German and English Treebanks and Lexica for Tree-Adjoining Grammars

What it is about

The paper builds a treebank and a lexicon for PLTAG, an incremental, psycholinguistically motivated version of tree-adjoining grammar. The English side is converted from the Penn Treebank, the German side from TIGER. Conversion adds structure the original annotation lacks, so that modifiers can adjoin; German uses sister-adjunction because its free word order produces flat trees. Elementary trees are extracted from the converted trees, and prediction trees are derived from connection paths, so that a parser can predict upcoming structure word by word. The conversion yields complete correct trees for 97.6% of PTB trees and 99.8% of TIGER trees. The English lexicon has about 6,000 tree templates, with 2.37 trees per word on average; the German lexicon is larger because German predicts more.

Ideas

• I1. en/src/lin.rs and 19. The lexicon: vocabulary, multiword expressions and register: a table of multi-word entries with gaps, such as either ... or and particle verbs like show up, each stored with its positions. Measure how many gold multi-word units in UD EWT dev are recovered by the table.
• I2. Report ambiguity per lemma the way the paper does (trees per word, and the most ambiguous words such as and). Keep a count table in en/src/dict.rs order, and use it to choose which function words need a rule.
• I3. Prefix-level measure for en/src/parse.rs: after each word, count the attachments still open, and report the parser's accuracy on the prefix. This tests the paper's point that a predictive grammar needs fewer open decisions.

For Mova

The chapters are 19. The lexicon: vocabulary, multiword expressions and register (multi-word units), 13. Verbs (particle verbs) and 20. Syntax: the Universal Dependencies frame (the parse). The code is en/src/dict.rs, en/src/parse.rs and en/src/lin.rs. The measures: recall of multi-word units on UD EWT dev, and per-lemma ambiguity counts. Only the ideas and the measures are for Mova; the treebanks themselves are not carried into the build.

Topics: Treebanks

Cite

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

@inproceedings{kaeshammer2012german,
  title = {{German and English Treebanks and Lexica for Tree-Adjoining Grammars}},
  author = {Kaeshammer, Miriam and Demberg, Vera},
  booktitle = {Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)},
  year = {2012},
  url = {https://aclanthology.org/L12-1204/}
}

References

30 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Tilman Becker, Aravind K. Joshi, and Owen Rambow. 1991. Long-Distance Scrambling and Tree Adjoining Grammars. In Proceedings of the fifth Conference of the EACL. find
2. Sabine Brants, Stefanie Dipper, Silvia Hansen, Wolfgang Lezius, and George Smith. 2002. The TIGER treebank. In Proceedings of the Workshop on Treebanks and Linguistic Theories. find
3. Aoife Cahill. 2004. Parsing with Automatically Acquired, Wide-Coverage, Robust, Probabilistic LFG Approximations. Ph.D. thesis, Dublin City University. find
4. Eugene Charniak. 1996. Tree-bank Grammars. In Proceedings of the AAAI-96. find
5. John Chen and Vijay K. Shanker. 2004. Automated extraction of TAGs from the Penn Treebank. New developments in parsing technology. find
6. David Chiang. 2000. Statistical Parsing with an Automatically-Extracted Tree Adjoining Grammar. In Proceedings ACL, volume 38. find
7. Vera Demberg and Frank Keller. 2008. A Psycholinguistically Motivated Version of TAG. In Proceedings of TAG+9. find
8. Vera Demberg-Winterfors. 2010. A Broad-Coverage Model of Prediction in Human Sentence Processing. Ph.D. thesis, University of Edinburgh. find
9. Amit Dubey. 2005. Statistical Parsing for German: Modeling syntactic properties and annotation differences. Ph.D. thesis, Universität des Saarlandes. find
10. Anette Frank. 2001. Treebank Conversion. Converting the NEGRA treebank to an LTAG grammar. In Proceedings of the Workshop on Multi-layer Corpus-based Analysis. find
11. Aravind K. Joshi, Leon S. Levy, and Masako Takahashi. 1975. Tree adjunct grammars. Journal of computer and system sciences, 10(1):136–163. find
12. Miriam Kaeshammer. 2012. A German Treebank and Lexicon for Tree-Adjoining Grammars. Master’s thesis, Saarland University. find
13. Yuki Kamide, Christoph Scheepers, and Gerry T. M. Altmann. 2003. Integration of syntactic and semantic information in predictive processing: Cross-linguistic evidence from German and English. Journal of Psycholinguistic Research, 32. find
14. Lars Konieczny. 2000. Locality and parsing complexity. Journal of Psycholinguistic Research, 29(6). find
15. Vincenzo Lombardo and Patrick Sturt. 2002. Incrementality and Lexicalism. In Lexical Representations in Sentence Processing. find
16. David M. Magerman. 1994. Natural Language Parsing as Statistical Pattern Recognition. Ph.D. thesis, Stanford University. find
17. Wolfgang Maier. 2010. Direct Parsing of Discontinuous Constituents in German. In Proceedings of the NAACL HLT 2010 First Workshop on Statistical Parsing of Morphologically-Rich Languages. find
18. Mitchell P. Marcus, Mary A. Marcinkiewicz, and Beatrice Santorini. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational linguistics, 19(2). find our card
19. Günter Neumann. 2003. A Uniform Method for Automatically Extracting Stochastic Lexicalized Tree Grammars from Treebanks and HPSG. Treebanks: Building and Using Parsed Corpora. find
20. Martha Palmer, Dan Gildea, and Paul Kingsbury. 2005. The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1). find our card
21. Wojciech Skut, Brigitte Krenn, Thorsten Brants, and Hans Uszkoreit. 1997. An Annotation Scheme for Free Word Order Languages. In Proceedings of the Fifth Conference on Applied Natural Language Processing. find
22. Adrian Staub and Charles Clifton. 2006. Syntactic prediction in language comprehension: Evidence from either . . . or. Journal of Experimental Psychology: Learning, Memory, and Cognition, 32. find
23. Patrick Sturt and Vincenzo Lombardo. 2005. Processing coordinate structures: Incrementality and connectedness. Cognitive Science, 29. find
24. Patrizia Tabossi, Rachele Fanari, and Kinou Wolf. 2005. Spoken idiom recognition: Meaning retrieval and word expectancy. Journal of Psycholinguistic Research, 34. find
25. Michael K. Tanenhaus, Michael J. Spivey-Knowlton, Kathleen M. Eberhard, and Julie C. Sedivy. 1995. Integration of visual and linguistic information in spoken language comprehension. Science, 268. find
26. David Vadas and James R. Curran. 2007. Adding Noun Phrase Structure to the Penn Treebank. In Proceedings ACL, volume 45. find our card
27. Jos J. A. van Berkum, Colin M. Brown, and Peter Hagoort. 1999. Early referential context effects in sentence processing: Evidence from event-related brain potentials. Journal of Memory and Language, 41. find
28. Fei Xia, Martha Palmer, and Aravind Joshi. 2000. A Uniform Method of Grammar Extraction and its Applications. In Proceedings of the 2000 Joint SIGDAT conference on EMNLP/VLC. find
29. Fei Xia. 2001. Automatic Grammar Generation From Two Different Perspectives. Ph.D. thesis, University of Pennsylvania. find
30. XTAG Research Group. 2001. A lexicalized tree adjoining grammar for english. Technical Report IRCS-01-03, IRCS, University of Pennsylvania. find our card

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/kaeshammer-2012-german-english-treebanks-lexica-tree/