Papers by Juri Opitz

20 papers
Information Representation Fairness in Long-Document Embeddings: The Peculiar Interaction of Positional and Language Bias (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies show that embedding models exhibit systematic positional and language biases when documents are longer and consist of multiple segments.
Approach: They propose a permutation-based evaluation framework to quantify embedding biases . they propose an inference-time attention calibration method that redistributes attention more evenly across document positions .
Outcome: The proposed framework reduces the positional and language biases in embedding models . the proposed framework improves the discoverability of later segments .
Similar, but why? A Toolkit for Explaining Text Similarity (2026.eacl-demo)

Copied to clipboard

Challenge: XPLAINSIM is a Python package that explains textual similarity in an easy-to-use way.
Approach: They propose a Python package that unifies three approaches to explain text similarity . they demonstrate the value of the package through intuitive examples and empirical research .
Outcome: XPLAINSIM is a Python package that unifies three approaches to explain text similarity . the authors show that the package is useful for explaining text similarities in a simple way .
PARAPHRASUS: A Comprehensive Benchmark for Evaluating Paraphrase Detection Models (2025.coling-main)

Copied to clipboard

Challenge: prevailing notion of paraphrase is simplistic, offering only limited view of vast spectrum of paraphrasing phenomena.
Approach: They propose a benchmarking tool for paraphrase detection that provides a fine-grained evaluation lens.
Outcome: The proposed benchmark enables rapid calibration of models to specific strictness levels.
ConLoan: A Contrastive Multilingual Dataset for Evaluating Loanwords (2025.acl-long)

Copied to clipboard

Challenge: Lexical borrowing is a ubiquitous linguistic phenomenon influenced by geopolitical, societal, and technological factors.
Approach: They propose a novel contrastive dataset comprising sentences with and without loanwords across 10 languages to examine how machine translation and language models process loanword .
Outcome: The proposed dataset shows that state-of-the-art models prefer loanwords over native terms and exhibit varying performance across languages.
Weisfeiler-Leman in the Bamboo: Novel AMR Graph Metrics and a Benchmark for AMR Graph Similarity (2021.tacl-1)

Copied to clipboard

Challenge: Existing metrics for assessing the similarity of abstract meaning representations (AMRs) have complementary strengths and weaknesses, and are expensive to implement.
Approach: They propose a Benchmark for AMR Metrics based on overt objectives that can be used to assess graph-based similarity metrics.
Outcome: The proposed metrics match contextualized substructures and induce n:m alignments between their nodes.
SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features (2022.aacl-main)

Copied to clipboard

Challenge: Abstract Meaning Representation (S3BERT) embeddings are composed of explainable sub-embeddings that emphasize various sentence meaning features.
Approach: They propose to induce Semantically Structured Sentence BERT embeddings (S3BERT) that emphasize various sentence meaning features.
Outcome: The proposed model shows high correlation to human similarity ratings, but lacks interpretability.
Interpretable Text Embeddings and Text Similarity Explanation: A Survey (2025.emnlp-main)

Copied to clipboard

Challenge: Text embeddings are a fundamental component in many NLP tasks, but their interpretation and explanation remain challenging.
Approach: They propose a framework for interpretable text embeddings and text similarity explanation . they characterize the main ideas, approaches, and trade-offs and discuss lessons learned .
Outcome: The proposed methods are compared with existing models and compare them with existing ones.
On the Role of Summary Content Units in Text Summarization Evaluation (2024.naacl-short)

Copied to clipboard

Challenge: a human written summary content unit (SCU) is used to judge the quality of a summary . a pyramid evaluation method is based on SCUs that decompose a reference summary into concise sentences .
Approach: They propose to use automated SCUs to evaluate the quality of a candidate summary . they propose to generate SCU approximations from AMR meaning representations and large language models .
Outcome: The proposed method can be fully automated, but lacks the human effort to validate it.
A Survey of AMR Applications (2024.emnlp-main)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a semantic representation that takes the form of a rooted, directed graph.
Approach: They analyze more than 100 papers which use Abstract Meaning Representation (AMR) they highlight the range of applications for which AMR has been harnessed and techniques for incorporating it . they also highlight broader AMR engineering patterns and outline areas of future work that seem ripe for AMR incorporation.
Outcome: The results highlight the range of applications for which AMR has been harnessed and the techniques for incorporating it into those applications.
Schroedinger’s Threshold: When the AUC Doesn’t Predict Accuracy (2024.lrec-main)

Copied to clipboard

Challenge: AUC is a useful tool for evaluating diverse models without calibration.
Approach: They show that the AUC yields an academic notion of accuracy that can misalign with actual accuracy observed in application.
Outcome: The AUC yields an academic and optimistic notion of accuracy that can misalign with actual accuracy observed in application.
With a Little Push, NLI Models can Robustly and Efficiently Predict Faithfulness (2023.acl-short)

Copied to clipboard

Challenge: Conditional language models generate unfaithful output that is not supported by their input . this jeopardizes trust in real-world applications, raising a need for automatic faithfulness metrics.
Approach: They propose to augment conditional language models with robust inference procedures to improve faithfulness.
Outcome: The proposed approach outperforms existing models on the TRUE benchmark.
Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR (2021.eacl-main)

Copied to clipboard

Challenge: Abstract meaning representations are typically evaluated using surface matching metrics . however, there are problems with these metrics, since they allow multiple surface realizations .
Approach: They propose a decomposable metric that measures the distance between the original and reconstructed AMRs.
Outcome: The proposed metric reduces the complexity of the evaluation process by allowing for multiple surface realizations.
AMR Similarity Metrics from Principles (2020.tacl-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) graphs are rooted, acyclic, directed, and edge-labeled.
Approach: They propose a canonical Smatch metric that aligns variables of two graphs and assesses triple matches.
Outcome: The proposed metric is more benevolent to only very slight meaning deviations and targets the fulfilment of all established criteria.
AMR Quality Rating with a Lightweight CNN (2020.aacl-main)

Copied to clipboard

Challenge: Structured semantic sentence representations are useful in various NLP tasks, but their quality can vary greatly and jeopardize their usefulness.
Approach: They propose to transfer the AMR graph to the domain of images and create a convolutional neural network that imitates a human judge tasked with rating graph quality.
Outcome: The proposed model can rate quality more accurately than strong baselines, in several quality dimensions, and reduces energy consumption.
Cheap Character Noise for OCR-Robust Multilingual Embeddings (2025.findings-acl)

Copied to clipboard

Challenge: Optical character recognition (OCR) is a key component of the digitization of historical documents.
Approach: They propose a method that fine-tunes existing multilingual models using noisy texts and a contrastive loss.
Outcome: The proposed model improves on the training data of existing models using noisy texts and a contrastive loss.
A Survey of Meaning Representations – From Theory to Practical Utility (2024.naacl-long)

Copied to clipboard

Challenge: Symbolic meaning representations of natural language text have been studied since at least the 1960s . with the availability of large annotated corpora, the field has recently seen several new developments .
Approach: They propose a framework for expressing meaning in natural language text using annotated corpora and a set of tools for machine learning.
Outcome: The frameworks are based on a set of theoretical and practical problems and their applications.
Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks (2023.acl-long)

Copied to clipboard

Challenge: Arguments often do not make explicit how a conclusion follows from its premises . we present a method for constructing Contextualized Commonsense Knowledge Graphs (CCKGs) that is efficient and high-quality .
Approach: They propose an unsupervised method for constructing Contextualized Commonsense Knowledge Graphs (CCKGs) they use triplet similarities to extract contextually relevant knowledge paths .
Outcome: The proposed method outperforms baselines and a GPT-3 based system in a knowledge-intense argumentation task.
A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation – through the Lens of Semantic Similarity Rating (2022.starsem-1)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a popular NLG evaluation metric . however, it is difficult to judge where exactly such a metric fails .
Approach: They propose a checklist for NLG evaluation metrics that focus on meaning by organizing them around meaning-relevant linguistic phenomena.
Outcome: The proposed metric GraCo computes lexical cohesion graphs over AMR concepts.
Sentence Smith: Controllable Edits for Evaluating Text Embeddings (2025.emnlp-main)

Copied to clipboard

Challenge: Controllable and transparent text generation has been a long-standing goal in NLP . but previous approaches were hindered by parsing and generation insufficiencies .
Approach: They propose a framework for English that has three steps: 1. Parsing a sentence into a semantic graph. 2. Applying human-designed semantic manipulation rules. 3. Generating text from the manipulated graph.
Outcome: The proposed framework for English is based on a neural network and parsers.
SMATCH++: Standardized and Extended Evaluation of Semantic Graphs (2023.findings-eacl)

Copied to clipboard

Challenge: Existing graph-alignment metrics that measure graph distances are not reliable, we show . metric is spread out and does not provide upper bounds for extended tasks.
Approach: They propose a metric to measure a distance between graphs by aligning nodes and counting matching graph triples.
Outcome: The proposed method reduces search space and improves scoring by reducing the number of errors.

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