Papers by Jonas Kuhn

25 papers
DEbateNet-mig15:Tracing the 2015 Immigration Debate in Germany Over Time (2020.lrec-1)

Copied to clipboard

Challenge: a dataset for germany covering the public debate on immigration is annotated . a political science notion of a claim is used to represent the political discourse .
Approach: They annotate a dataset for german public debate on immigration in 2015 using a political science notion of a claim . they identify claims in newspaper articles, assign them to actors and fine-grained categories and annotize their polarity and date.
Outcome: The dataset is annotated by a political science framework and shows it captures political debate . it shows that political actors can change their positions and take a strong stand against them .
CCOHA: Clean Corpus of Historical American English (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods to model language change in diachronic studies have been used to overcome its limitations.
Approach: They propose to use the corpus of historical american english to overcome its limitations . they use a downloadable version of the corpora to remove inconsistent lemmas and malformed tokens .
Outcome: The proposed corpus overcomes its main limitations without compromising its qualitative and distributional properties.
Lexical Semantic Change Discovery (2021.acl-long)

Copied to clipboard

Challenge: Existing approaches to Lexical Semantic Change Detection are limited.
Approach: They propose a shift from change detection to change discovery by fine-tuning a type-based and a token-based approach on recently published German data.
Outcome: The proposed models can be applied to discover new words undergoing meaning change from the full corpus vocabulary.
Modeling Sense Structure in Word Usage Graphs with the Weighted Stochastic Block Model (2021.starsem-1)

Copied to clipboard

Challenge: Word Usage Graphs capture fine-grained semantic proximity distinctions between word uses.
Approach: They propose to model word use Graphs using a Bayesian weighted stochastic block model and a probabilistic weightes-based model to capture fine-grained semantic proximity distinctions between word uses.
Outcome: The proposed model is compared with existing models and is empirically most adequate.
Investigating Active Learning Sampling Strategies for Extreme Multi Label Text Classification (2022.lrec-1)

Copied to clipboard

Challenge: Large scale, multi-label text datasets with high numbers of different classes are expensive to annotate due to domain experts taking a lot of time working through all the classes.
Approach: They propose to build classifiers on multi-label text datasets using Active Learning to reduce labeling effort.
Outcome: The proposed classifiers can be used to reduce labeling effort on multi-label datasets.
»textklang« – Towards a Multi-Modal Exploration Platform for German Poetry (2022.lrec-1)

Copied to clipboard

Challenge: »textklang« aims to explore the relationship between written text and its potential and actual sonic realisation in lyric poetry . the platform will combine three modalities: the poetic text, the audio signal of a recorded recitation and, at a later stage, music scores of . musical setting of lyrical poetry.
Approach: They propose to combine a multi-modal corpus of German lyric poetry from the Romantic era with a platform for systematic exploration.
Outcome: The platform will combine the poetic text, the audio signal of a recorded recitation and, at a later stage, music scores of . a musical setting of lyric poetry.
Improving Neural Political Statement Classification with Class Hierarchical Information (2022.findings-acl)

Copied to clipboard

Challenge: skewed classification of fine-grained categories in text-based computational social science is challenging on the NLP side.
Approach: They propose to use hierarchical relations among categories in codebooks to create constraints on the learned model.
Outcome: The proposed model improves on two datasets and multiple languages.
GRAIN-S: Manually Annotated Syntax for German Interviews (2020.lrec-1)

Copied to clipboard

Challenge: GRAIN-S is a set of manually created syntactic annotations for radio interviews in germany.
Approach: They propose to use GRAIN-S to create syntactic annotations for radio interviews in germany.
Outcome: The proposed dataset extends an existing corpus GRAIN and comes with constituency and dependency trees for six interviews.
Evaluating Pre-Trained Sentence-BERT with Class Embeddings in Active Learning for Multi-Label Text Classification (2022.aacl-short)

Copied to clipboard

Challenge: Existing Active Learning strategies for pre-trained transformer language models are limited and do not work well on domain-specific datasets.
Approach: They employ pre-trained transformer sentence embeddings to group samples with the same labels in the embeddable space on a legal document corpus.
Outcome: The proposed method performs significantly worse than baselines on two domain-specific datasets.
A Lightweight Modeling Middleware for Corpus Processing (L18-1)

Copied to clipboard

Challenge: Present-day empirical research in computational or theoretical linguistics has richly annotated and diverse corpus resources.
Approach: They propose a framework for modeling arbitrary multi-modal corpus resources in a unified form for processing tools.
Outcome: The proposed framework allows researchers to explore and query more diverse corpus resources and artifacts through a single interactive interface.
Who Sides with Whom? Towards Computational Construction of Discourse Networks for Political Debates (P19-1)

Copied to clipboard

Challenge: a vision of computational construction of discourse networks from newspaper reports is essential for understanding democratic political decision making.
Approach: They propose to use a requirements analysis and an annotated pilot corpus of migration claims to build a computationally-based model of political debates from newspaper reports.
Outcome: The proposed framework could be scaled up to a large scale and be useful for political scientists.
Reinforced Active Learning for Low-Resource, Domain-Specific, Multi-Label Text Classification (2023.findings-acl)

Copied to clipboard

Challenge: Modern text classification systems achieve excellent accuracy across tasks and corpora.
Approach: They propose a Reinforcement Learning policy that uses many different aspects of the data and task to select the most informative unlabeled subset dynamically over the course of the AL procedure.
Outcome: The proposed framework outperforms baselines on four complex multi-class, multi-label text classification datasets.
Fast and Accurate Non-Projective Dependency Tree Linearization (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for decoding dependency trees are 10 times faster than current ones.
Approach: They propose a graph-based method to tackle a dependency tree linearization task . they propose to solve a Traveling Salesman Problem and combine the solution into a projective tree .
Outcome: The proposed method outperforms the state-of-the-art linearizer while being 10 times faster in training and decoding.
Moving TIGER beyond Sentence-Level (L18-1)

Copied to clipboard

Challenge: TIGER 2.2-doc is a new set of annotations for the German TIger corpus.
Approach: They propose a new set of annotations for the German TIGER corpus . they introduce new document-level annotations: authors and their gender.
Outcome: The new annotations improve the TIGER corpus and its structure and authors and gender.
An Environment for Relational Annotation of Political Debates (P19-3)

Copied to clipboard

Challenge: Scalable text analysis techniques can open corpora to new questions in computational social sciences and digital humanities.
Approach: They describe a tool that allows annotating newspaper text with rich information about claims (demands) raised by politicians and other actors.
Outcome: The MARDY tool realizes the complete workflow necessary for annotating a large newspaper text collection with rich information about claims (demands) raised by politicians and other actors.
Polyglot Semantic Parsing in APIs (N18-1)

Copied to clipboard

Challenge: Existing approaches to semantic parsing work by training individual models for each available parallel dataset of text-meaning pairs.
Approach: They propose a polyglot semantic translation approach that trains on multiple datasets and natural languages to learn parsing models.
Outcome: The proposed model can be used for parsing a wide variety of natural languages and output languages, and achieves state-of-the-art performance on the above datasets.
German Radio Interviews: The GRAIN Release of the SFB732 Silver Standard Collection (L18-1)

Copied to clipboard

Challenge: GRAIN contains German radio interviews and is annotated on multiple linguistic layers.
Approach: They present GRAIN as part of the SFB732 Silver Standard Collection . GRAIN contains German radio interviews and is annotated on multiple linguistic layers .
Outcome: The GRAIN data set contains German radio interviews and is annotated on multiple linguistic layers.
The (Non-)Utility of Structural Features in BiLSTM-based Dependency Parsers (P19-1)

Copied to clipboard

Challenge: Existing non-neural dependency parsers benefit from information coming from structural features . however, their successors lack explicit information about the structural context .
Approach: They propose to model the structural context of a biLSTM-based dependency parser with features built from partial subtrees.
Outcome: The proposed models do not use any conventional structural features but capture implicitly the structural context.
Explaining and Improving BERT Performance on Lexical Semantic Change Detection (2021.eacl-srw)

Copied to clipboard

Challenge: Lexical semantic change detection is still a challenging field due to the success of type-based embeddings in SemEval-2020 Task 1 and other NLP tasks.
Approach: They compare the performance of BERT embeddings with results from the word sense disambiguation dataset underlying SemEval-2020 Task 1 and the Italian follow-up task DIACR-Ita.
Outcome: The proposed model outperforms token-based embeddings on lexical semantic change detection tasks.
IMSurReal: IMS at the Surface Realization Shared Task 2019 (D19-63)

Copied to clipboard

Challenge: a system for shallow and deep completion is presented for the Surface Realization Shared Task 2019 . the system achieves state-of-the-art performance without using external data.
Approach: They propose a surface realization system that takes five steps without external data . they perform detailed error analysis revealing correlation between word order freedom and difficulty .
Outcome: The proposed system achieves state-of-the-art without external data . it achieves highest BLEU scores on tokenized text and human evaluation on four languages .
Compound or Term Features? Analyzing Salience in Predicting the Difficulty of German Noun Compounds across Domains (2021.starsem-1)

Copied to clipboard

Challenge: Using domain-specific vocabulary, it is important to analyse domain-related characteristics to improve the communication between lay people and experts.
Approach: They focus on the interaction of compound-based lexical features (such as frequency and productivity) and terminology-based features (contrasting domain-specific and general language) across word representations and classifiers.
Outcome: The proposed model shows that the interaction of compound-based lexical features and terminology-based features across word representations and classifiers is important for a broad binary distinction into ‘easy’ vs. ‘difficult’ general-language compound frequency is sufficient, but for . a more fine-grained four-class distinction it is crucial to include contrastive termhood features and compound and constituent features.
Bridging resolution: Task definition, corpus resources and rule-based experiments (C18-1)

Copied to clipboard

Challenge: Recent work on bridging resolution has been based on the corpus ISNotes, as this was the only corpus available with unrestricted bridling annotations.
Approach: They propose a rule-based system to resolve bridging annotations in ISNotes corpus and apply it to new corpora.
Outcome: The proposed system achieves state-of-the-art performance on ISNotes corpus, but low performance on in-domain corpora.
The DURel Annotation Tool: Human and Computational Measurement of Semantic Proximity, Sense Clusters and Semantic Change (2024.eacl-demo)

Copied to clipboard

Challenge: DURel is an open source tool for semantic proximity between word uses.
Approach: They present an open-source tool for the annotation of semantic proximity between word uses.
Outcome: The proposed tool supports standardized human annotation and computational annotation, building on recent advances with Word-in-Context models.
Real-Valued Logics for Typological Universals: Framework and Application (2020.coling-main)

Copied to clipboard

Challenge: a framework for typological statements captures the truth value of a formula on a given data source.
Approach: They propose a framework which captures the empirical truth value of a formula on a given data source.
Outcome: The proposed framework can be used to express typological statements on multilingual treebanks with comparable annotation.
NLATool: an Application for Enhanced Deep Text Understanding (C18-2)

Copied to clipboard

Challenge: a wide range of subfields in natural language processing see systems solving their tasks with sufficiently high-quality levels.
Approach: They propose a web application that supports text annotation and enriches the text with additional information from a number of sources directly within the application.
Outcome: The proposed web application is based on a human-centered design process . it offers a rich visualization of texts and the entities mentioned in them through an easy to use interface.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations