#format wiki #language en #acl +All:read Default = Scwad project = == Project factsheet == || English name: || Compositional distributional modelling of Polish language semantics || || Polish name: || Kompozycyjno-dystrybucyjne modelowanie semantyki języka polskiego || || Project type: || The [[http://www.ncn.gov.pl/|National Science Centre]] SONATA 8 grant 2014/15/D/HS2/03486 || || Duration: || 30 September 2015 ‒ 29 September 2018 (extended to 30 September 2020) || || NCN project info page: || https://projekty.ncn.gov.pl/index.php?projekt_id=279039 || || Principal investigator: || Alina Wróblewska || == Project summary == Within the project, basic research will be conducted on compositional distributional semantics employed in modelling the meaning of phrases and sentences. A compositional distributional semantic model endeavours to determine the meaning of sentences or phrases based on the sophisticated procedure of composing distributional word vectors, and to generate a vector representation of this meaning. The degree of similarity between two vectors, which belong to the same vector space but represent meanings of different sentences, can be estimated with similarity measures. With respect to the Polish language, this scientific issue has been studied neither by us nor by other members of the natural language processing community in Poland. Within our pioneering studies, we will investigate whether it is possible to estimate compositional distributional semantic models for languages with a complex inflectional system and relatively free word order, such as Polish. == Achievements == * [[https://github.com/360er0/COMBO|COMBO]], the jointly trained neural tagger, morphological analyser, lemmatizer and dependency parser ranked 3rd/4th in the [[http://universaldependencies.org/conll18/results.html|CoNLL 2018 UD shared task]]. * COMBO won the shared task 1(A) in [[http://2018.poleval.pl|PolEval 2018]] competition ([[http://2018.poleval.pl/index.php/results|Task 1(A) results]]). * The morphosyntactic disambiguator Toygger won the shared task 1(A) in [[http://2017.poleval.pl|PolEval 2017]] competition ([[http://2017.poleval.pl/index.php/results/|Task 1(A) results]]). == Resources == * [[http://git.nlp.ipipan.waw.pl/Scwad/SCWAD-CDSCorpus|Polish CDSCorpus]] (Wróblewska and Krasnowska-Kieraś, 2017) * [[http://zil.ipipan.waw.pl/Scwad/AIDe|AIDe - Corpus of Annotated Image Descriptions]] (Wróblewska, 2018a) * [[http://git.nlp.ipipan.waw.pl/Scwad/SCWAD-probing-data|Polish and English probing task data sets]] (Krasnowska-Kieraś and Wróblewska, 2019) == Tools and Demo == * [[http://scwad-demo.nlp.ipipan.waw.pl:8000|Scwad-demo]] - wizualizacja wyników modeli parsowania zależnościowego, wynikania tekstowego i powiązania semantycznego opracowanych w projekcie. * [[https://github.com/ipipan/combo|COMBO-pytorch]] - the reimplementation of COMBO in [[https://pytorch.org|PyTorch]] library * [[https://github.com/360er0/COMBO|COMBO]] - the jointly trained neural tagger, morphological analyser, lemmatizer and dependency parser (Rybak and Wróblewska, 2018). The [[http://zil.ipipan.waw.pl/PDB/PDBparser|COMBO models for Polish]] trained on [[http://zil.ipipan.waw.pl/PDB|Polish Dependency Bank]] (Wróblewska, 2018b) are publicly available. * [[http://mozart.ipipan.waw.pl/~kkrasnowska/PolEval/src/|Toygger]] - morphosyntactic disambiguator of Polish (Krasnowska-Kieraś, 2017) == Publications == <> <> <> <> <> <> <> <> <> ## == Selected results ==