Search Results for author:
Found 34 papers, 6 papers with code
Evaluation of Transfer Learning and Domain Adaptation for Analyzing German-Speaking Job Advertisements
Our main contribution consists in building language models which are adapted to the domain of job advertisements, and their assessment on a broad range of machine learning problems.
CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation
We report competitive results for morpheme segmentation (including sharing first place in part 2 of the challenge).
Ranked #3 on
Morpheme Segmentaiton
on UniMorph 4.0
(f1 macro avg (subtask 2) metric)
On Isotropy Calibration of Transformer Models
Different studies of the embedding space of transformer models suggest that the distribution of contextual representations is highly anisotropic - the embeddings are distributed in a narrow cone.
Results of the Second SIGMORPHON Shared Task on Multilingual Grapheme-to-Phoneme Conversion
Grapheme-to-phoneme conversion is an important component in many speech technologies, but until recently there were no multilingual benchmarks for this task.
CLUZH at SIGMORPHON 2021 Shared Task on Multilingual Grapheme-to-Phoneme Conversion: Variations on a Baseline
This paper describes the submission by the team from the Department of Computational Linguistics, Zurich University, to the Multilingual Grapheme-to-Phoneme Conversion (G2P) Task 1 of the SIGMORPHON 2021 challenge in the low and medium settings.
Text Zoning and Classification for Job Advertisements in German, French and English
We present experiments to structure job ads into text zones and classify them into pro- fessions, industries and management functions, thereby facilitating social science analyses on labor marked demand.
Searching for Legal Documents at Paragraph Level: Automating Label Generation and Use of an Extended Attention Mask for Boosting Neural Models of Semantic Similarity
For this domain, we formulated a task to compare different ways of modeling semantic similarity at paragraph level, using neural and non-neural systems.
Automatic Generation and Evaluation of Reading Comprehension Test Items with Large Language Models
We then used this protocol and the dataset to evaluate the quality of items generated by Llama 2 and GPT-4.
UZH_CLyp at SemEval-2023 Task 9: Head-First Fine-Tuning and ChatGPT Data Generation for Cross-Lingual Learning in Tweet Intimacy Prediction
This paper describes the submission of UZH_CLyp for the SemEval 2023 Task 9 "Multilingual Tweet Intimacy Analysis".
Transformer-based HTR for Historical Documents
We apply the TrOCR framework to real-world, historical manuscripts and show that TrOCR per se is a strong model, ideal for transfer learning.
Evaluation of HTR models without Ground Truth Material
The evaluation of Handwritten Text Recognition (HTR) models during their development is straightforward: because HTR is a supervised problem, the usual data split into training, validation, and test data sets allows the evaluation of models in terms of accuracy or error rates.
On Isotropy Calibration of Transformers
Different studies of the embedding space of transformer models suggest that the distribution of contextual representations is highly anisotropic - the embeddings are distributed in a narrow cone.
Semi-supervised Contextual Historical Text Normalization
Historical text normalization, the task of mapping historical word forms to their modern counterparts, has recently attracted a lot of interest (Bollmann, 2019; Tang et al., 2018; Lusetti et al., 2018; Bollmann et al., 2018;Robertson and Goldwater, 2018; Bollmannet al., 2017; Korchagina, 2017).
CLUZH at SIGMORPHON 2020 Shared Task on Multilingual Grapheme-to-Phoneme Conversion
The submission adapts our system from the 2018 edition of the SIGMORPHON shared task.
How Much Data Do You Need? About the Creation of a Ground Truth for Black Letter and the Effectiveness of Neural OCR
Recent advances in Optical Character Recognition (OCR) and Handwritten Text Recognition (HTR) have led to more accurate textrecognition of historical documents.
Language Resources for Historical Newspapers: the Impresso Collection
If this represents a huge step forward in terms of preservation and accessibility, the next fundamental challenge{--} and real promise of digitization{--} is to exploit the contents of these digital assets, and therefore to adapt and develop appropriate language technologies to search and retrieve information from this {`}Big Data of the Past{'}.
Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers
The massive amounts of digitized historical documents acquired over the last decades naturally lend themselves to automatic processing and exploration.
Geotagging a Diachronic Corpus of Alpine Texts: Comparing Distinct Approaches to Toponym Recognition
Geotagging historic and cultural texts provides valuable access to heritage data, enabling location-based searching and new geographically related discoveries.
Imitation Learning for Neural Morphological String Transduction
We employ imitation learning to train a neural transition-based string transducer for morphological tasks such as inflection generation and lemmatization.
Neural Transition-based String Transduction for Limited-Resource Setting in Morphology
We present a neural transition-based model that uses a simple set of edit actions (copy, delete, insert) for morphological transduction tasks such as inflection generation, lemmatization, and reinflection.
Align and Copy: UZH at SIGMORPHON 2017 Shared Task for Morphological Reinflection
The second approach is a neural state-transition system over a set of explicit edit actions, including a designated COPY action.
CLUZH at VarDial GDI 2017: Testing a Variety of Machine Learning Tools for the Classification of Swiss German Dialects
Measured by classification accuracy, our ensemble run (Na{\"\i}ve Bayes, CRF, SVM) reaches 67{\%} (second rank) being 1{\%} lower than the best system.
Stance Detection in Facebook Posts of a German Right-wing Party
We argue that in order to detect stance, not only the explicit attitudes of the stance holder towards the targets are crucial.
Crowdsourcing an OCR Gold Standard for a German and French Heritage Corpus
Crowdsourcing approaches for post-correction of OCR output (Optical Character Recognition) have been successfully applied to several historic text collections.
Optical Character Recognition
Optical Character Recognition (OCR)
Collaboratively Annotating Multilingual Parallel Corpora in the Biomedical Domain---some MANTRAs
The coverage of multilingual biomedical resources is high for the English language, yet sparse for non-English languages―an observation which holds for seemingly well-resourced, yet still dramatically low-resourced ones such as Spanish, French or German but even more so for really under-resourced ones such as Dutch.
Using Large Biomedical Databases as Gold Annotations for Automatic Relation Extraction
We show how to use large biomedical databases in order to obtain a gold standard for training a machine learning system over a corpus of biomedical text.
MLSA --- A Multi-layered Reference Corpus for German Sentiment Analysis
The construction of the corpus is based on the manual annotation of 270 German-language sentences considering three different layers of granularity.
Dependency parsing for interaction detection in pharmacogenomics
We give an overview of our approach to the extraction of interactions between pharmacogenomic entities like drugs, genes and diseases and suggest classes of interaction types driven by data from PharmGKB and partly following the top level ontology WordNet and biomedical types from BioNLP.
