1 |
Extraction of transforming sequences and sentence histories from writing process data : a first step towards linguistic modeling of writing ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Are we summarizing the right way? : a survey of dialogue summarization data sets ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
The Sentence End and Punctuation Prediction in NLG text (SEPP-NLG) shared task 2021 ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Are We Summarizing the Right Way? A Survey of Dialogue Summarization Data Sets ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
University of Regensburg @ SwissText 2021 SEPP-NLG: Adding Sentence Structure to Unpunctuated Text
|
|
|
|
Abstract:
This paper describes our approach (UR- mSBD) to address the shared task on Sentence End and Punctuation Prediction in NLG Text (SEPP-NLG) organised as part of SwissText 2021. We participated in Subtask 1 (fully un- punctuated sentences – full stop detection) and submitted a run for every featured language (English, German, French, Italian). Our sub- missions are based on pre-trained BERT mod- els that have been fine-tuned to the task at hand. We had recently demonstrated, that such an ap- proach achieves state-of-the-art performance when identifying end-of-sentence markers on automatically transcribed texts. The difference to that work is that here we use language- specific BERT models for each featured lan- guage. By framing the problem as a binary tagging task using the outlined architecture we are able to achieve competitive results on the official test set across all languages, with Re- call, Precision, F1 ranging between 0.91 and 0.96 which makes us joint winners for Recall in two of the languages. The official baselines are beaten by large margins.
|
|
Keyword:
020 Bibliotheks- und Informationswissenschaft; ddc:020
|
|
URL: https://epub.uni-regensburg.de/49352/1/sepp_paper5.pdf https://epub.uni-regensburg.de/49352/ http://ceur-ws.org/Vol-2957/
|
|
BASE
|
|
Hide details
|
|
6 |
Spot The Bot : a robust and efficient framework for the evaluation of conversational dialogue systems ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
German compound splitting using the compound productivity of morphemes ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Co-reference Resolution of Elided Subjects and Possessive Pronouns in Spanish-English Statistical Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Machine Translation of Spanish Personal and Possessive Pronouns Using Anaphora Probabilities ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
A method for in-depth comparative evaluation: How (dis)similar are outputs of POS taggers, dependency parsers and coreference resolvers really? ...
|
|
Tuggener, Don. - : Association for Computational Linguistics, 2017
|
|
BASE
|
|
Show details
|
|
11 |
Co-reference Resolution of Elided Subjects and Possessive Pronouns in Spanish-English Statistical Machine Translation
|
|
|
|
In: Rios, Annette; Tuggener, Don (2017). Co-reference Resolution of Elided Subjects and Possessive Pronouns in Spanish-English Statistical Machine Translation. In: 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, 3 April 2017 - 7 April 2017. Association for Computational Linguistics, 657-662. (2017)
|
|
BASE
|
|
Show details
|
|
12 |
A method for in-depth comparative evaluation: How (dis)similar are outputs of POS taggers, dependency parsers and coreference resolvers really?
|
|
|
|
In: Tuggener, Don (2017). A method for in-depth comparative evaluation: How (dis)similar are outputs of POS taggers, dependency parsers and coreference resolvers really? In: 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain, 3 April 2017 - 7 April 2017. Association for Computational Linguistics, 188-198. (2017)
|
|
BASE
|
|
Show details
|
|
13 |
Coreference resolution evaluation for higher level applications ...
|
|
Tuggener, Don. - : Association for Computational Linguistics, 2014
|
|
BASE
|
|
Show details
|
|
14 |
A Hybrid Entity-Mention Pronoun Resolution Model for German Using Markov Logic Networks
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Coreference resolution evaluation for higher level applications
|
|
|
|
In: Tuggener, Don (2014). Coreference resolution evaluation for higher level applications. In: 14th Conference of the European Chapter of the Association for Computational Linguistics, Gothenburg, Sweden, 26 April 2014 - 30 April 2014. Association for Computational Linguistics, 231-235. (2014)
|
|
BASE
|
|
Show details
|
|
16 |
A Hybrid Entity-Mention Pronoun Resolution Model for German Using Markov Logic Networks
|
|
|
|
In: Tuggener, Don; Klenner, Manfred (2014). A Hybrid Entity-Mention Pronoun Resolution Model for German Using Markov Logic Networks. In: KONVENS 2014, Hildesheim, 8 October 2014 - 10 October 2014, 21-29. (2014)
|
|
BASE
|
|
Show details
|
|
18 |
UZH in BioNLP 2013
|
|
|
|
In: Schneider, Gerold; Clematide, Simon; Ellendorff, Tilia; Tuggener, Don; Rinaldi, Fabio; Grigonyte, Gintare (2013). UZH in BioNLP 2013. In: Proceedings of the BioNLP Shared Task 2013 Workshop, Sophia, Bulgaria, 9 August 2013 - 9 August 2013, 116-120. (2013)
|
|
BASE
|
|
Show details
|
|
|
|