Milen Kouylekov

• Lison, Pierre; Tiedemann, Jörg & Kouylekov, Milen (2018). OpenSubtitles 2018: Statistical rescoring of sentence alignments in large, noisy parallel corpora. In Calzolari, Nicoletta; Choukri, Khalid; Cieri, Christopher; Declerck, Thierry; Goggi, Sara; Hasida, Koiti; Isahara, Hitoshi; Maegaard, Bente; Mariani, Joseph; Mazo, Hélène; Moreno, Asuncion; Odijk, Jan; Piperidis, Stelios & Tokunaga, Takenobu (Ed.), Proceedings of the Eleventh International Conference on Language Resources and Evaluation. European Language Resources Association. ISSN 9791095546009. p. 1742–1748. Full text in Research Archive Show summary

  Movie and TV subtitles are a highly valuable resource for the compilation of parallel corpora thanks to their availability in large numbers and across many languages. However, the quality of the resulting sentence alignments is often lower than for other parallel corpora. This paper presents a new major release of the OpenSubtitles collection of parallel corpora, which is extracted from a total of 3.7 million subtitles spread over 60 languages. In addition to a substantial increase in the corpus size (about 30 % compared to the previous version), this new release associates explicit quality scores to each sentence alignment. These scores are determined by a statistical regression model based on simple language-independent features and estimated on a small sample of aligned sentence pairs. Evaluation results show that the model is able predict lexical translation probabilities with a root mean square error of 0.07 (coefficient of determination R2 = 0.47). Based on the scores produced by this regression model, the parallel corpora can be filtered to prune out alignments with a score below a given threshold.

• Szpektor, Idan; Tanev, Hristo; Dagan, Ido; Coppola, Bonaventura & Kouylekov, Milen (2015). Unsupervised acquisition of entailment relations from the Web. Natural Language Engineering. ISSN 1351-3249. 21(01), p. 3–47. doi: 10.1017/S1351324913000156. Full text in Research Archive
• Lien, Elisabeth & Kouylekov, Milen (2015). Semantic Parsing for Textual Entailment. In Carroll, John; Gojenola, Koldo & Oepen, Stephan (Ed.), Proceedings of the 14th International Conference on Parsing Technologies. Association for Computational Linguistics (ACL). ISSN 9781941643983. p. 40–49. doi: 10.18653/v1/w15-2205. Full text in Research Archive
• Kouylekov, Milen & Oepen, Stephan (2014). Semantic Technologies for Querying Linguistic Annotations: An Experiment Focusing on Graph-Structured Data. In Calzolari, Nicoletta; Choukri, Khalid; Declerck, Thierry; Loftsson, Hrafn; Maegaard, Bente; Mariani, Joseph; Moreno, Asuncion; Odijk, Jan & Piperidis, Stelios (Ed.), Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14). European Language Resources Association. ISSN 9782951740884. Full text in Research Archive Show summary

  With growing interest in the creation and search of linguistic annotations that form general graphs (in contrast to formally simpler, rooted trees), there also is an increased need for infrastructures that support the exploration of such representations, for example logical-form meaning representations or semantic dependency graphs. In this work, we heavily lean on semantic technologies and in particular the data model of the Resource Description Framework (RDF) to represent, store, and efficiently query very large collections of text annotated with graph-structured representations of sentence meaning. The LREC 2014 Proceedings are licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

• Kouylekov, Milen & Oepen, Stephan (2014). RDF Triple Stores and a Custom SPARQL Front-End for Indexing and Searching (Very) Large Semantic Networks. In Tounsi, Lamia & Rafal, Rak (Ed.), Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: System Demonstrations. Association for Computational Linguistics (ACL). ISSN 9781941643273. p. 90–94. Full text in Research Archive
• Lien, Elisabeth & Kouylekov, Milen (2014). UIO-Lien: Entailment Recognition using Minimal Recursion Semantics. In Nakov, Preslav & Zesch, Torsten (Ed.), Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014). Association for Computational Linguistics (ACL). ISSN 9781941643242. p. 699–703. doi: 10.3115/v1/s14-2125. Full text in Research Archive Show summary

  In this paper we present our participation in the Semeval 2014 task “Evaluation of compositional distributional semantic models on full sentences through semantic relatedness and textual entailment”. Our results demonstrate that using generic tools for semantic analysis is a viable option for a system that recognizes textual entailment. The invested effort in developing such tools allows us to build systems for reasoning that do not require training. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), 2014, Pages 699-703.

View all works in NVA

• Lison, Pierre; Tiedemann, Jörg & Kouylekov, Milen (2018). OpenSubtitles 2018: Statistical Rescoring of Sentence Alignments in Large, Noisy Parallel Corpora. Full text in Research Archive Show summary

  Movie and TV subtitles are a highly valuable resource for the compilation of parallel corpora thanks to their availability in large numbers and across many languages. However, the quality of the resulting sentence alignments is often lower than for other parallel corpora. This paper presents a new major release of the OpenSubtitles collection of parallel corpora, which is extracted from a total of 3.7 million subtitles spread over 60 languages. In addition to a substantial increase in the corpus size (about 30 % compared to the previous version), this new release associates explicit quality scores to each sentence alignment. These scores are determined by a statistical regression model based on simple language-independent features and estimated on a small sample of aligned sentence pairs. Evaluation results show that the model is able predict lexical translation probabilities with a root mean square error of 0.07 (coefficient of determination R2 = 0.47). Based on the scores produced by this regression model, the parallel corpora can be filtered to prune out alignments with a score below a given threshold

• Lien, Elisabeth & Kouylekov, Milen (2015). Semantic Parsing for Textual Entailment. Full text in Research Archive
• Lien, Elisabeth & Kouylekov, Milen (2014). UIO-Lien: Entailment Recognition using Minimal Recursion Semantics. Full text in Research Archive

View all works in NVA