---
title: "Revisiting Supertagging for Faster HPSG Pasing (2023)"
description: "HPSG parsers built on large hand-written precision grammars give very detailed analyses… 97.26% accuracy on 950 WSJ23. 58 references."
authors: ["Olga Zamaraeva", "Carlos Gomez-Rodriguez"]
year: 2023
venue: "arXiv:2309.07590"
source: "https://arxiv.org/abs/2309.07590"
doi: "10.48550/arxiv.2309.07590"
arxiv: "2309.07590"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zamaraeva-2023-revisiting-supertagging-faster-hpsg-pasing/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zamaraeva-2023-revisiting-supertagging-faster-hpsg-pasing/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/17/) / Revisiting Supertagging for Faster HPSG Pasing

# Revisiting Supertagging for Faster HPSG Pasing

**Authors:** [Olga Zamaraeva](https://md.research.elamur.ai/free/en/authors/olga-zamaraeva/) and [Carlos Gomez-Rodriguez](https://md.research.elamur.ai/free/en/authors/carlos-gomez-rodriguez/) · **Year:** 2023 · **Venue:** arXiv:2309.07590 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2309.07590) · [PDF](https://arxiv.org/pdf/2309.07590) · [DOI 10.48550/arxiv.2309.07590](https://doi.org/10.48550/arxiv.2309.07590) · [arXiv 2309.07590](https://arxiv.org/abs/2309.07590) · [OpenAlex](https://openalex.org/W4386794771)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
HPSG parsers built on large hand-written precision grammars give very detailed analyses, but they are slow and memory-hungry. A single sentence often takes more than a second, and long sentences can exhaust RAM. The authors return to supertagging, which means predicting a fine-grained lexical type for each token and then pruning the parse chart before unification begins. They train SVM, neural CRF (NCRF++) and fine-tuned BERT taggers on the 2023 English Resource Grammar (ERG) treebanks and compare them with an older MaxEnt baseline. The best BERT tagger is then plugged into the lexical-analysis stage of a DELPH-IN parser. It keeps only the top tag per token, except for a list of word classes that are never pruned.

Compared with parsing without tags, the system is about three times faster and also more accurate on the dependency-based EDM metric. A production-integrated ubertagger remains faster, but it is usually less accurate. The results differ noticeably across domains. The work matters because it makes high-precision, grammar-derived treebanks cheaper to produce, and it releases the ERG data in Huggingface token-classification format.

## Key points
- The training and evaluation data come from the ERG 2023 release: 30 treebanked corpora with over 1.5M tokens and 105,155 sentences. The genres include news, Wikipedia, fiction, emails, phone transcripts, technical essays and phenomenon test suites.
- The ERG defines 43,505 lexical types, of which only 1,299 occur in the training portion. The Penn Treebank tagset, by comparison, has 48 tags.
- The fine-tuned BERT tagger reaches 97.26% accuracy on 950 WSJ23 sentences. On the out-of-domain essay The Cathedral and the Bazaar (cb) it reaches 93.88%.
- With the tagger integrated, parsing is roughly 3× faster than with no tagging, and recall and precision improve on most datasets. The ubertagger is about 12× faster on average but loses accuracy.
- On e-commerce data, tagging helps least. The supertagger gains 6% in speed at a cost of 3% F-score, while the ubertagger loses 16% F-score.

## Interesting ideas
- The tagger keeps a single best label to maximise pruning but exempts a hand-picked set of 15 word classes, so the risky cases keep their full ambiguity.
- The tags are rich grammar lexical types that encode syntactic behaviour such as subcategorisation, rather than coarse POS, so the tagger does part of the parser's work in advance.
- The treebank is regenerated by the grammar itself, so a fix in the grammar spreads systematically through all the data without any manual re-annotation.
- The tagger is judged by downstream parse quality (EDM precision and recall) and speed, not only by tag accuracy, because one wrong tag can sink an entire sentence.
- The evaluation covers many genres plus constructed phenomenon suites, and it shows that results vary even across in-domain sets.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (tree): the perceptron parser and gparse could prune candidate heads and labels using tagger confidence, while leaving known trouble classes (e.g. particles, wh-words) unpruned to avoid sentence-level failures.
- **I2** (tokens): crate en could predict verb-frame-like lexical subtypes alongside UPOS, which would narrow the parser's options and later feed VerbNet role assignment.
- **I3** (learn): self-induced repair rules could be applied as a re-derivation pass over silver data, so that one correction updates the whole corpus consistently.
- **I4** (learn): tagger and parser changes could be scored by their effect on final frames or answers, with per-domain breakdowns.
- **I5** (answer): the test sets for fables, maths problems and school tests could be reported separately, together with small targeted phenomenon suites (e.g. control, raising), instead of a single averaged score.

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

## Institutions

- [Universidade da Coruña](https://md.research.elamur.ai/free/en/universities/universidade-da-coruna/) — University, A Coruña, Spain · 14 works · 328 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [📐 Syntax & grammar formalisms](https://md.research.elamur.ai/free/en/topics/syntax-grammar/) · 221 works

## Cite

Cite as: Olga Zamaraeva and Carlos Gomez-Rodriguez. 2023. Revisiting Supertagging for Faster HPSG Pasing. arXiv:2309.07590.

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

```bibtex
@misc{zamaraeva2023revisiting,
  title = {{Revisiting Supertagging for Faster HPSG Pasing}},
  author = {Olga Zamaraeva and Carlos Gomez-Rodriguez},
  year = {2023},
  doi = {10.48550/arxiv.2309.07590},
  eprint = {2309.07590},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2309.07590}
}
```

- [← previous Review of the First International Ancient Chinese Word Segmentation and POS Tagging Bakeoff](https://md.research.elamur.ai/free/en/papers/li-2023-first-international-ancient/)
- [next → Role of Context in Unsupervised Sentence Representation Learning: the Case of Dialog Act Modeling](https://md.research.elamur.ai/free/en/papers/hronsky-2023-role-context-unsupervised-sentence-representation/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/17/)

## References

58 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Lasse F. Wolff Anthony, Benjamin Kanding, and Raghavendra Selvan. 2020. Carbontracker: Tracking and predicting the carbon footprint of training deep learning models. ICML Workshop on Challenges in Deploying and monitoring Machine Learning Systems. ArXiv:2007.03051. [↗](https://arxiv.org/abs/2007.03051)
2. Srinivas Bangalore and Aravind Joshi. 1999. [Supertagging: An approach to almost parsing](https://md.research.elamur.ai/free/en/papers/bangalore-1999-supertagging-approach-almost-parsing/). Computational linguistics, 25(2):237–265.
3. Emily M Bender and Guy Emerson. 2021. Computational linguistics and grammar engineering. In Stefan Müller, Anne Abeillé, Robert D. Borsley, and Jean-Pierre Koenig, editors, [Head-Driven Phrase Structure Grammar: The handbook](https://md.research.elamur.ai/free/en/papers/muller-2021-hpsg-handbook/).
4. Philip Blunsom. 2007. Structured classification for multilingual natural language processing. Ph.D. thesis, University of Melbourne. [find](https://scholar.google.com/scholar?q=Philip+Blunsom%2E+2007%2E+Structured+classification+for+multilingual+natural+language+processing%2E+Ph%2ED%2E+thesis%2C+University+of+Melbourne%2E)
5. Thorsten Brants. 2000. [TnT-a statistical part-of-speech tagger](https://md.research.elamur.ai/free/en/papers/brants-2000-tnt-statistical-part-speech-tagger/). arXiv preprint cs/0003055.
6. Jan Buys and Phil Blunsom. 2017. Robust incremental neural semantic graph parsing. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1215–1226. [find](https://scholar.google.com/scholar?q=Jan+Buys+and+Phil+Blunsom%2E+2017%2E+Robust+incremental+neural+semantic+graph+parsing%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C+p)
7. Ulrich Callmeier. 2000. PET–a platform for experimentation with efficient hpsg processing techniques. Natural Language Engineering, 6(1):99–107. [find](https://scholar.google.com/scholar?q=Ulrich+Callmeier%2E+2000%2E+PET%E2%80%93a+platform+for+experimentation+with+efficient+hpsg+processing+techniques%2E+Natural+Language+Engineering%2C+6%281%29%3A99%E2%80%93107%2E)
8. Robert Carpenter. 1992. The logic of typed feature structures: with applications to unification grammars, logic programs and constraint resolution, volume 32. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Robert+Carpenter%2E+1992%2E+The+logic+of+typed+feature+structures%3A+with+applications+to+unification+grammars%2C+logic+programs+and+constraint+resolution%2C+volume+32%2E+Cambridge+University+Press%2E)
9. John Carroll. 1993. Practical unification-based parsing of natural language. Ph.D. thesis, University of Cambridge. [find](https://scholar.google.com/scholar?q=John+Carroll%2E+1993%2E+Practical+unification%2Dbased+parsing+of+natural+language%2E+Ph%2ED%2E+thesis%2C+University+of+Cambridge%2E)
10. Yufei Chen, Weiwei Sun, and Xiaojun Wan. 2018. Accurate SHRG-based semantic parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 408–418, Melbourne, Australia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yufei+Chen%2C+Weiwei+Sun%2C+and+Xiaojun+Wan%2E+2018%2E+Accurate+SHRG%2Dbased+semantic+parsing%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+1%3A+Long+Papers%29%2C)
11. Stephen Clark and James R Curran. 2003. Log-linear models for wide-coverage CCG parsing. In Proceedings of the 2003 conference on Empirical methods in natural language processing, pages 97–104. [find](https://scholar.google.com/scholar?q=Stephen+Clark+and+James+R+Curran%2E+2003%2E+Log%2Dlinear+models+for+wide%2Dcoverage+CCG+parsing%2E+In+Proceedings+of+the+2003+conference+on+Empirical+methods+in+natural+language+processing%2C+pages+97%E2%80%93104%2E)
12. Ann Copestake. 2002. Definitions of typed feature structures. In Stephan Oepen, Dan Flickinger, Jun-ichi Tsujii, and Hans Uszkoreit, editors, Collaborative Language Engineering, pages 227–230. CSLI Publications, Stanford, CA. [find](https://scholar.google.com/scholar?q=Ann+Copestake%2E+2002%2E+Definitions+of+typed+feature+structures%2E+In+Stephan+Oepen%2C+Dan+Flickinger%2C+Jun%2Dichi+Tsujii%2C+and+Hans+Uszkoreit%2C+editors%2C+Collaborative+Language+Engineering%2C+pages+227%E2%80%93230%2E+CSLI+Pu)
13. Berthold Crysmann and Woodley Packard. 2012. Towards efficient HPSG generation for German, a non-configurational language. In COLING, pages 695– 710. [find](https://scholar.google.com/scholar?q=Berthold+Crysmann+and+Woodley+Packard%2E+2012%2E+Towards+efficient+HPSG+generation+for+German%2C+a+non%2Dconfigurational+language%2E+In+COLING%2C+pages+695%E2%80%93+710%2E)
14. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of NAACL-HLT, pages 4171–4186.
15. Rebecca Dridan. 2009. Using lexical statistics to improve HPSG parsing. Ph.D. thesis, University of Saarland. [find](https://scholar.google.com/scholar?q=Rebecca+Dridan%2E+2009%2E+Using+lexical+statistics+to+improve+HPSG+parsing%2E+Ph%2ED%2E+thesis%2C+University+of+Saarland%2E)
16. Dirk Hovy and Anders Søgaard. 2015. [Tagging performance correlates with author age](https://md.research.elamur.ai/free/en/papers/hovy-2015-tagging-performance-correlates-author-age/). In Proceedings of the 53rd annual meeting of the Association for Computational Linguistics and the 7th international joint conference on natural language processing (volume 2: Short papers), pages 483–488.
17. Konstantinos Kogkalidis and Michael Moortgat. 2023. Geometry-aware supertagging with heterogeneous dynamic convolutions. In Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD), pages 107–119. [find](https://scholar.google.com/scholar?q=Konstantinos+Kogkalidis+and+Michael+Moortgat%2E+2023%2E+Geometry%2Daware+supertagging+with+heterogeneous+dynamic+convolutions%2E+In+Proceedings+of+the+2023+CLASP+Conference+on+Learning+with+Small+Data+%28LSD%29%2C+)
18. Zi Lin, Jeremiah Zhe Liu, and Jingbo Shang. 2022. Towards collaborative neural-symbolic graph semantic parsing via uncertainty. Findings of the Association for Computational Linguistics: ACL 2022. [find](https://scholar.google.com/scholar?q=Zi+Lin%2C+Jeremiah+Zhe+Liu%2C+and+Jingbo+Shang%2E+2022%2E+Towards+collaborative+neural%2Dsymbolic+graph+semantic+parsing+via+uncertainty%2E+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2022%2E)
19. Yufang Liu, Tao Ji, Yuanbin Wu, and Man Lan. 2021. Generating CCG categories. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 13443–13451. [find](https://scholar.google.com/scholar?q=Yufang+Liu%2C+Tao+Ji%2C+Yuanbin+Wu%2C+and+Man+Lan%2E+2021%2E+Generating+CCG+categories%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+35%2C+pages+13443%E2%80%9313451%2E)
20. Rebecca Dridan. 2013. [Ubertagging: Joint segmentation and supertagging for english](https://md.research.elamur.ai/free/en/papers/dridan-2013-ubertagging-joint-segmentation-supertagging-english/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1201–1212.
21. Robert Malouf, John Carroll, and Ann Copestake. 2000. Efficient feature structure operations without compilation. Natural Language Engineering, 6(1):29–46. [find](https://scholar.google.com/scholar?q=Robert+Malouf%2C+John+Carroll%2C+and+Ann+Copestake%2E+2000%2E+Efficient+feature+structure+operations+without+compilation%2E+Natural+Language+Engineering%2C+6%281%29%3A29%E2%80%9346%2E)
22. Rebecca Dridan, Valia Kordoni, and Jeremy Nicholson. 2008. Enhancing performance of lexicalised grammars. In Proceedings of ACL-08: HLT, pages 613–621. [find](https://scholar.google.com/scholar?q=Rebecca+Dridan%2C+Valia+Kordoni%2C+and+Jeremy+Nicholson%2E+2008%2E+Enhancing+performance+of+lexicalised+grammars%2E+In+Proceedings+of+ACL%2D08%3A+HLT%2C+pages+613%E2%80%93621%2E)
23. Mitchell Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. [Building a large annotated corpus of English: The Penn Treebank](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/). University of Pennsylvania Department of Computer and Information Science Technical Report No. MS-CIS-93-87.
24. Rebecca Dridan and Stephan Oepen. 2011. Parser evaluation using elementary dependency matching. In Proceedings of the 12th International Conference on Parsing Technologies, pages 225–230, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Rebecca+Dridan+and+Stephan+Oepen%2E+2011%2E+Parser+evaluation+using+elementary+dependency+matching%2E+In+Proceedings+of+the+12th+International+Conference+on+Parsing+Technologies%2C+pages+225%E2%80%93230%2C+Dublin%2C+Irel)
25. Montserrat Marimon, Núria Bel, and Lluı́s Padró. 2014. Automatic selection of hpsg-parsed sentences for treebank construction. Computational Linguistics, 40(3):523–531. [find](https://scholar.google.com/scholar?q=Montserrat+Marimon%2C+Nu%CC%81ria+Bel%2C+and+Llu%C4%B1%CC%81s+Padro%CC%81%2E+2014%2E+Automatic+selection+of+hpsg%2Dparsed+sentences+for+treebank+construction%2E+Computational+Linguistics%2C+40%283%29%3A523%E2%80%93531%2E)
26. Dan Flickinger. 2000. [On building a more efficient grammar by exploiting types](https://md.research.elamur.ai/free/en/papers/flickinger-2000-building-more-efficient-grammar/). Natural Language Engineering, 6(01):15–28.
27. Takuya Matsuzaki, Yusuke Miyao, and Jun’ichi Tsujii. 2007. Efficient hpsg parsing with supertagging and cfg-filtering. In Proceedings of the 20th international joint conference on Artifical intelligence, pages 1671– 1676. [find](https://scholar.google.com/scholar?q=Takuya+Matsuzaki%2C+Yusuke+Miyao%2C+and+Jun%E2%80%99ichi+Tsujii%2E+2007%2E+Efficient+hpsg+parsing+with+supertagging+and+cfg%2Dfiltering%2E+In+Proceedings+of+the+20th+international+joint+conference+on+Artifical+intelligen)
28. Dan Flickinger. 2011. Accuracy v. robustness in grammar engineering. In Emily M. Bender and Jennifer E. Arnold, editors, Language from a Cognitive Perspective: Grammar, Usage and Processing, pages 31–50. CSLI Publications, Stanford, CA. [find](https://scholar.google.com/scholar?q=Dan+Flickinger%2E+2011%2E+Accuracy+v%2E+robustness+in+grammar+engineering%2E+In+Emily+M%2E+Bender+and+Jennifer+E%2E+Arnold%2C+editors%2C+Language+from+a+Cognitive+Perspective%3A+Grammar%2C+Usage+and+Processing%2C+pages+31%E2%80%93)
29. Yusuke Miyao and Jun’ichi Tsujii. 2008. [Feature forest models for probabilistic HPSG parsing](https://md.research.elamur.ai/free/en/papers/miyao-2008-feature-forest-models-probabilistic-hpsg/). Computational linguistics, 34(1):35–80.
30. Dan Flickinger and Jiye Yu. 2013. Toward more precision in correction of grammatical errors. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning: Shared Task, pages 68– 73. [find](https://scholar.google.com/scholar?q=Dan+Flickinger+and+Jiye+Yu%2E+2013%2E+Toward+more+precision+in+correction+of+grammatical+errors%2E+In+Proceedings+of+the+Seventeenth+Conference+on+Computational+Natural+Language+Learning%3A+Shared+Task%2C+pages)
31. Dan Flickinger, Yi Zhang, and Valia Kordoni. 2012. Deepbank. a dynamically annotated treebank of the wall street journal. In Proceedings of the 11th International Workshop on Treebanks and Linguistic Theories, pages 85–96. [find](https://scholar.google.com/scholar?q=Dan+Flickinger%2C+Yi+Zhang%2C+and+Valia+Kordoni%2E+2012%2E+Deepbank%2E+a+dynamically+annotated+treebank+of+the+wall+street+journal%2E+In+Proceedings+of+the+11th+International+Workshop+on+Treebanks+and+Linguistic+)
32. Valerie Hajdik, Jan Buys, Michael W Goodman, and Emily M Bender. 2019. Neural text generation from rich semantic representations. In Proceedings of NAACL-HLT, pages 2259–2266. [find](https://scholar.google.com/scholar?q=Valerie+Hajdik%2C+Jan+Buys%2C+Michael+W+Goodman%2C+and+Emily+M+Bender%2E+2019%2E+Neural+text+generation+from+rich+semantic+representations%2E+In+Proceedings+of+NAACL%2DHLT%2C+pages+2259%E2%80%932266%2E)
33. Luis Morgado da Costa, Francis Bond, and Xiaoling He. 2016. Syntactic well-formedness diagnosis and error-based coaching in computer assisted language learning using machine translation. In Proceedings of the 3rd Workshop on Natural Language Processing Techniques for Educational Applications (NLPTEA2016), pages 107–116. [find](https://scholar.google.com/scholar?q=Luis+Morgado+da+Costa%2C+Francis+Bond%2C+and+Xiaoling+He%2E+2016%2E+Syntactic+well%2Dformedness+diagnosis+and+error%2Dbased+coaching+in+computer+assisted+language+learning+using+machine+translation%2E+In+Proceeding)
34. Luis Morgado da Costa, Roger VP Winder, Shu Yun Li, Benedict Christopher Lin Tzer Liang, Joseph Mackinnon, and Francis Bond. 2020. Automated writing support using deep linguistic parsers. In Proceedings of The 12th Language Resources and Evaluation Conference, pages 369–377. [find](https://scholar.google.com/scholar?q=Luis+Morgado+da+Costa%2C+Roger+VP+Winder%2C+Shu+Yun+Li%2C+Benedict+Christopher+Lin+Tzer+Liang%2C+Joseph+Mackinnon%2C+and+Francis+Bond%2E+2020%2E+Automated+writing+support+using+deep+linguistic+parsers%2E+In+Proceedin)
35. Takashi Ninomiya, Takuya Matsuzaki, Yusuke Miyao, and Jun’ichi Tsujii. 2007. A log-linear model with an n-gram reference distribution for accurate hpsg parsing. In Proceedings of the 10th International Conference on Parsing Technologies, pages 60–68. Citeseer. [find](https://scholar.google.com/scholar?q=Takashi+Ninomiya%2C+Takuya+Matsuzaki%2C+Yusuke+Miyao%2C+and+Jun%E2%80%99ichi+Tsujii%2E+2007%2E+A+log%2Dlinear+model+with+an+n%2Dgram+reference+distribution+for+accurate+hpsg+parsing%2E+In+Proceedings+of+the+10th+Internationa)
36. Masaru Tomita. 1985. An efficient context-free parsing algorithm for natural languages. In IJCAI, volume 2, pages 756–764. [find](https://scholar.google.com/scholar?q=Masaru+Tomita%2E+1985%2E+An+efficient+context%2Dfree+parsing+algorithm+for+natural+languages%2E+In+IJCAI%2C+volume+2%2C+pages+756%E2%80%93764%2E)
37. Stephan Oepen. 1999. [incr tsdb ()] competence and performance laboratory. User and reference manual. [find](https://scholar.google.com/scholar?q=Stephan+Oepen%2E+1999%2E+%5Bincr+tsdb+%28%29%5D+competence+and+performance+laboratory%2E+User+and+reference+manual%2E)
38. Ashish Vaswani, Yonatan Bisk, Kenji Sagae, and Ryan Musa. 2016. Supertagging with lstms. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 232– 237. [find](https://scholar.google.com/scholar?q=Ashish+Vaswani%2C+Yonatan+Bisk%2C+Kenji+Sagae%2C+and+Ryan+Musa%2E+2016%2E+Supertagging+with+lstms%2E+In+Proceedings+of+the+2016+Conference+of+the+North+American+Chapter+of+the+Association+for+Computational+Lingui)
39. Stephan Oepen and John Carroll. 2002. Efficient parsing for unification-based grammars. In Stephan Oepen, Dan Flickinger, Jun-ichi Tsujii, and Hans Uszkoreit, editors, Collaborative Language Engineering. CSLI Press. [find](https://scholar.google.com/scholar?q=Stephan+Oepen+and+John+Carroll%2E+2002%2E+Efficient+parsing+for+unification%2Dbased+grammars%2E+In+Stephan+Oepen%2C+Dan+Flickinger%2C+Jun%2Dichi+Tsujii%2C+and+Hans+Uszkoreit%2C+editors%2C+Collaborative+Language+Engineeri)
40. Stephan Oepen, Dan Flickinger, Kristina Toutanova, and Christopher D Manning. 2004. LinGO Redwoods. Research on Language and Computation, 2(4):575– 596. [find](https://scholar.google.com/scholar?q=Stephan+Oepen%2C+Dan+Flickinger%2C+Kristina+Toutanova%2C+and+Christopher+D+Manning%2E+2004%2E+LinGO+Redwoods%2E+Research+on+Language+and+Computation%2C+2%284%29%3A575%E2%80%93+596%2E)
41. Woodley Packard. 2015. Full-forest treebanking. Master’s thesis, University of Washington. [find](https://scholar.google.com/scholar?q=Woodley+Packard%2E+2015%2E+Full%2Dforest+treebanking%2E+Master%E2%80%99s+thesis%2C+University+of+Washington%2E)
42. Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in pytorch. [find](https://scholar.google.com/scholar?q=Adam+Paszke%2C+Sam+Gross%2C+Soumith+Chintala%2C+Gregory+Chanan%2C+Edward+Yang%2C+Zachary+DeVito%2C+Zeming+Lin%2C+Alban+Desmaison%2C+Luca+Antiga%2C+and+Adam+Lerer%2E+2017%2E+Automatic+differentiation+in+pytorch%2E)
43. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830. [find](https://scholar.google.com/scholar?q=F%2E+Pedregosa%2C+G%2E+Varoquaux%2C+A%2E+Gramfort%2C+V%2E+Michel%2C+B%2E+Thirion%2C+O%2E+Grisel%2C+M%2E+Blondel%2C+P%2E+Prettenhofer%2C+R%2E+Weiss%2C+V%2E+Dubourg%2C+J%2E+Vanderplas%2C+A%2E+Passos%2C+D%2E+Cournapeau%2C+M%2E+Brucher%2C+M%2E+Perrot%2C+and+E%2E+Duc)
44. Carl Pollard and Ivan A. Sag. 1994. Head-Driven Phrase Structure Grammar. Studies in Contemporary Linguistics. The University of Chicago Press and CSLI Publications, Chicago, IL and Stanford, CA. [find](https://scholar.google.com/scholar?q=Carl+Pollard+and+Ivan+A%2E+Sag%2E+1994%2E+Head%2DDriven+Phrase+Structure+Grammar%2E+Studies+in+Contemporary+Linguistics%2E+The+University+of+Chicago+Press+and+CSLI+Publications%2C+Chicago%2C+IL+and+Stanford%2C+CA%2E)
45. Jakob Prange, Nathan Schneider, and Vivek Srikumar. 2021. Supertagging the long tail with tree-structured decoding of complex categories. Transactions of the Association for Computational Linguistics, 9:243– 260. [find](https://scholar.google.com/scholar?q=Jakob+Prange%2C+Nathan+Schneider%2C+and+Vivek+Srikumar%2E+2021%2E+Supertagging+the+long+tail+with+tree%2Dstructured+decoding+of+complex+categories%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C)
46. RP Prins and GJM van Noord. 2004. Reinforcing parser preferences through tagging. Traitement Automatique des Langues, 3:121–139. [find](https://scholar.google.com/scholar?q=RP+Prins+and+GJM+van+Noord%2E+2004%2E+Reinforcing+parser+preferences+through+tagging%2E+Traitement+Automatique+des+Langues%2C+3%3A121%E2%80%93139%2E)
47. Adwait Ratnaparkhi et al. 1996. [A maximum entropy model for part-of-speech tagging](https://md.research.elamur.ai/free/en/papers/ratnaparkhi-1996-maximum-entropy-model-part-speech/). In EMNLP, volume 1, pages 133–142. Citeseer.
48. Eric Raymond. 1999. The cathedral and the bazaar. Knowledge, Technology & Policy, 12(3):23–49. [find](https://scholar.google.com/scholar?q=Eric+Raymond%2E+1999%2E+The+cathedral+and+the+bazaar%2E+Knowledge%2C+Technology+%26+Policy%2C+12%283%29%3A23%E2%80%9349%2E)
49. Taiga Someya, Ryo Yoshida, and Yohei Oseki. 2024. [Targeted syntactic evaluation on the chomsky hierarchy](https://md.research.elamur.ai/free/en/papers/someya-2024-targeted-syntactic-evaluation-chomsky-hierarchy/). In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15595–15605.
50. Yuanhe Tian, Yan Song, and Fei Xia. 2020. Supertagging combinatory categorial grammar with attentive graph convolutional networks. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6037–6044. [find](https://scholar.google.com/scholar?q=Yuanhe+Tian%2C+Yan+Song%2C+and+Fei+Xia%2E+2020%2E+Supertagging+combinatory+categorial+grammar+with+attentive+graph+convolutional+networks%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural)
51. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, et al. 2019. [Huggingface’s transformers: State-ofthe-art natural language processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). arXiv preprint arXiv:1910.03771. [↗](https://arxiv.org/abs/1910.03771)
52. Wenduan Xu, Michael Auli, and Stephen Clark. 2015. CCG supertagging with a recurrent neural network. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 250–255. [find](https://scholar.google.com/scholar?q=Wenduan+Xu%2C+Michael+Auli%2C+and+Stephen+Clark%2E+2015%2E+CCG+supertagging+with+a+recurrent+neural+network%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+)
53. Jie Yang and Yue Zhang. 2018. [NCRF++: An open-source neural sequence labeling toolkit](https://md.research.elamur.ai/free/en/papers/yang-2018-ncrf-open-source-neural-sequence/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.
54. Deniz Yuret, Aydin Han, and Zehra Turgut. 2010. Semeval-2010 task 12: Parser evaluation using textual entailments. In Proceedings of the 5th International Workshop on Semantic Evaluation, pages 51–56. [find](https://scholar.google.com/scholar?q=Deniz+Yuret%2C+Aydin+Han%2C+and+Zehra+Turgut%2E+2010%2E+Semeval%2D2010+task+12%3A+Parser+evaluation+using+textual+entailments%2E+In+Proceedings+of+the+5th+International+Workshop+on+Semantic+Evaluation%2C+pages+51%E2%80%9356%2E)
55. Yao-Zhong Zhang, Takuya Matsuzaki, and Jun’ichi Tsujii. 2012. Structure-guided supertagger learning. Natural Language Engineering, 18(2):205–234. [find](https://scholar.google.com/scholar?q=Yao%2DZhong+Zhang%2C+Takuya+Matsuzaki%2C+and+Jun%E2%80%99ichi+Tsujii%2E+2012%2E+Structure%2Dguided+supertagger+learning%2E+Natural+Language+Engineering%2C+18%282%29%3A205%E2%80%93234%2E)
56. Yao-Zhong Zhang, Takuya Matsuzaki, and Jun’ichi Tsujii. 2009. HPSG supertagging: A sequence labeling view. In Proceedings of the 11th International Conference on Parsing Technologies (IWPT’09), pages 210–213. [find](https://scholar.google.com/scholar?q=Yao%2DZhong+Zhang%2C+Takuya+Matsuzaki%2C+and+Jun%E2%80%99ichi+Tsujii%2E+2009%2E+HPSG+supertagging%3A+A+sequence+labeling+view%2E+In+Proceedings+of+the+11th+International+Conference+on+Parsing+Technologies+%28IWPT%E2%80%9909%29%2C+pages+)
57. Yao-Zhong Zhang, Takuya Matsuzaki, and Jun’ichi Tsujii. 2010. A simple approach for HPSG supertagging using dependency information. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 645–648. [find](https://scholar.google.com/scholar?q=Yao%2DZhong+Zhang%2C+Takuya+Matsuzaki%2C+and+Jun%E2%80%99ichi+Tsujii%2E+2010%2E+A+simple+approach+for+HPSG+supertagging+using+dependency+information%2E+In+Human+Language+Technologies%3A+The+2010+Annual+Conference+of+the+No)
58. Yi Zhang and Hans-Ulrich Krieger. 2011. Large-scale corpus-driven PCFG approximation of an HPSG. In Proceedings of the 12th international conference on parsing technologies, pages 198–208. [find](https://scholar.google.com/scholar?q=Yi+Zhang+and+Hans%2DUlrich+Krieger%2E+2011%2E+Large%2Dscale+corpus%2Ddriven+PCFG+approximation+of+an+HPSG%2E+In+Proceedings+of+the+12th+international+conference+on+parsing+technologies%2C+pages+198%E2%80%93208%2E)

*Updated 2 November 2026*