Papers by Sabine Schulte im Walde

31 papers
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.
Made of Steel? Learning Plausible Materials for Components in the Vehicle Repair Domain (2023.eacl-main)

Copied to clipboard

Challenge: a novel approach to learn domain-specific plausible materials for components in the vehicle repair domain is proposed . connecting a symptom to an underlying cause is a crucial building block for natural language understanding across domains.
Approach: They propose a method to aggregate salient predictions from a set of cloze task style templates and use a Wikipedia corpus to augment the model.
Outcome: The proposed approach outperforms a traditional pattern-based approach by exploiting the compositionality assumption in a cloze task style setting.
A Systematic Search for Compound Semantics in Pretrained BERT Architectures (2023.eacl-main)

Copied to clipboard

Challenge: Existing models for noun compounds have been less successful in predicting compositionality than transformers . authors: suboptimal use of encoded information may be a contributing factor . performance of transformer-based models is poor, authors say .
Approach: They propose to use semantic knowledge derived from pretrained BERT to predict compositionality . they find distinct linguistic roles of heads and modifiers are reflected by differences in BERT representations .
Outcome: The proposed model improves on unsupervised implementations of pretrained BERT . empirical properties such as frequency, productivity, and ambiguity affect performance .
Combining Abstractness and Language-specific Theoretical Indicators for Detecting Non-Literal Usage of Estonian Particle Verbs (N18-4)

Copied to clipboard

Challenge: Existing studies on identifying nonliteral language use have focused on resource-rich languages and focused on general indicators to identify non-literal meaning.
Approach: They propose to use two datasets and a random forest classifier to automatically predict literal vs. non-literal language usage for a highly frequent type of multi-word expression in a low-resource language, i.e., Estonian.
Outcome: The proposed dataset outperforms a high majority baseline when combined with language-independent features of non-literal language.
A Laypeople Study on Terminology Identification across Domains and Task Definitions (N18-2)

Copied to clipboard

Challenge: Existing studies on term annotation show that even experts differ in their understanding of termhood .
Approach: They propose a new dataset of term annotation that examines the common understanding of what constitutes a term.
Outcome: The proposed datasets show that even experts differ in their understanding of termhood . the findings suggest that there is a common understanding of what constitutes a term .
AbsVis – Benchmarking How Humans and Vision-Language Models “See” Abstract Concepts in Images (2025.emnlp-main)

Copied to clipboard

Challenge: Abstract concepts like mercy and peace lack clear visual grounding, and therefore challenge humans and models to provide suitable image representations.
Approach: They propose a dataset of 675 images annotated with 14,175 concept–explanation attributions from humans and two Vision-Language Models where each concept is accompanied by a textual explanation.
Outcome: The proposed dataset compares human and VLM attributions in terms of diversity, abstractness, and alignment, and shows that overlapping concepts are most preferred.
More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods (2021.findings-acl)

Copied to clipboard

Challenge: Using unsupervised methods of hypernymy prediction, we show that the predictions of three methods overlap and are highly correlated with frequency-based predictions.
Approach: They compare unsupervised methods of hypernymy prediction to supervised methods . they show that the methods overlap and are highly correlated with frequency-based predictions .
Outcome: The proposed methods overlap and are highly correlated with frequency-based predictions across English and German datasets.
Variants of Vector Space Reductions for Predicting the Compositionality of English Noun Compounds (2020.lrec-1)

Copied to clipboard

Challenge: Existing approaches to predict the degree of compositionality of noun compounds are based on comparing compounds and their constituents within a vector space and using distributional similarity as a proxy to predict their degree of semantic relatedness.
Approach: They propose to use distributional similarity as a proxy to predict the semantic relatedness between the compounds and their constituents as the compound’s degree of compositionality.
Outcome: The proposed methods are most successful and stable in terms of dimensionality and part-of-speech reductions.
Projecting Embeddings for Domain Adaption: Joint Modeling of Sentiment Analysis in Diverse Domains (C18-1)

Copied to clipboard

Challenge: Existing domain adaptation methods for sentiment analysis are sensitive to domain differences, resulting in classifiers that perform poorly on new domains.
Approach: They propose a domain adaptation problem as an embedding projection task using two mono-domain embeddable spaces and a bi-domain space to project across domains and predict sentiment.
Outcome: The proposed model performs better on domains similar to state-of-the-art methods while requiring longer training times.
VOLIMET: A Parallel Corpus of Literal and Metaphorical Verb-Object Pairs for English–German and English–French (2024.starsem-1)

Copied to clipboard

Challenge: Metaphorical language is a complex interplay of cultural and linguistic elements that characterizes metaphorical language . a corpus of parallel sentences containing gold standard alignments of metaphorical verb-object pairs and literal paraphrases is presented .
Approach: They propose to analyze metaphorical verb-object pairs and literal paraphrases in parallel sentences from English to German and French.
Outcome: The proposed corpus of 2,916 parallel sentences reveals monolingual patterns for metaphorical vs. literal uses in English . cross-lingually, the results show a rich variability in translations as well as different behaviors for the two target languages .
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.
You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP (D19-1)

Copied to clipboard

Challenge: Current approaches to social media modelling ignore the fact that an individual may be part of several communities which are not equally relevant in all communicative situations.
Approach: They propose a model that captures the sociological phenomenon of homophily and combines it with linguistic information to make a prediction.
Outcome: The proposed model significantly outperforms existing models on three different tasks and is compared with other models.
A Domain-Specific Dataset of Difficulty Ratings for German Noun Compounds in the Domains DIY, Cooking and Automotive (2020.lrec-1)

Copied to clipboard

Challenge: a dataset with difficulty ratings for 1,030 closed noun compounds is presented . authors use a simple compound splitter to identify compound types in domain-specific texts .
Approach: They present a German closed noun compound dataset with difficulty ratings . they used a simple compound splitter to identify compounds in texts .
Outcome: The proposed dataset has difficulty ratings for 1,030 closed noun compounds extracted from domain-specific texts for do-it-ourself, cooking and automotive.
Introducing Two Vietnamese Datasets for Evaluating Semantic Models of (Dis-)Similarity and Relatedness (N18-2)

Copied to clipboard

Challenge: Existing datasets for low-resource language Vietnamese assess semantic similarity . a dataset for word pairs with similarity levels is needed to evaluate these models .
Approach: They present two new datasets for the low-resource language Vietnamese to assess models of semantic similarity.
Outcome: The two datasets are comparable to the English datasets.
Features of Perceived Metaphoricity on the Discourse Level: Abstractness and Emotionality (2022.lrec-1)

Copied to clipboard

Challenge: a metaphorical discourse is more emotional and abstract than a literal one, according to a new study . a metaphorical discourse may be more abstract than literal, but it is not triggered by its emotionality or metaphoricity.
Approach: They examine which features human annotators perceive as important for metaphoricity . they ask: is a metaphorical expression preceded by a more metaphorical/abstract/emotional context?
Outcome: The proposed dataset shows that metaphorical discourses are more emotional and abstract than literal ones.
Investigating Independence vs. Control: Agenda-Setting in Russian News Coverage on Social Media (2022.lrec-1)

Copied to clipboard

Challenge: a major challenge in the media industry has always been its targeted manipulation, says a new study . agenda-setting is a well-known phenomenon in political science . authors explore the relationship between economic indicators and mentions of foreign geopolitical entities .
Approach: They investigate agenda-setting in the Russian social media landscape . they explore the relation between economic indicators and mentions of foreign geopolitical entities .
Outcome: The authors examine the relationship between economic indicators and mentions of foreign geopolitical entities, as well as of Russia itself.
To Split or Not to Split: Composing Compounds in Contextual Vector Spaces (2023.emnlp-main)

Copied to clipboard

Challenge: Contextual word embedding models rely on sub-word tokenization to represent single orthographic words but are often suboptimal in under-resourced contexts.
Approach: They propose to use a masked language modelling task to evaluate the model's performance . they use re-trained tokenizers to pre-split compounds into constituents .
Outcome: The proposed models improve on the masked language modelling task and compositionality prediction by pre-splitting compounds into constituents.
DiaWUG: A Dataset for Diatopic Lexical Semantic Variation in Spanish (2022.lrec-1)

Copied to clipboard

Challenge: Existing approaches to dialectology have been limited and rarely address language variation regarding lexical meaning.
Approach: They propose to use existing framework DURel and framework-embedded Word Usage Graphs to distinguish, visualize and interpret diatopic lexical semantic variation of contextualized words in Spanish from these perspectives.
Outcome: The proposed dataset exploits existing frameworks for annotating word senses in context and framework-embedded Word Usage Graphs (WUGs) . it distinguishes, visualizes and interprets lexical semantic variation of contextualized words in Spanish from these two perspectives, i.e., semasiological and onomasiology.
Concreteness vs. Abstractness: A Selectional Preference Perspective (2022.aacl-srw)

Copied to clipboard

Challenge: Using a collection of 5,438 nouns and 1,275 verbs, we exploit selectional preferences as a salient characteristic in classifying abstract vs. concrete words.
Approach: They propose to use selectional preferences as a criterion to distinguish between concrete and abstract concepts and words.
Outcome: The proposed method achieves an f1-score of 0.84 for nouns and 0.71 for verbs in classification and Spearman’s correlation of 0.86 for nonoms and 0.59% for verb.
What Can Diachronic Contexts and Topics Tell Us about the Present-Day Compositionality of English Noun Compounds? (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to determine the semantic relatedness between compounds and constituents have applied a synchronic perspective, but this study examines what diachronic changes in contexts and semantic topics reveal about the compounds’ present-day compositionality.
Approach: They propose to use two diachronic vector spaces to model compositional patterns between compounds with low and high present-day compositionality.
Outcome: The proposed model performs on par with co-occurrence space and captures similar information.
Willkommens-Merkel, Chaos-Johnson, and Tore-Klose: Modeling the Evaluative Meaning of German Personal Name Compounds (2024.lrec-main)

Copied to clipboard

Challenge: Personal name compounds (PNCs) are compositions that refer to a person, such as Willkommens-Merkel ('Welcome-Meerkel') and a personal name such as Merkel.
Approach: They propose to model 321 personal name compounds and their corresponding full names at discourse level and compare two approaches to assess whether a PNC is more positively or negatively evaluative . they further enrich data with personal, domain-specific, and extra-linguistic information and perform regression analyses revealing that factors including compound and modifier valence, domain, and political party membership influence how a pnc is evaluated.
Outcome: The proposed model shows that the PNCs are perceived as more positively or negatively than their full name and that they are perceived to be more positive or negative.
Bilingual Sentiment Embeddings: Joint Projection of Sentiment Across Languages (P18-1)

Copied to clipboard

Challenge: Existing approaches to sentiment analysis in low-resource languages lack annotated corpora or do not capture sentiment information.
Approach: They propose a model that represents sentiment in a source and target language without annotated corpus.
Outcome: The proposed model outperforms state-of-the-art methods on four out of six setups and captures complementary information to machine translation.
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.
Predicting Degrees of Technicality in Automatic Terminology Extraction (2020.acl-main)

Copied to clipboard

Challenge: a recent study has focused on term technicality, but there are still few studies on it.
Approach: They semi-automatically create a German gold standard of technicality across four domains . they propose two new models to exploit general- vs. domain-specific comparisons based on vector spaces .
Outcome: The proposed model outperforms previous methods in terms of general- vs. domain-specific comparisons.
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.
A Wind of Change: Detecting and Evaluating Lexical Semantic Change across Times and Domains (P19-1)

Copied to clipboard

Challenge: Existing models for diachronic and synchronic detection of lexical semantic divergences are superficial and lack of comparison.
Approach: They propose to extend benchmark models on a common state-of-the-art evaluation task . they also demonstrate that the same evaluation task and modelling approaches can be utilised for synchronic detection of domain-specific sense divergences in the field of term extraction.
Outcome: The proposed model can be utilised for the detection of domain-specific sense divergences in the field of term extraction.
Varying Vector Representations and Integrating Meaning Shifts into a PageRank Model for Automatic Term Extraction (2020.lrec-1)

Copied to clipboard

Challenge: a comparative study for automatic term extraction from domain-specific language using a PageRank graph algorithm with different edge-weighting methods.
Approach: They propose to use a PageRank algorithm to extract automatic terms from domain-specific language using different edge-weighting methods.
Outcome: The proposed model is compared with a PageRank model with different edge-weighting methods.
Diachronic Usage Relatedness (DURel): A Framework for the Annotation of Lexical Semantic Change (N18-2)

Copied to clipboard

Challenge: Existing frameworks for evaluating lexical semantic change are limited . evaluation of lexicals is a major obstacle in the field of semantic change detection .
Approach: They propose a framework that extends synchronic polysemy annotation to diachronic changes in lexical meaning to counteract lack of resources for evaluating computational models of lexiconal semantic change.
Outcome: The proposed framework exploits an intuitive notion of semantic relatedness and distinguishes between innovative and reductive meaning changes with high inter-annotator agreement.
Inclusive Leadership in the Age of AI: A Dataset and Comparative Study of LLMs vs. Real-Life Leaders in Workplace Action Planning (2025.findings-emnlp)

Copied to clipboard

Challenge: a new study compares LLMs and human leaders in workplace action planning tasks . the leader success bot guides real-life leaders in generating inclusive workplace action plans .
Approach: They propose a leader success bot that guides leaders in generating inclusive workplace action plans.
Outcome: The Leader Success Bot guides real-life leaders in generating inclusive workplace action plans.
Analogies in Complex Verb Meaning Shifts: the Effect of Affect in Semantic Similarity Models (N18-2)

Copied to clipboard

Challenge: German particle verbs are complex verb structures that combine a prefix particle with a base verb.
Approach: They propose a computational model to detect and distinguish analogies in meaning shifts between German base and complex verbs using a standard similarity model.
Outcome: The proposed model detects and distinguishes analogies in meaning shifts between German base and complex verbs using a standard similarity model.

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