Before becoming an academic, I worked for two years with the SDS-940 timesharing system, fifteen years with the PDP-10 timesharing system, and eight years with Data General office management software. DG nearly put me through grad school, and after I left there I completed my dissertation at WPI.
Because of this long commercial experience programming in assembler, PL-1, and C, I tend to focus on solutions which maximize the limited resources that computers still provide.
In the thirty years since I received my Ph.D. I have taught at WPI, Holy Cross, and Fitchburg State College in the US, at UAE University, Birzeit University, and Yarmouk University in the Middle East, and I am currently a researcher in the Natural Language Processing Group at the University of West Bohemia, where I have been since 2017.
EDUCATION
AB 1968 Harvard College
PhD 1995 Worcester Polytechnic Institute
RESEARCH, TEACHING, or OTHER INTERESTS
Artificial Intelligence, Speech and Hearing, Signal Processing, Language and Linguistics
UWB@RuShiftEval Measuring Semantic Difference as per-word Variation in Aligned Semantic Spaces P. Pribán, O. Pražák, S. E. Taylor, and Komp Juternaja Lingvistika I Intellektual Nye Tehnologii, 2021 We present our system for measuring the lexical semantic change between corpora pairs, developed for the RuShiftEval competition. We measure semantic changes in a list of test words between three different corpora (for each pair), pre-Soviet , Soviet
UWB @ DIACR-Ita: Lexical semantic change detection with CCA and orthogonal transformation Ondřej Pražák, Pavel Přibáň, Stephen Taylor Ceur Workshop Proceedings, 2020 In this paper, we describe our method for detection of lexical semantic change (i.e., word sense changes over time) for the DIACR-Ita shared task, where we ranked 1st. We examine semantic differences between specific words in two Italian corpora, chosen from different time periods. Our method is fully unsupervised and language independent. It consists of preparing a semantic vector space for each corpus, earlier and later. Then we compute a linear transformation between earlier and later spaces, using CCA and Orthogonal Transformation. Finally, we measure the cosines between the transformed vectors.
UWB at SemEval-2020 Task 1: Lexical Semantic Change Detection Ondřej Pražák, Pavel Přibáň, Stephen Taylor, Jakub Sido 14th International Workshops on Semantic Evaluation Semeval 2020 Co Located 28th International Conference on Computational Linguistics Coling 2020 Proceedings, 2020
The representation of some phrases in Arabic word semantic vector spaces Stephen Taylor, Tomáš Brychcín Open Computer Science, 2018 We demonstrate several ways to use morphological word analogies to examine the representation of complex words in semantic vector spaces. We present a set of morphological relations, each of which can be used to generate many word analogies. 1. We show that the difference-vectors for pairs which have the same relation to each other are similarly aligned. 2. We suggest that addition of difference-vectors is a useful phrase-building operator. 3. We propose that pairs in the same relation may have similar relative frequencies. 4. We suggest that homographs, which necessarily have the same semantic vectors, can sometimes be separated into different vectors for different senses, using frequency estimates and alignment constraints obtained from word analogies. 5. We observe that some of our analogies seem to be parallel, and might be combined. We use Arabic words as a case study, because Arabic orthography includes verb conjugations, object pronouns, definitive articles, possessive pronouns, and some prepositions in single word-forms. Therefore, a number of short phrases, built up of easily perceived constituents, are already present in stock semantic spaces for Arabic available on the web. Similar phrases in English would require including bigrams or trigrams as lemmas in the word embedding, although English derivational morphology allows for other relationships in standard semantic spaces which Arabic does not, for example negation. We make our corpus of morphological relations available to other researchers.
Palestinian Arabic regional accent recognition Abualsoud Hanani, Hanna Basha, Yasmeen Sharaf, Stephen Taylor 2015 International Conference on Speech Technology and Human Computer Dialogue Sped 2015, 2015
Approximate query answering in numerical databases Scientific and Statistical Database Management Proceedings of the International Working Conference, 1996
BASIC COMPILER SYSTEM. Proc of the Digital Equip Comput Users Soc, 1977
RECENT SCHOLAR PUBLICATIONS
Polymeric composition for use in electroless plating, method of elecroless plating, and polymeric article made by electroless plating C Wan, S Taylor, B Zhou, J Eshenaur, RR Gallucci, J Xu US Patent App. 17/768,969 , 2024 2024
UWB at Arabic Reverse Dictionary shared task: Computing the meaning of a gloss S Taylor Proceedings of ArabicNLP 2023, 461-466 , 2023 2023 Citations: 1
UWB at KSAA-RD shared task: Computing the meaning of a gloss S Taylor Association for Computational Linguistics , 2023 2023
CompareWords: Measuring semantic change in word usage in different corpora S Taylor, P Přibáň, O Pražák Software Impacts 8, 100067 , 2021 2021 Citations: 3
UWB@ RuShiftEval Measuring Semantic Difference as per-word Variation in Aligned Semantic Spaces P Přibáň Russian State University for the Humanities , 2021 2021 Citations: 2
UWB at SemEval-2020 task 1: Lexical semantic change detection O Pražák, P Přibáň, S Taylor, J Sido Proceedings of the Fourteenth Workshop on Semantic Evaluation, 246-254 , 2020 2020 Citations: 41
UWB@ DIACR-Ita: Lexical Semantic Change Detection with CCA and Orthogonal Transformation O Pražák, P Přibáň, S Taylor arXiv preprint arXiv:2011.14678 , 2020 2020 Citations: 10
Is There a Linear Subspace in which the Difference Vectors of Word Analogy Pairs are Parallel?. S Taylor, T Brychcín Res. Comput. Sci. 148 (12), 127-139 , 2019 2019
Cross-lingual word analogies using linear transformations between semantic spaces T Brychcín, S Taylor, L Svoboda Expert Systems with Applications 135, 287-295 , 2019 2019 Citations: 34
Zcu-nlp at madar 2019: Recognizing arabic dialects P Přibáň, S Taylor Proceedings of the fourth arabic natural language processing workshop, 208-213 , 2019 2019 Citations: 9
The representation of some phrases in Arabic word semantic vector spaces S Taylor, T Brychcín Open Computer Science 8 (1), 182-193 , 2018 2018 Citations: 4
Arabic word analogies and semantics of simple phrases S Taylor, T Brychcín 2018 2nd International Conference on Natural Language and Speech Processing … , 2018 2018 Citations: 8
Identifying dialects with textual and acoustic cues A Hanani, A Qaroush, S Taylor Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties … , 2017 2017 Citations: 19
Classifying ASR transcriptions according to Arabic dialect A Hanani, A Qaroush, S Taylor Proceedings of the Third Workshop on NLP for Similar Languages, Varieties … , 2016 2016 Citations: 12
Automatic Identification of Articulation Disorders for Arabic Children Speakers. A Hanani, M Attari, A Atta'Farakhna, JA Aseel, M Hussein, S Taylor WOCCI, 35-39 , 2016 2016 Citations: 16
Palestinian Arabic regional accent recognition A Hanani, H Basha, Y Sharaf, S Taylor 2015 International Conference on Speech Technology and Human-Computer … , 2015 2015 Citations: 21
Morphological Analysis of Arabic dialect Transcriptions S Taylor Fourth International Arabic Linguistics Symposium, Alexandria, Egypt , 2010 2010
FSC at TREC. S Taylor, O Montalvo-Huhn, N Kartha TREC , 2007 2007
Comparing Frequencies of Lexical Productions in Arabic Words S Taylor Perspectives in Arabic Linguistics XV, 181-190 , 2003 2003 Citations: 1
Emerging behavior as binary search trees are symmetrically updated S Taylor, M Durand Theoretical Computer Science 297, 425 - 445 , 2003 2003
MOST CITED SCHOLAR PUBLICATIONS
UWB at SemEval-2020 task 1: Lexical semantic change detection O Pražák, P Přibáň, S Taylor, J Sido Proceedings of the Fourteenth Workshop on Semantic Evaluation, 246-254 , 2020 2020 Citations: 41
Cross-lingual word analogies using linear transformations between semantic spaces T Brychcín, S Taylor, L Svoboda Expert Systems with Applications 135, 287-295 , 2019 2019 Citations: 34
Palestinian Arabic regional accent recognition A Hanani, H Basha, Y Sharaf, S Taylor 2015 International Conference on Speech Technology and Human-Computer … , 2015 2015 Citations: 21
Identifying dialects with textual and acoustic cues A Hanani, A Qaroush, S Taylor Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties … , 2017 2017 Citations: 19
Automatic Identification of Articulation Disorders for Arabic Children Speakers. A Hanani, M Attari, A Atta'Farakhna, JA Aseel, M Hussein, S Taylor WOCCI, 35-39 , 2016 2016 Citations: 16
Classifying ASR transcriptions according to Arabic dialect A Hanani, A Qaroush, S Taylor Proceedings of the Third Workshop on NLP for Similar Languages, Varieties … , 2016 2016 Citations: 12
UWB@ DIACR-Ita: Lexical Semantic Change Detection with CCA and Orthogonal Transformation O Pražák, P Přibáň, S Taylor arXiv preprint arXiv:2011.14678 , 2020 2020 Citations: 10
Zcu-nlp at madar 2019: Recognizing arabic dialects P Přibáň, S Taylor Proceedings of the fourth arabic natural language processing workshop, 208-213 , 2019 2019 Citations: 9
Arabic word analogies and semantics of simple phrases S Taylor, T Brychcín 2018 2nd International Conference on Natural Language and Speech Processing … , 2018 2018 Citations: 8
A Direct Algorithm for Computing the Transitive Closure of a Two-Dimensionally Structured File S Taylor, N Hachem Proceedings of the Mathematical Foundations for Database Systems Symposium … , 1991 1991 Citations: 7
The representation of some phrases in Arabic word semantic vector spaces S Taylor, T Brychcín Open Computer Science 8 (1), 182-193 , 2018 2018 Citations: 4
CompareWords: Measuring semantic change in word usage in different corpora S Taylor, P Přibáň, O Pražák Software Impacts 8, 100067 , 2021 2021 Citations: 3
Emerging behavior as binary search trees are symmetrically updated S Taylor Latin American Symposium on Theoretical Informatics, 78-87 , 2000 2000 Citations: 3
UWB@ RuShiftEval Measuring Semantic Difference as per-word Variation in Aligned Semantic Spaces P Přibáň Russian State University for the Humanities , 2021 2021 Citations: 2
UWB at Arabic Reverse Dictionary shared task: Computing the meaning of a gloss S Taylor Proceedings of ArabicNLP 2023, 461-466 , 2023 2023 Citations: 1
Comparing Frequencies of Lexical Productions in Arabic Words S Taylor Perspectives in Arabic Linguistics XV, 181-190 , 2003 2003 Citations: 1
Polymeric composition for use in electroless plating, method of elecroless plating, and polymeric article made by electroless plating C Wan, S Taylor, B Zhou, J Eshenaur, RR Gallucci, J Xu US Patent App. 17/768,969 , 2024 2024
UWB at KSAA-RD shared task: Computing the meaning of a gloss S Taylor Association for Computational Linguistics , 2023 2023
Is There a Linear Subspace in which the Difference Vectors of Word Analogy Pairs are Parallel?. S Taylor, T Brychcín Res. Comput. Sci. 148 (12), 127-139 , 2019 2019
Morphological Analysis of Arabic dialect Transcriptions S Taylor Fourth International Arabic Linguistics Symposium, Alexandria, Egypt , 2010 2010
