---
title: "ConSeC — paper by Barba et al. (2021) — summary and ideas"
description: "It builds on the extractive reformulation of WSD by Barba et al. (2021a), in which… 82.0 F1 on the ALL. 46 references, cited by 51 papers here."
authors: ["Edoardo Barba", "Luigi Procopio", "Roberto Navigli"]
year: 2021
venue: "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/2021.emnlp-main.112/"
doi: "10.18653/v1/2021.emnlp-main.112"
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/barba-2021-consec-word-sense-disambiguation-as/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/barba-2021-consec-word-sense-disambiguation-as/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/4/) / ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension

# ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension

**Authors:** [Edoardo Barba](https://md.research.elamur.ai/free/en/authors/edoardo-barba/), [Luigi Procopio](https://md.research.elamur.ai/free/en/authors/luigi-procopio/) and [Roberto Navigli](https://md.research.elamur.ai/free/en/authors/roberto-navigli/) · **Year:** 2021 · **Venue:** [Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2021](https://md.research.elamur.ai/free/en/venues/emnlp/2021/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.emnlp-main.112/) · [PDF](https://aclanthology.org/2021.emnlp-main.112.pdf) · [DOI 10.18653/v1/2021.emnlp-main.112](https://doi.org/10.18653/v1/2021.emnlp-main.112) · [OpenAlex](https://openalex.org/W3213432108)

**Citations:** 58 citations (OpenAlex, 2026-10-14) · [51](https://md.research.elamur.ai/free/en/papers/barba-2021-consec-word-sense-disambiguation-as/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary

Most modern supervised Word Sense Disambiguation (WSD) systems assign a sense to each target word separately. Even when several ambiguous words share a sentence, the sense chosen for one word never informs the choices for the others. ConSeC (CONtinuous SEnse Comprehension) removes this limitation. It builds on the extractive reformulation of WSD by Barba et al. (2021a), in which a model reads the context together with the candidate glosses of a target word and selects the most fitting gloss.

ConSeC sorts the targets in a sentence with a heuristic ordering function. It then disambiguates them one at a time, feeding the glosses already chosen for earlier words back into the input. The backbone is DeBERTa large with a linear classification head. The model's relative position encodings are rewritten so that each chosen definition appears right next to the word it describes, while the sentence's own word order stays unchanged.

ConSeC sets a new state of the art on the English all-words benchmark of Raganato et al. (2017a) and on the multilingual framework of Pasini et al. (2021). This shows that explicitly modelling dependencies between sense choices helps neural WSD.

## Key points

- **English results:** Trained only on SemCor, with WordNet as the sense inventory, ConSeC reaches 82.0 F1 on the ALL test set, 1.3 F1 points above the previous best system. Adding WordNet's tagged glosses and examples as extra training data raises this to 83.2 F1.
- **Input format:** The target word is wrapped in the special tokens `<d>` and `</d>`, and each candidate gloss starts with a `<def>` token. The model predicts which `<def>` token opens the correct gloss.
- **Behavioral tests (SemCor-trained, ALL):**
  - Turning off the feedback loop gives 80.7 F1 (−1.3), which is still close to the previous state of the art. The loop can therefore be dropped when speed matters, allowing words to be disambiguated independently in batches.
  - Deliberately supplying less likely context definitions gives 80.0 F1 (−2.0).
  - Supplying gold context definitions instead of the model's own predictions gives 82.5 F1 (+0.5).
- **Cross-lingual results:** Using the Pasini et al. (2021) framework, ConSeC was tested in eight languages: English, French, German, Italian, Spanish, Dutch, Estonian and Japanese. It outperformed baselines such as XLMR-Large and EWISER on every language, including lower-resource ones like Estonian and Japanese.
- **Analysis and release:** Instance polysemy and error rate are strongly linked (Spearman correlation 0.94). Code and models are available at github.com/SapienzaNLP/consec.

*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

- [Sapienza University of Rome](https://md.research.elamur.ai/free/en/universities/sapienza-university-of-rome/) — University, Rome, Italy · 60 works · 10,105 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): [🔀 Word sense disambiguation](https://md.research.elamur.ai/free/en/topics/word-sense-disambiguation/) · 87 works

## Cite

Cite as: Edoardo Barba, Luigi Procopio and Roberto Navigli. 2021. ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{barba2021consec,
  title = {{ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension}},
  author = {Edoardo Barba, Luigi Procopio and Roberto Navigli},
  booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
  year = {2021},
  doi = {10.18653/v1/2021.emnlp-main.112},
  url = {https://doi.org/10.18653/v1/2021.emnlp-main.112}
}
```

- [← previous NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints](https://md.research.elamur.ai/free/en/papers/lu-2021-neurologic-decoding-un-supervised-neural/)
- [next → Coreference Resolution without Span Representations](https://md.research.elamur.ai/free/en/papers/kirstain-2021-coreference-resolution-without-span-representations/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/4/)

## References

46 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Edoardo Barba, Tommaso Pasini, and Roberto Navigli. 2021a. ESC: Redesigning WSD with extractive sense comprehension. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4661–4672, Online. Association… [find](https://scholar.google.com/scholar?q=Edoardo+Barba%2C+Tommaso+Pasini%2C+and+Roberto+Navigli%2E+2021a%2E+ESC%3A+Redesigning+WSD+with+extractive+sense+comprehension%2E+In+Proceedings+of+the+2021+Conference+of+the+North+American+Chapter+of+the+Associat)
2. Edoardo Barba, Luigi Procopio, Caterina Lacerra, Tommaso Pasini, and Roberto Navigli. 2021b. [Exemplification modeling: Can you give me an example, please?](https://md.research.elamur.ai/free/en/papers/barba-2021-exemplification-modeling/) In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pages 3779–3785. International Joint Confere…
3. Michele Bevilacqua and Roberto Navigli. 2020. [Breaking through the 80% glass ceiling: Raising the state of the art in word sense disambiguation by incorporating knowledge graph information](https://md.research.elamur.ai/free/en/papers/bevilacqua-2020-breaking-through-80-glass-ceiling/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2854–2864, O…
4. Michele Bevilacqua, Tommaso Pasini, Alessandro Raganato, and Roberto Navigli. 2021. Recent trends in word sense disambiguation: A survey. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, pages 4330–4338. International Joint Conferences on Artificia… [find](https://scholar.google.com/scholar?q=Michele+Bevilacqua%2C+Tommaso+Pasini%2C+Alessandro+Raganato%2C+and+Roberto+Navigli%2E+2021%2E+Recent+trends+in+word+sense+disambiguation%3A+A+survey%2E+In+Proceedings+of+the+Thirtieth+International+Joint+Conference)
5. Terra Blevins and Luke Zettlemoyer. 2020. [Moving down the long tail of word sense disambiguation with gloss informed bi-encoders](https://md.research.elamur.ai/free/en/papers/blevins-2020-moving-down-long-tail-word/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1006–1017, Online. Association for Computational Linguistics.
6. Gerlof Bouma. 2009. Normalized (pointwise) mutual information in collocation extraction. Proceedings of GSCL, pages 31–40. [find](https://scholar.google.com/scholar?q=Gerlof+Bouma%2E+2009%2E+Normalized+%28pointwise%29+mutual+information+in+collocation+extraction%2E+Proceedings+of+GSCL%2C+pages+31%E2%80%9340%2E)
7. Comet.ML. 2021. Comet.ML home page. [find](https://scholar.google.com/scholar?q=Comet%2EML%2E+2021%2E+Comet%2EML+home+page%2E)
8. Simone Conia and Roberto Navigli. 2021. Framing word sense disambiguation as a multi-label problem for model-agnostic knowledge integration. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3269–3275, Online. Associati… [find](https://scholar.google.com/scholar?q=Simone+Conia+and+Roberto+Navigli%2E+2021%2E+Framing+word+sense+disambiguation+as+a+multi%2Dlabel+problem+for+model%2Dagnostic+knowledge+integration%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Chapt)
9. Montse Cuadros and German Rigau. 2008. KnowNet: Building a large net of knowledge from the web. In Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pages 161–168, Manchester, UK. [find](https://scholar.google.com/scholar?q=Montse+Cuadros+and+German+Rigau%2E+2008%2E+KnowNet%3A+Building+a+large+net+of+knowledge+from+the+web%2E+In+Proceedings+of+the+22nd+International+Conference+on+Computational+Linguistics+%28Coling+2008%29%2C+pages+16)
10. Coling 2008 Organizing Committee. [find](https://scholar.google.com/scholar?q=Coling+2008+Organizing+Committee%2E)
11. 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 the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
12. Thomas G Dietterich. 1998. Approximate statistical tests for comparing supervised classification learning algorithms. Neural computation, 10(7):1895– 1923. [find](https://scholar.google.com/scholar?q=Thomas+G+Dietterich%2E+1998%2E+Approximate+statistical+tests+for+comparing+supervised+classification+learning+algorithms%2E+Neural+computation%2C+10%287%29%3A1895%E2%80%93+1923%2E)
13. Philip Edmonds and Scott Cotton. 2001. [SENSEVAL-2: Overview](https://md.research.elamur.ai/free/en/papers/edmonds-2001-senseval-2-overview/). In Proceedings of SENSEVAL-2 Second International Workshop on Evaluating Word Sense Disambiguation Systems, pages 1–5, Toulouse, France. Association for Computational Linguistics.
14. Katrin Erk and Diana McCarthy. 2009. Graded word sense assignment. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 2009, 6-7 August 2009, Singapore, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 440–449. ACL. [find](https://scholar.google.com/scholar?q=Katrin+Erk+and+Diana+McCarthy%2E+2009%2E+Graded+word+sense+assignment%2E+In+Proceedings+of+the+2009+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+EMNLP+2009%2C+6%2D7+August+2009%2C+Singapore%2C+A+)
15. William Falcon, Jirka Borovec, Adrian Wälchli, Nic Eggert, Justus Schock, Jeremy Jordan, Nicki Skafte, Ir1dXD, Vadim Bereznyuk, Ethan Harris, Tullie Murrell, Peter Yu, Sebastian Præsius, Travis Addair, Jacob Zhong, Dmitry Lipin, So Uchida, Shreyas Ba-pat, Hendrik Schröter, Boris Dayma, Alexey Kar-na… [find](https://scholar.google.com/scholar?q=William+Falcon%2C+Jirka+Borovec%2C+Adrian+W%C3%A4lchli%2C+Nic+Eggert%2C+Justus+Schock%2C+Jeremy+Jordan%2C+Nicki+Skafte%2C+Ir1dXD%2C+Vadim+Bereznyuk%2C+Ethan+Harris%2C+Tullie+Murrell%2C+Peter+Yu%2C+Sebastian+Pr%C3%A6sius%2C+Travis+Addair)
16. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press. [http://www.deeplearningbook.org](http://www.deeplearningbook.org). [↗](http://www.deeplearningbook.org)
17. Christian Hadiwinoto, Hwee Tou Ng, and Wee Chung Gan. 2019. Improved word sense disambiguation using pre-trained contextualized word representations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Langua… [find](https://scholar.google.com/scholar?q=Christian+Hadiwinoto%2C+Hwee+Tou+Ng%2C+and+Wee+Chung+Gan%2E+2019%2E+Improved+word+sense+disambiguation+using+pre%2Dtrained+contextualized+word+representations%2E+In+Proceedings+of+the+2019+Conference+on+Empirical)
18. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. [Deberta: decoding-enhanced bert with disentangled attention](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/). In 9th International Conference on Learning Representations, ICLR 2021.
19. Luyao Huang, Chi Sun, Xipeng Qiu, and Xuanjing Huang. 2019. [GlossBERT: BERT for word sense disambiguation with gloss knowledge](https://md.research.elamur.ai/free/en/papers/huang-2019-glossbert-bert-word-sense-disambiguation/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-I…
20. Mikael Kågebäck and Hans Salomonsson. 2016. Word sense disambiguation using a bidirectional LSTM. In Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V), pages 51–56, Osaka, Japan. [find](https://scholar.google.com/scholar?q=Mikael+K%C3%A5geb%C3%A4ck+and+Hans+Salomonsson%2E+2016%2E+Word+sense+disambiguation+using+a+bidirectional+LSTM%2E+In+Proceedings+of+the+5th+Workshop+on+Cognitive+Aspects+of+the+Lexicon+%28CogALex+%2D+V%29%2C+pages+51%E2%80%9356%2C+Osa)
21. The COLING 2016 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COLING+2016+Organizing+Committee%2E)
22. Adam Kilgarriff. 2004. How dominant is the commonest sense of a word? In Text, Speech and Dialogue, pages 103–111, Berlin, Heidelberg. Springer Berlin Heidelberg. [find](https://scholar.google.com/scholar?q=Adam+Kilgarriff%2E+2004%2E+How+dominant+is+the+commonest+sense+of+a+word%3F+In+Text%2C+Speech+and+Dialogue%2C+pages+103%E2%80%93111%2C+Berlin%2C+Heidelberg%2E+Springer+Berlin+Heidelberg%2E)
23. Sawan Kumar, Sharmistha Jat, Karan Saxena, and Partha Talukdar. 2019. Zero-shot word sense disambiguation using sense definition embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5670–5681, Florence, Italy. Association for Computational Lin… [find](https://scholar.google.com/scholar?q=Sawan+Kumar%2C+Sharmistha+Jat%2C+Karan+Saxena%2C+and+Partha+Talukdar%2E+2019%2E+Zero%2Dshot+word+sense+disambiguation+using+sense+definition+embeddings%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Associatio)
24. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. [BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/). In Proceedings of the 58th Annual Meeting of the…
25. Liyuan Liu, Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao, and Jiawei Han. 2020a. On the variance of the adaptive learning rate and beyond. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Liyuan+Liu%2C+Haoming+Jiang%2C+Pengcheng+He%2C+Weizhu+Chen%2C+Xiaodong+Liu%2C+Jianfeng+Gao%2C+and+Jiawei+Han%2E+2020a%2E+On+the+variance+of+the+adaptive+learning+rate+and+beyond%2E+In+International+Conference+on+Learni)
26. Weijie Liu, Peng Zhou, Zhe Zhao, Zhiruo Wang, Qi Ju, Haotang Deng, and Ping Wang. 2020b. [K-bert: Enabling language representation with knowledge graph](https://md.research.elamur.ai/free/en/papers/liu-2019-k-bert-enabling-language-representation/). In Proceedings of the AAAI Conference on Artificial Intelligence, pages 2901–2908.
27. Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, and Luke Zettlemoyer. 2020c. Multilingual denoising pre-training for neural machine translation. Transactions of the Association for Computational Linguistics, 8:726–742. [find](https://scholar.google.com/scholar?q=Yinhan+Liu%2C+Jiatao+Gu%2C+Naman+Goyal%2C+Xian+Li%2C+Sergey+Edunov%2C+Marjan+Ghazvininejad%2C+Mike+Lewis%2C+and+Luke+Zettlemoyer%2E+2020c%2E+Multilingual+denoising+pre%2Dtraining+for+neural+machine+translation%2E+Transacti)
28. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [RoBERTa: A robustly optimized BERT pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv preprint arXiv:1907.11692.
29. Marco Maru, Federico Scozzafava, Federico Martelli, and Roberto Navigli. 2019. SyntagNet: Challenging supervised word sense disambiguation with lexical-semantic combinations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Con… [find](https://scholar.google.com/scholar?q=Marco+Maru%2C+Federico+Scozzafava%2C+Federico+Martelli%2C+and+Roberto+Navigli%2E+2019%2E+SyntagNet%3A+Challenging+supervised+word+sense+disambiguation+with+lexical%2Dsemantic+combinations%2E+In+Proceedings+of+the+201)
30. George A. Miller, R.T. Beckwith, Christiane D. Fellbaum, D. Gross, and K. Miller. 1990. Introduction to WordNet: an online lexical database. International Journal of Lexicography, 3(4):235–244. [find](https://scholar.google.com/scholar?q=George+A%2E+Miller%2C+R%2ET%2E+Beckwith%2C+Christiane+D%2E+Fellbaum%2C+D%2E+Gross%2C+and+K%2E+Miller%2E+1990%2E+Introduction+to+WordNet%3A+an+online+lexical+database%2E+International+Journal+of+Lexicography%2C+3%284%29%3A235%E2%80%93244%2E)
31. George A Miller, Claudia Leacock, Randee Tengi, and Ross T Bunker. 1993. [A semantic concordance](https://md.research.elamur.ai/free/en/papers/miller-1993-semantic-concordance/). In Proceedings of the workshop on Human Language Technology, pages 303–308. Association for Computational Linguistics.
32. Andrea Moro and Roberto Navigli. 2015. SemEval-2015 task 13: Multilingual all-words sense disambiguation and entity linking. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 288–297, Denver, Colorado. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Andrea+Moro+and+Roberto+Navigli%2E+2015%2E+SemEval%2D2015+task+13%3A+Multilingual+all%2Dwords+sense+disambiguation+and+entity+linking%2E+In+Proceedings+of+the+9th+International+Workshop+on+Semantic+Evaluation+%28Se)
33. Roberto Navigli, David Jurgens, and Daniele Vannella. 2013. SemEval-2013 task 12: Multilingual word sense disambiguation. In Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013), pages… [find](https://scholar.google.com/scholar?q=Roberto+Navigli%2C+David+Jurgens%2C+and+Daniele+Vannella%2E+2013%2E+SemEval%2D2013+task+12%3A+Multilingual+word+sense+disambiguation%2E+In+Second+Joint+Conference+on+Lexical+and+Computational+Semantics+%28%2ASEM%29%2C+Volu)
34. Roberto Navigli and Paola Velardi. 2004. Structural semantic interconnection: a knowledge-based approach to word sense disambiguation. In Proceedings of SENSEVAL-3, the Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, pages 179–182, Barcelona, Spain. Assoc… [find](https://scholar.google.com/scholar?q=Roberto+Navigli+and+Paola+Velardi%2E+2004%2E+Structural+semantic+interconnection%3A+a+knowledge%2Dbased+approach+to+word+sense+disambiguation%2E+In+Proceedings+of+SENSEVAL%2D3%2C+the+Third+International+Workshop+on)
35. Tommaso Pasini, Alessandro Raganato, and Roberto Navigli. 2021. XL-WSD: An extra-large and cross-lingual evaluation framework for word sense disambiguation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(15):13648–13656. [find](https://scholar.google.com/scholar?q=Tommaso+Pasini%2C+Alessandro+Raganato%2C+and+Roberto+Navigli%2E+2021%2E+XL%2DWSD%3A+An+extra%2Dlarge+and+cross%2Dlingual+evaluation+framework+for+word+sense+disambiguation%2E+Proceedings+of+the+AAAI+Conference+on+Artif)
36. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Te-jani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and… — [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/)
37. Sameer Pradhan, Edward Loper, Dmitriy Dligach, and Martha Palmer. 2007. [SemEval-2007 task-17: English lexical sample, SRL and all words](https://md.research.elamur.ai/free/en/papers/pradhan-2007-semeval-2007-task-17-english/). In Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), pages 87–92, Prague, Czech Republic. Association for Computational Ling…
38. Alessandro Raganato, Jose Camacho-Collados, and Roberto Navigli. 2017a. [Word sense disambiguation: A unified evaluation framework and empirical comparison](https://md.research.elamur.ai/free/en/papers/raganato-2017-word-sense-disambiguation-unified-evaluation/). In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 99–…
39. Alessandro Raganato, Claudio Delli Bovi, and Roberto Navigli. 2017b. Neural sequence learning models for word sense disambiguation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1156–1167, Copenhagen, Denmark. Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Alessandro+Raganato%2C+Claudio+Delli+Bovi%2C+and+Roberto+Navigli%2E+2017b%2E+Neural+sequence+learning+models+for+word+sense+disambiguation%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+Natura)
40. Bianca Scarlini, Tommaso Pasini, and Roberto Navigli. 2020. With more contexts comes better performance: Contextualized sense embeddings for all-round word sense disambiguation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3528–3539, Online… [find](https://scholar.google.com/scholar?q=Bianca+Scarlini%2C+Tommaso+Pasini%2C+and+Roberto+Navigli%2E+2020%2E+With+more+contexts+comes+better+performance%3A+Contextualized+sense+embeddings+for+all%2Dround+word+sense+disambiguation%2E+In+Proceedings+of+the+)
41. Federico Scozzafava, Marco Maru, Fabrizio Brignone, Giovanni Torrisi, and Roberto Navigli. 2020. Personalized PageRank with syntagmatic information for Multilingual Word Sense Disambiguation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstra… [find](https://scholar.google.com/scholar?q=Federico+Scozzafava%2C+Marco+Maru%2C+Fabrizio+Brignone%2C+Giovanni+Torrisi%2C+and+Roberto+Navigli%2E+2020%2E+Personalized+PageRank+with+syntagmatic+information+for+Multilingual+Word+Sense+Disambiguation%2E+In+Proce)
42. Benjamin Snyder and Martha Palmer. 2004. The English all-words task. In Proceedings of SENSEVAL-3, the Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, pages 41–43, Barcelona, Spain. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Benjamin+Snyder+and+Martha+Palmer%2E+2004%2E+The+English+all%2Dwords+task%2E+In+Proceedings+of+SENSEVAL%2D3%2C+the+Third+International+Workshop+on+the+Evaluation+of+Systems+for+the+Semantic+Analysis+of+Text%2C+page)
43. Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, and Angela Fan. 2020. Multilingual translation with extensible multilingual pretraining and finetuning. arXiv preprint arXiv:2008.00401. [find](https://scholar.google.com/scholar?q=Yuqing+Tang%2C+Chau+Tran%2C+Xian+Li%2C+Peng%2DJen+Chen%2C+Naman+Goyal%2C+Vishrav+Chaudhary%2C+Jiatao+Gu%2C+and+Angela+Fan%2E+2020%2E+Multilingual+translation+with+extensible+multilingual+pretraining+and+finetuning%2E+arXiv)
44. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In Advances in Neural Information Processing Systems, page 6000–6010. Curran Associates, Inc.
45. Loïc Vial, Benjamin Lecouteux, and Didier Schwab. 2019. Sense vocabulary compression through the semantic knowledge of WordNet for neural word sense disambiguation. In Proceedings of the 10th Global Wordnet Conference, pages 108–117, Wroclaw, Poland. Global Wordnet Association. [find](https://scholar.google.com/scholar?q=Lo%C3%AFc+Vial%2C+Benjamin+Lecouteux%2C+and+Didier+Schwab%2E+2019%2E+Sense+vocabulary+compression+through+the+semantic+knowledge+of+WordNet+for+neural+word+sense+disambiguation%2E+In+Proceedings+of+the+10th+Global+W)
46. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtow-icz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lh… — [Transformers: State-of-the-Art Natural Language Processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/)

*Updated 2 November 2026*