--- title: "Unsupervised AMR-Dependency Parse Alignment — Chen 2017" description: "The paper aligns AMR concepts to the nodes of an English dependency tree, not to spans of words as earlier aligners… 1 reference, cited by 7 papers here." authors: ["Wei-Te Chen", "Martha Palmer"] year: 2017 venue: "Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers" source: "https://aclanthology.org/E17-1053/" doi: "10.18653/v1/e17-1053" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/chen-2017-unsupervised-amr-dependency-parse-alignment/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/chen-2017-unsupervised-amr-dependency-parse-alignment/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/3/) / Unsupervised AMR-Dependency Parse Alignment # Unsupervised AMR-Dependency Parse Alignment **Authors:** [Wei-Te Chen](https://md.research.elamur.ai/free/en/authors/wei-te-chen/) and [Martha Palmer](https://md.research.elamur.ai/free/en/authors/martha-palmer/) · **Year:** 2017 · **Venue:** EACL 2017 (15th Conference of the European Chapter of the ACL, Long Papers) **Link:** [aclanthology.org/E17-1053](https://aclanthology.org/E17-1053/) · **Licence:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) [**13** citations](https://openalex.org/works?filter=cites:W2741008457) OpenAlex, 2026-10-14 · [**7** citations in our library](https://md.research.elamur.ai/free/en/papers/chen-2017-unsupervised-amr-dependency-parse-alignment/cited-by/) of the 140,884 papers whose bibliographies we read · [Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers](https://md.research.elamur.ai/free/en/venues/eacl/) · published by [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · [licence](https://creativecommons.org/licenses/by/4.0/) - [Publisher's page](https://aclanthology.org/E17-1053/) - [PDF](https://aclanthology.org/E17-1053.pdf) - [DOI 10.18653/v1/e17-1053](https://doi.org/10.18653/v1/e17-1053) - [OpenAlex](https://openalex.org/W2741008457) **Authors (2)** 1. [Wei-Te Chen](https://openalex.org/A5077281650) [Semantic Scholar](https://www.semanticscholar.org/author/34566787) · h 7 · 295 citations · 8 works 2. [Martha Palmer](https://openalex.org/A5017464054) [ORCID](https://orcid.org/0000-0001-9864-6974) · [Semantic Scholar](https://www.semanticscholar.org/author/145755155) · h 57 · 20,837 citations · 417 works Citations and author metrics: OpenAlex, 2026-10-14; authors with the same name are not always told apart. ## What it is about The paper aligns AMR concepts to the nodes of an English dependency tree, not to spans of words as earlier aligners did. The dependency parse comes from ClearNLP and carries named-entity tags and semantic roles. The aligner scores candidate pairs with lexical, named-entity, role and global features, and trains the feature weights with EM. A beam-search decoder then finds the most likely alignment. On the gold alignments the full feature set reaches an F-score of about 87.1. The intro cites 83.1 for the ISI string aligner of Pourdamghani et al. (2014). When its alignments are given to the CAMR parser, parsing Smatch rises. In the error analysis, about 40% of the errors are meaning-coverage errors: the concept is aligned to the head word of its phrase rather than to its own word. Duplicate words account for 17% and long-distance dependencies for 14%. Parse errors are 4%. ## Ideas - I1. Align meta tokens to tree nodes rather than to word spans, and count how often a concept lands on its governor instead of its own word. The paper's largest error class is exactly this. The count is a direct measure for open problem 1 (reader attachment noise). - I3. The EM step, run for a fixed number of iterations (the paper uses 50), can be replaced by a count table over (concept, head relation, tag) triples with the same iteration rule. Keep the table in BTreeMap order and check that two runs give identical output before any gain is claimed. - I4. The paper ablates feature groups in turn (lexical, then plus named entities, then plus roles, then plus global features). Run the same ablation on the reader: remove one group at a time and report the reader's bits per class. This is the value-ablation rule applied to the reader. ## For Mova - I2. Duplicate words cause 17% of the errors, because the lexicon key is the word alone. Adding the tree relation or the role to the key would separate the two occurrences of an ordinal such as *first*. Test this as a change to the key in `meta.rs` and measure the residual. The ideas apply to `tools/translate/meta.rs` (the lexicon and the head of each meta token), `tools/translate/hebrew.rs` (the Hebrew words are aligned to meta tokens with IBM Model 1; the tree-feature view is the English counterpart of its prior), and `tools/roundtrip` (the tree and frame stack the reader reads). The paper's aligner is trained with features from a neural tagger and parser. Mova can use the same features from its own parser as counts, and the decoder is a plain argmax over a table. ## Institutions [🎓**University of Colorado Boulder** Boulder · United States 41 works · 48,832 citations](https://md.research.elamur.ai/free/en/universities/university-of-colorado-boulder/) 📚 Shelves 4[Computer Science · 7,349 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 7,183 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 7,418 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 7,357 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 🧭 Topics 2[Machine translation · 877 works](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Semantic parsing & meaning representation · 120 works](https://md.research.elamur.ai/free/en/topics/semantic-parsing/) ## Cite Cite as Wei-Te Chen and Martha Palmer. 2017. Unsupervised AMR-Dependency Parse Alignment. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.18653/v1/e17-1053](https://doi.org/10.18653/v1/e17-1053) ```bibtex @inproceedings{chen2017unsupervised, title = {{Unsupervised AMR-Dependency Parse Alignment}}, author = {Wei-Te Chen and Martha Palmer}, booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers}, year = {2017}, doi = {10.18653/v1/e17-1053}, url = {https://doi.org/10.18653/v1/e17-1053} } ``` - [← previous Multi-source annotation projection of coreference chains: assessing strategies and testing opportunities](https://md.research.elamur.ai/free/en/papers/grishina-2017-multi-source-annotation-projection-coreference/) - [next → RIGOTRIO at SemEval-2017 Task 9: Combining Machine Learning and Grammar Engineering for AMR Parsing and Generation](https://md.research.elamur.ai/free/en/papers/gruzitis-2017-rigotrio-semeval-2017-task-9/) - [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/3/) ## References 1 references, 1 of them with a card of ours. ↗ leads to the work. 1. Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. Abstract meaning representation for sembanking. [our card](https://md.research.elamur.ai/free/en/papers/banarescu-2013-abstract-meaning-representation-sembanking/) Updated 23 October 2026