Author
Glavaš, Goran and Vulić, Ivan
Conference
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Year
2018
Figures & Tables
Table 6: DST performance of G LO V E -CC embed-dings specialized using explicit retrofitting.
Table 2: Performance (ρ) on SL and SV for ER-
Table 5: Examples of lexical simplifications performed with the Light-LS tool when using different embedding spaces. The target word to be simplified is in bold.
Table 1: Spearman’s ρ correlation scores for three standard English distributional vectors spaces on English SimLex-999 (SL) and SimVerb-3500 (SV), using explicit retrofitting models with two different objective functions (ER-MSD and ER-CNT, cf. Section 3.3).
Table 4: Lexical simplification performance with explicit retrofitting applied on three input spaces.
Table of Contents
- Abstract
- 1 Introduction
- 2 Related Work
- 3 Explicit Retrofitting
- 3.1 From Constraints to Training Instances
- 5 Results and Discussion
- 5.1 Word Similarity
- 5.2 Language Transfer
- 5.3 Downstream Tasks
- 5.3.1 Lexical Text Simplification
- 5.3.2 Dialog State Tracking
- 6 Conclusion
- Acknowledgments
- References
- 5:135–146. Danushka Bollegala, Mohammed Alsuhaibani,
- 3:211–225. Quan Liu, Hui Jiang, Si Wei, Zhen-Hua Ling, and
References
- Rami Al-Rfou, Bryan Perozzi, and Steven Skiena.2013. Polyglot: Distributed word representations for multilingual NLP. In Proceedings of CoNLL,pages 183–192.View this Paper
- Rami Al-Rfou, Bryan Perozzi, and Steven Skiena.2013. Polyglot: Distributed word representations for multilingual NLP. In Proceedings of CoNLL,pages 183–192.View this Paper
- Collin F. Baker, Charles J. Fillmore, and John B. Lowe.1998. The Berkeley FrameNet project. In Proceedings of ACL, pages 86–90.View this Paper
- Collin F. Baker, Charles J. Fillmore, and John B. Lowe.1998. The Berkeley FrameNet project. In Proceedings of ACL, pages 86–90.View this Paper
- Jiang Bian, Bin Gao, and Tie-Yan Liu. 2014. Knowledge-powered deep learning for word embedding. In Proceedings of ECML-PKDD, pages 132–148.View this Paper
- Jiang Bian, Bin Gao, and Tie-Yan Liu. 2014. Knowledge-powered deep learning for word embedding. In Proceedings of ECML-PKDD, pages 132–148.View this Paper
- Piotr Bojanowski, Edouard Grave, Armand Joulin, andView this Paper
- Piotr Bojanowski, Edouard Grave, Armand Joulin, and
- Tomas Mikolov. 2017. Enriching word vectors with
- Tomas Mikolov. 2017. Enriching word vectors with
- subword information. Transactions of the ACL,
- subword information. Transactions of the ACL,
+- Similar Papers (10)