Abstract Meaning Representation, Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Baltimore, Maryland, pp. 1426–1436. [find](https://scholar.google.com/scholar?q=Flanigan%2C+Jeffrey%2C+Sam+Thomson%2C+Jaime+Carbonell%2C+Chris+Dyer%2C+and+Noah+A%2E+Smith+%282014%29%2C+A+Discriminative+Graph%2DBased+Parser+for+the+Abstract+Meaning+Representation%2C+Proceedings+of+the+52nd+Annual+Meeti)
23. Foland, William and James H. Martin (2017), Abstract Meaning Representation Parsing using LSTM Recurrent Neural Networks, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Vancouver, Canada, pp. 463–472. [find](https://scholar.google.com/scholar?q=Foland%2C+William+and+James+H%2E+Martin+%282017%29%2C+Abstract+Meaning+Representation+Parsing+using+LSTM+Recurrent+Neural+Networks%2C+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computational+Li)
24. Junczys-Dowmunt, Marcin, Tomasz Dwojak, and Rico Sennrich (2016), The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT, Proceedings of the First Conference on Machine Translation, Association for Computational Linguistics, Berlin, Germany, pp. 319–325. http://www.aclweb.org/anthology/W16-2316. [↗](https://aclanthology.org/W16-2316/)
25. Klein, Guillaume, Yoon Kim, Yuntian Deng, Jean Senellart, and Alexander M Rush (2017), Open-NMT: Open-Source Toolkit for Neural Machine Translation, arXiv preprint arXiv:1701.02810. [↗](https://arxiv.org/abs/1701.02810)
26. Konstas, Ioannis, Srinivasan Iyer, Mark Yatskar, Yejin Choi, and Luke Zettlemoyer (2017), Neural AMR: Sequence-to-Sequence Models for Parsing and Generation, arXiv preprint (accepted in ACL-2017) arXiv:1704.08381. [↗](https://arxiv.org/abs/1704.08381) [our card](https://md.research.elamur.ai/free/papers/konstas-2017-neural-amr-sequence-sequence-models/)
27. Le, Phong and Willem Zuidema (2012), Learning Compositional Semantics for Open Domain Semantic Parsing, Proceedings of COLING 2012, Vol. 1 of COLING 2012, Association for Computational Linguistics, p. 3350. [find](https://scholar.google.com/scholar?q=Le%2C+Phong+and+Willem+Zuidema+%282012%29%2C+Learning+Compositional+Semantics+for+Open+Domain+Semantic+Parsing%2C+Proceedings+of+COLING+2012%2C+Vol%2E+1+of+COLING+2012%2C+Association+for+Computational+Linguistics%2C+p%2E)
28. Lewis, Mike and Mark Steedman (2013), Combined distributional and logical semantics, Transactions of the Association of Computational Linguistics – Volume 1 pp. 179–192. [find](https://scholar.google.com/scholar?q=Lewis%2C+Mike+and+Mark+Steedman+%282013%29%2C+Combined+distributional+and+logical+semantics%2C+Transactions+of+the+Association+of+Computational+Linguistics+%E2%80%93+Volume+1+pp%2E+179%E2%80%93192%2E)
29. Luong, Thang, Hieu Pham, and Christopher D. Manning (2015), Effective Approaches to Attention-based Neural Machine Translation, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Lisbon, Portugal, pp. 1412–1421. [find](https://scholar.google.com/scholar?q=Luong%2C+Thang%2C+Hieu+Pham%2C+and+Christopher+D%2E+Manning+%282015%29%2C+Effective+Approaches+to+Attention%2Dbased+Neural+Machine+Translation%2C+Proceedings+of+the+2015+Conference+on+Empirical+Methods+in+Natural+Langu)
30. May, Jonathan (2016), SemEval-2016 Task 8: Meaning Representation Parsing, Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), San Diego, California, pp. 1063–1073. [find](https://scholar.google.com/scholar?q=May%2C+Jonathan+%282016%29%2C+SemEval%2D2016+Task+8%3A+Meaning+Representation+Parsing%2C+Proceedings+of+the+10th+International+Workshop+on+Semantic+Evaluation+%28SemEval%2D2016%29%2C+San+Diego%2C+California%2C+pp%2E+1063%E2%80%931073%2E)
31. Peng, Xiaochang, Chuan Wang, Daniel Gildea, and Nianwen Xue (2017), Addressing the Data Sparsity Issue in Neural AMR Parsing, Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, Association for Computational Linguistics, Valencia, Spain, pp. 366–375. [find](https://scholar.google.com/scholar?q=Peng%2C+Xiaochang%2C+Chuan+Wang%2C+Daniel+Gildea%2C+and+Nianwen+Xue+%282017%29%2C+Addressing+the+Data+Sparsity+Issue+in+Neural+AMR+Parsing%2C+Proceedings+of+the+15th+Conference+of+the+European+Chapter+of+the+Associat)
32. Plank, Barbara, Anders Søgaard, and Yoav Goldberg (2016), Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss, Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Association for Computational Linguistics, Berlin, Germany, pp. 412–418. http://anthology.aclweb.org/P16-2067. [↗](https://aclanthology.org/P16-2067/) [our card](https://md.research.elamur.ai/free/papers/plank-2016-multilingual-part-speech-tagging-bidirectional/)
33. Pust, Michael, Ulf Hermjakob, Kevin Knight, Daniel Marcu, and Jonathan May (2015), Parsing English into abstract meaning representation using syntax-based machine translation, Training 10, pp. 218–021. [find](https://scholar.google.com/scholar?q=Pust%2C+Michael%2C+Ulf+Hermjakob%2C+Kevin+Knight%2C+Daniel+Marcu%2C+and+Jonathan+May+%282015%29%2C+Parsing+English+into+abstract+meaning+representation+using+syntax%2Dbased+machine+translation%2C+Training+10%2C+pp%2E+218%E2%80%93021) [our card](https://md.research.elamur.ai/free/papers/pust-2015-parsing-english-into-abstract-meaning/)
34. Santos, Cicero D and Bianca Zadrozny (2014), Learning character-level representations for part-of-speech tagging, Proceedings of the 31st International Conference on Machine Learning (ICML-14), pp. 1818–1826. [find](https://scholar.google.com/scholar?q=Santos%2C+Cicero+D+and+Bianca+Zadrozny+%282014%29%2C+Learning+character%2Dlevel+representations+for+part%2Dof%2Dspeech+tagging%2C+Proceedings+of+the+31st+International+Conference+on+Machine+Learning+%28ICML%2D14%29%2C+pp%2E+18)
35. Sutskever, Ilya, James Martens, and Geoffrey E Hinton (2011), Generating text with recurrent neural networks, Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 1017–1024. [find](https://scholar.google.com/scholar?q=Sutskever%2C+Ilya%2C+James+Martens%2C+and+Geoffrey+E+Hinton+%282011%29%2C+Generating+text+with+recurrent+neural+networks%2C+Proceedings+of+the+28th+International+Conference+on+Machine+Learning+%28ICML%2D11%29%2C+pp%2E+1017%E2%80%931)
36. Sutskever, Ilya, Oriol Vinyals, and Quoc V Le (2014), Sequence to sequence learning with neural networks, Advances in neural information processing systems, pp. 3104–3112. [find](https://scholar.google.com/scholar?q=Sutskever%2C+Ilya%2C+Oriol+Vinyals%2C+and+Quoc+V+Le+%282014%29%2C+Sequence+to+sequence+learning+with+neural+networks%2C+Advances+in+neural+information+processing+systems%2C+pp%2E+3104%E2%80%933112%2E)
37. van Noord, Rik and Johan Bos (2017), The Meaning Factory at SemEval-2017 Task 9: Producing AMRs with Neural Semantic Parsing, Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), Association for Computational Linguistics, Vancouver, Canada, pp. 929–933. [find](https://scholar.google.com/scholar?q=van+Noord%2C+Rik+and+Johan+Bos+%282017%29%2C+The+Meaning+Factory+at+SemEval%2D2017+Task+9%3A+Producing+AMRs+with+Neural+Semantic+Parsing%2C+Proceedings+of+the+11th+International+Workshop+on+Semantic+Evaluation+%28Sem)
38. Wang, Chuan, Nianwen Xue, and Sameer Pradhan (2015), A Transition-based Algorithm for AMR Parsing, Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, Denver, Colorado, pp. 366–375. [find](https://scholar.google.com/scholar?q=Wang%2C+Chuan%2C+Nianwen+Xue%2C+and+Sameer+Pradhan+%282015%29%2C+A+Transition%2Dbased+Algorithm+for+AMR+Parsing%2C+Proceedings+of+the+2015+Conference+of+the+North+American+Chapter+of+the+Association+for+Computational)
39. Zhang, Xiang, Junbo Zhao, and Yann LeCun (2015), Character-level convolutional networks for text classification, Advances in neural information processing systems, pp. 649–657. [find](https://scholar.google.com/scholar?q=Zhang%2C+Xiang%2C+Junbo+Zhao%2C+and+Yann+LeCun+%282015%29%2C+Character%2Dlevel+convolutional+networks+for+text+classification%2C+Advances+in+neural+information+processing+systems%2C+pp%2E+649%E2%80%93657%2E) [our card](https://md.research.elamur.ai/free/papers/zhang-2015-character-level-convolutional-networks-text/)