2020
|
Skórzewski, Paweł; Sieińska, Weronika; Kubis, Marek Noetic end-to-end response selection with supervised neural network based classifiers and unsupervised similarity models Journal Article Computer Speech & Language, 62 , 2020, ISSN: 0885-2308. Abstract | Links | BibTeX @article{SKORZEWSKI2020101074,
title = {Noetic end-to-end response selection with supervised neural network based classifiers and unsupervised similarity models},
author = {Paweł Skórzewski and Weronika Sieińska and Marek Kubis},
url = {http://www.sciencedirect.com/science/article/pii/S0885230820300073},
doi = {https://doi.org/10.1016/j.csl.2020.101074},
issn = {0885-2308},
year = {2020},
date = {2020-07-01},
journal = {Computer Speech & Language},
volume = {62},
abstract = {This paper describes a solution for the Noetic End-to-End Response Selection challenge – one of the tasks of the 7th Dialog System Technology Challenge. The goal of the task is to select the most appropriate continuation of a dialogue from a given set of responses. We approach this problem by building an ensemble of supervised neural network based classifiers and unsupervised similarity models. The dialogue continuation is selected according to a score that aggregates the rankings of candidate responses determined by the models in the ensemble.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper describes a solution for the Noetic End-to-End Response Selection challenge – one of the tasks of the 7th Dialog System Technology Challenge. The goal of the task is to select the most appropriate continuation of a dialogue from a given set of responses. We approach this problem by building an ensemble of supervised neural network based classifiers and unsupervised similarity models. The dialogue continuation is selected according to a score that aggregates the rankings of candidate responses determined by the models in the ensemble. |
2019
|
Kubis, Marek Quantitative Analysis of Character Networks in Polish XIX and XX Century Novels Inproceedings Proceedings of the Digital Humanities 2019 Conference, Utrecht, The Netherlands, 2019. Abstract | Links | BibTeX @inproceedings{Kubis19c,
title = {Quantitative Analysis of Character Networks in Polish XIX and XX Century Novels},
author = {Marek Kubis},
url = {http://mkubis.home.amu.edu.pl/dh2019.pdf
https://dev.clariah.nl/files/dh2019/boa/0843.html},
year = {2019},
date = {2019-07-09},
booktitle = {Proceedings of the Digital Humanities 2019 Conference},
address = {Utrecht, The Netherlands},
abstract = {This paper presents a study on induction and quantitative analysis of character networks inferred from Polish novels. The corpus gathered for this study is an order of magnitude larger than the collection of novels used by Elson et al. (2010) and Jayannavar et al (2015). It contains primarily novels from the second half of the 19th century and the first half of the 20th century. The main goal of this paper is to present novel results on systematic differences between the 19th century and 20th century Polish prose with respect to the collected corpus. },
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents a study on induction and quantitative analysis of character networks inferred from Polish novels. The corpus gathered for this study is an order of magnitude larger than the collection of novels used by Elson et al. (2010) and Jayannavar et al (2015). It contains primarily novels from the second half of the 19th century and the first half of the 20th century. The main goal of this paper is to present novel results on systematic differences between the 19th century and 20th century Polish prose with respect to the collected corpus. |
Kubis, Marek; Vetulani, Zygmunt; Wypych, Mikołaj; Ziętkiewicz, Tomasz Open Challenge for Correcting Errors of Speech Recognition Systems Inproceedings Vetulani, Zygmunt; Paroubek, Patrick (Ed.): Proceedings of the 9th Language and Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics, pp. 219–223, Wydawnictwo Nauka i Innowacje, Poznań, Poland, 2019, ISBN: 978-83-65988-30-0. Abstract | Links | BibTeX @inproceedings{Kubis19b,
title = {Open Challenge for Correcting Errors of Speech Recognition Systems},
author = {Marek Kubis and Zygmunt Vetulani and Mikołaj Wypych and Tomasz Ziętkiewicz},
editor = {Zygmunt Vetulani and Patrick Paroubek},
url = {https://arxiv.org/abs/2001.03041
https://gonito.net/gitlist/asr-corrections.git/},
isbn = {978-83-65988-30-0},
year = {2019},
date = {2019-05-17},
booktitle = {Proceedings of the 9th Language and Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics},
pages = {219--223},
publisher = {Wydawnictwo Nauka i Innowacje},
address = {Poznań, Poland},
abstract = {The paper announces the new long-term challenge for improving the performance of automatic speech recognition systems. The goal of the challenge is to investigate methods of correcting the recognition results on the basis of previously made errors by the speech processing system. The dataset prepared for the task is described and evaluation criteria are presented.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper announces the new long-term challenge for improving the performance of automatic speech recognition systems. The goal of the challenge is to investigate methods of correcting the recognition results on the basis of previously made errors by the speech processing system. The dataset prepared for the task is described and evaluation criteria are presented. |
Skórzewski, Paweł; Sieińska, Weronika; Kubis, Marek Noetic end-to-end response selection with supervised neural network based classifiers and unsupervised similarity models Inproceedings Proceedings of the 7th Dialog System Technology Challenge (DSTC7), Honolulu, 2019. Abstract | Links | BibTeX @inproceedings{Skórzewski2019bb,
title = {Noetic end-to-end response selection with supervised neural network based classifiers and unsupervised similarity models},
author = {Paweł Skórzewski and Weronika Sieińska and Marek Kubis},
url = {http://workshop.colips.org/dstc7/papers/21.pdf},
year = {2019},
date = {2019-01-27},
booktitle = {Proceedings of the 7th Dialog System Technology Challenge (DSTC7)},
address = {Honolulu},
abstract = {The paper describes a solution for the Noetic End-to-End Response Selection challenge – one of the tasks of the 7th Dialog System Technology Challenge. The goal of the task is to select the most appropriate continuation of a dialog from a given set of responses. We approach this problem by building the ensemble of supervised neural network based classifiers and unsupervised similarity models. The dialog continuation is selected according to the score that aggregates rankings of candidate responses determined by models that participate in the ensemble.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper describes a solution for the Noetic End-to-End Response Selection challenge – one of the tasks of the 7th Dialog System Technology Challenge. The goal of the task is to select the most appropriate continuation of a dialog from a given set of responses. We approach this problem by building the ensemble of supervised neural network based classifiers and unsupervised similarity models. The dialog continuation is selected according to the score that aggregates rankings of candidate responses determined by models that participate in the ensemble. |
2018
|
Kubis, Marek A Semantic Similarity Measurement Tool for WordNet-Like Databases Inproceedings Vetulani, Zygmunt; Mariani, Joseph; Kubis, Marek (Ed.): Human Language Technology. Challenges for Computer Science and Linguistics, pp. 155–168, Springer International Publishing, Cham, 2018, ISBN: 978-3-319-93781-6. Abstract | Links | BibTeX @inproceedings{Kubis18,
title = {A Semantic Similarity Measurement Tool for WordNet-Like Databases},
author = {Marek Kubis},
editor = {Zygmunt Vetulani and Joseph Mariani and Marek Kubis},
url = {http://mkubis.home.amu.edu.pl/ltc2015lnai.pdf},
doi = {10.1007/978-3-319-93782-3_12},
isbn = {978-3-319-93781-6},
year = {2018},
date = {2018-06-16},
booktitle = {Human Language Technology. Challenges for Computer Science and Linguistics},
volume = {10930},
pages = {155--168},
publisher = {Springer International Publishing},
address = {Cham},
abstract = {The paper describes a new framework for computing the semantic similarity of words and concepts using WordNet-like databases. The main advantage of the presented approach is the ability to implement similarity measures as concise expressions in the embedded query language. The preliminary results of the use of the framework to model the semantic similarity of Polish nouns are reported.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper describes a new framework for computing the semantic similarity of words and concepts using WordNet-like databases. The main advantage of the presented approach is the ability to implement similarity measures as concise expressions in the embedded query language. The preliminary results of the use of the framework to model the semantic similarity of Polish nouns are reported. |
2017
|
Kubis, Marek; Skórzewski, Paweł; Ziętkiewicz, Tomasz EUDAMU at SemEval-2017 Task 11: Action Ranking and Type Matching for End-User Development Inproceedings Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pp. 1000–1004, Association for Computational Linguistics, Vancouver, Canada, 2017. Abstract | Links | BibTeX @inproceedings{Kubis17,
title = {EUDAMU at SemEval-2017 Task 11: Action Ranking and Type Matching for End-User Development},
author = {Marek Kubis and Paweł Skórzewski and Tomasz Ziętkiewicz},
url = {https://www.aclweb.org/anthology/S17-2175.pdf},
doi = {10.18653/v1/S17-2175},
year = {2017},
date = {2017-08-03},
booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)},
pages = {1000--1004},
publisher = {Association for Computational Linguistics},
address = {Vancouver, Canada},
abstract = {The paper describes a system for end-user development using natural language. Our approach uses a ranking model to identify the actions to be executed followed by reference and parameter matching models to select parameter values that should be set for the given commands. We discuss the results of evaluation and possible improvements for future work.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
The paper describes a system for end-user development using natural language. Our approach uses a ranking model to identify the actions to be executed followed by reference and parameter matching models to select parameter values that should be set for the given commands. We discuss the results of evaluation and possible improvements for future work. |
2016
|
Kubis, Marek A Query Language for WordNet-like Lexical Databases Journal Article International Journal of Intelligent Information and Database Systems, 9 (2), pp. 103–133, 2016, ISSN: 1751-5858. Abstract | Links | BibTeX @article{Kubis16,
title = {A Query Language for WordNet-like Lexical Databases},
author = {Marek Kubis},
url = {http://mkubis.home.amu.edu.pl/ijiids2016.pdf},
doi = {10.1504/IJIIDS.2016.075419},
issn = {1751-5858},
year = {2016},
date = {2016-03-22},
journal = {International Journal of Intelligent Information and Database Systems},
volume = {9},
number = {2},
pages = {103--133},
publisher = {Inderscience Publishers},
address = {Geneva, Switzerland},
abstract = {WordNet-like lexical databases are used in many natural language processing tasks, such as word sense disambiguation, information extraction and sentiment analysis. The paper discusses the problem of querying such databases. The types of queries specific to WordNet-like databases are analysed and previous approaches that were undertaken to query wordnets are discussed. A query language which incorporates data types and syntactic constructs based on concepts that form the core of a WordNet-like database (synsets, word senses, semantic relations, etc.) is proposed as a new solution to the problem of querying wordnets.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
WordNet-like lexical databases are used in many natural language processing tasks, such as word sense disambiguation, information extraction and sentiment analysis. The paper discusses the problem of querying such databases. The types of queries specific to WordNet-like databases are analysed and previous approaches that were undertaken to query wordnets are discussed. A query language which incorporates data types and syntactic constructs based on concepts that form the core of a WordNet-like database (synsets, word senses, semantic relations, etc.) is proposed as a new solution to the problem of querying wordnets. |
2014
|
Kubis, Marek A Tool for Transforming WordNet-Like Databases Incollection Vetulani, Zygmunt; Mariani, Joseph (Ed.): Human Language Technology Challenges for Computer Science and Linguistics, 8387 , pp. 343–355, Springer International Publishing, 2014, ISBN: 978-3-319-08957-7. Abstract | Links | BibTeX @incollection{Kubis14,
title = {A Tool for Transforming WordNet-Like Databases},
author = {Marek Kubis},
editor = {Zygmunt Vetulani and Joseph Mariani},
url = {http://mkubis.home.amu.edu.pl/ltc2011lnai.pdf
https://link.springer.com/chapter/10.1007/978-3-319-08958-4_28},
doi = {10.1007/978-3-319-08958-4_28},
isbn = {978-3-319-08957-7},
year = {2014},
date = {2014-01-01},
booktitle = {Human Language Technology Challenges for Computer Science and Linguistics},
volume = {8387},
pages = {343--355},
publisher = {Springer International Publishing},
series = {Lecture Notes in Computer Science},
abstract = {The paper presents WUpdate – a data manipulation language designed for WordNet-like lexical databases. The language can be used to perform modifications of a wordnet, such as adding word senses, removing words, interlinking synsets, etc. The focus of the paper is on solving wordnet-specific problems that are not addressed by other data manipulation languages. In particular, the paper addresses the problem of preserving the properties of semantic hierarchies while they are being transformed and the problem of changing the granularity of a WordNet-like database. The paper outlines the syntax and semantics of the WUpdate language and describes the underlying data model. Alternative approaches that may be undertaken to modify a WordNet-like database are discussed.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
The paper presents WUpdate – a data manipulation language designed for WordNet-like lexical databases. The language can be used to perform modifications of a wordnet, such as adding word senses, removing words, interlinking synsets, etc. The focus of the paper is on solving wordnet-specific problems that are not addressed by other data manipulation languages. In particular, the paper addresses the problem of preserving the properties of semantic hierarchies while they are being transformed and the problem of changing the granularity of a WordNet-like database. The paper outlines the syntax and semantics of the WUpdate language and describes the underlying data model. Alternative approaches that may be undertaken to modify a WordNet-like database are discussed. |
2012
|
Kubis, Marek A Query Language for WordNet-like Lexical Databases Incollection Pan, Jeng-Shyang; Chen, Shyi-Ming; Nguyen, Ngoc-Thanh (Ed.): Intelligent Information and Database Systems, 7198 , pp. 436–445, Springer Heidelberg, 2012, ISBN: 978-3-642-28492-2. Abstract | Links | BibTeX @incollection{Kubis12,
title = {A Query Language for WordNet-like Lexical Databases},
author = {Marek Kubis},
editor = {Jeng-Shyang Pan and Shyi-Ming Chen and Ngoc-Thanh Nguyen},
url = {http://mkubis.home.amu.edu.pl/aciids2012.pdf
https://link.springer.com/chapter/10.1007/978-3-642-28493-9_46},
doi = {10.1007/978-3-642-28493-9_46},
isbn = {978-3-642-28492-2},
year = {2012},
date = {2012-03-19},
booktitle = {Intelligent Information and Database Systems},
volume = {7198},
pages = {436--445},
publisher = {Springer Heidelberg},
series = {Lecture Notes in Artificial Intelligence},
abstract = {WordNet-like lexical databases are used in many natural language processing tasks, such as word sense disambiguation, information extraction and sentiment analysis. The paper discusses the problem of querying such databases. The types of queries specific to WordNet-like databases are analyzed and previous approaches that were undertaken to query wordnets are discussed. A query language which incorporates data types and syntactic constructs based on concepts that form the core of a WordNet-like database (synsets, word senses, semantic relations, etc.) is proposed as a new solution to the problem of querying wordnets.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
WordNet-like lexical databases are used in many natural language processing tasks, such as word sense disambiguation, information extraction and sentiment analysis. The paper discusses the problem of querying such databases. The types of queries specific to WordNet-like databases are analyzed and previous approaches that were undertaken to query wordnets are discussed. A query language which incorporates data types and syntactic constructs based on concepts that form the core of a WordNet-like database (synsets, word senses, semantic relations, etc.) is proposed as a new solution to the problem of querying wordnets. |
2011
|
Kubis, Marek An Access Layer to PolNet – Polish WordNet Incollection Vetulani, Zygmunt (Ed.): Human Language Technology. Challenges for Computer Science and Linguistics, 6562 , pp. 444–455, Springer Berlin / Heidelberg, 2011, ISBN: 978-3-642-20094-6. Abstract | Links | BibTeX @incollection{Kubis11,
title = {An Access Layer to PolNet – Polish WordNet},
author = {Marek Kubis},
editor = {Zygmunt Vetulani},
url = {http://mkubis.home.amu.edu.pl/ltc2009lnai.pdf
https://link.springer.com/chapter/10.1007/978-3-642-20095-3_41},
doi = {10.1007/978-3-642-20095-3_41},
isbn = {978-3-642-20094-6},
year = {2011},
date = {2011-01-01},
booktitle = {Human Language Technology. Challenges for Computer Science and Linguistics},
volume = {6562},
pages = {444--455},
publisher = {Springer Berlin / Heidelberg},
series = {Lecture Notes in Computer Science},
abstract = {The paper describes an access layer developed in order to provide access to PolNet (a lexical database developed for the Polish language). The access layer was developed on top of a domain-specific language designed to query WordNet-like lexical databases (WQuery). The paper presents the overall architecture of the access layer and shows typical queries passed by an AI system with NL competence (POLINT-112-SMS) to WQuery. The paper discusses the reasons for integrating an ontology into an NLP system through a domain-specific query language.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
The paper describes an access layer developed in order to provide access to PolNet (a lexical database developed for the Polish language). The access layer was developed on top of a domain-specific language designed to query WordNet-like lexical databases (WQuery). The paper presents the overall architecture of the access layer and shows typical queries passed by an AI system with NL competence (POLINT-112-SMS) to WQuery. The paper discusses the reasons for integrating an ontology into an NLP system through a domain-specific query language. |
