Aligning English Strings with Abstract Meaning Representation Graphs

What it is about

The paper aligns the tokens of an English sentence to the concepts and relations of its AMR graph, as a step toward learning semantic interpretation and generation rules. Each AMR is linearized by a depth-first walk that keeps the graph structure for rebuilding it later. Before training, function-like tokens (articles, the copula, role labels, instance markers) are removed, and their positions are remembered. Sense suffixes are stripped. The alignment model is IBM-style: it is trained symmetrically in both directions, with an EM step that pushes the two directional tables to agree. Among the variants compared, the symmetric Model 4 is best, with an F-score of 86.5 on the development set and 83.1 on the test set. Role labels are the hard part. Their F-score is about 60 on development and about 49 on test, against about 92 and 90 for concepts. Removing stop words costs about a third of the recall errors.

Ideas

I1. Use the symmetric training as a count step: estimate each direction's table and keep only the pairs that agree in both directions. This needs no neural part and fits tools/translate/ibm.rs. The paper also reports that the simple Model 1 is the weakest variant, and the Hebrew aligner in hebrew.rs uses that same Model 1.
I2. Do not drop function words from the alignment. The paper's stop-word removal costs about a third of the recall. For the translator the function words should stay as features of the meta token (definiteness, clause boundary, speech), which is open problem 4.
I3. Report role-label and concept alignment F-scores separately in every reader run, as the paper's table does, so that a change to relations cannot hide behind a good concept score.
I4. The depth-first linearization is deterministic and can be reversed. Use it as a round-trip test for the meta-world: linearize, rebuild, and compare with the original graph; a mismatch counts as a reader bug.

For Mova

The ideas apply to tools/translate/ibm.rs and hebrew.rs (the IBM aligner that reads Hebrew onto meta tokens), tools/translate/measure.rs (the per-class report), and tools/roundtrip (the tree and frame graph whose order the linearizer must reproduce). The paper's hand-aligned gold set is small. Mova should treat it as a check on a method, not as training data; its licence allows only summaries.

Topics: Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.3115/v1/d14-1048

@inproceedings{pourdamghani2014aligning,
  title = {{Aligning English Strings with Abstract Meaning Representation Graphs}},
  author = {Pourdamghani, Nima and Gao, Yang and Hermjakob, Ulf and Knight, Kevin},
  booktitle = {Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2014},
  doi = {10.3115/v1/d14-1048},
  url = {https://doi.org/10.3115/v1/d14-1048}
}

References

7 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

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. In Linguistic Annotation Workshop (LAW VII-ID), ACL. find our card
Peter F. Brown, Vincent J. Della Pietra, Stephen A. Della Pietra, and Robert L. Mercer. 1993. The mathematics of statistical machine translation: Parameter estimation. Computational linguistics, 19(2):263–311. find
Jeffrey Flanigan, Sam Thomson, Jaime Carbonell, Chris Dyer, and Noah A. Smith. 2014. A discriminative graph-based parser for the abstract meaning representation. In ACL. find
Michel Galley, Mark Hopkins, Kevin Knight, and Daniel Marcu. 2004. What’s in a translation rule? In HLT-NAACL. find our card
Qin Gao and Stephan Vogel. 2008. Parallel implementations of word alignment tool. In Software Engineering, Testing, and Quality Assurance for Natural Language Processing Workshop, ACL. find
Bevan Jones, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, and Kevin Knight. 2012. Semantics-based machine translation with hyperedge replacement grammars. In COLING. find our card
Percy Liang, Ben Taskar, and Dan Klein. 2006. Alignment by agreement. In HLT-NAACL. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/pourdamghani-2014-aligning-english-strings-abstract-meaning/