Papers by Micha Elsner
LLMs in the Real World: Evaluating “AI” in Emergency Contexts (2026.findings-acl)
Copied to clipboard
| Challenge: | Despite considerable overlap between academic and industry-based developers of Large Language Models (LLMs), it seems Natural Language Processing researchers have a science outreach problem. |
| Approach: | They propose a set of concrete recommendations for stakeholders at every stage of the development and deployment pipeline. |
| Outcome: | The proposed model performs worse with lower-resourced languages or worse with higher-resource languages. |
Exploring How Generative Adversarial Networks Learn Phonological Representations (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies in natural language processing (NLP) have demonstrated two generic trends: neural networks dominate language-specific machine learning models; the interpretability of these models is limited that the language representation they learned might not align to human language. |
| Approach: | They propose to use a phonological feature-learning architecture to encode contrastive and non-contrastive nasality in French and English vowels. |
| Outcome: | The proposed architecture encodes contrastive and non-contrastive nasality in French and English vowels. |
Practical, Efficient, and Customizable Active Learning for Named Entity Recognition in the Digital Humanities (N19-1)
Copied to clipboard
Alexander Erdmann, David Joseph Wrisley, Benjamin Allen, Christopher Brown, Sophie Cohen-Bodénès, Micha Elsner, Yukun Feng, Brian Joseph, Béatrice Joyeux-Prunel, Marie-Catherine de Marneffe
| Challenge: | Scholars in interdisciplinary fields like the Digital Humanities are increasingly interested in semantic annotation of specialized corpora. |
| Approach: | They propose an active learning solution for named entity recognition that maximizes a custom model’s improvement per additional unit of manual annotation. |
| Outcome: | The proposed model reduces required annotation by 20-60% and outperforms a competitive active learning baseline. |
Measuring the perceptual availability of phonological features during language acquisition using unsupervised binary stochastic autoencoders (N19-1)
Copied to clipboard
| Challenge: | Xitsonga and English are typologically unrelated languages . phonological features are not directly observed by humans . |
| Approach: | They deploy binary stochastic neural autoencoder networks as models of infant language learning in two typologically unrelated languages. |
| Outcome: | The proposed model is well represented in both languages, while others are less so. |
Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance (2026.eacl-long)
Copied to clipboard
| Challenge: | LISTEN is a controlled benchmark to disentangle lexical reliance from acoustic sensitivity in emotion understanding. |
| Approach: | They propose a benchmark to disentangle lexical reliance from acoustic sensitivity in emotion understanding. |
| Outcome: | LISTEN shows that current LALMs largely "transcribe" rather than "listen" authors note that models underutilize acoustic cues while relying on lexical semantics . |
The Paradigm Discovery Problem (2020.acl-main)
Copied to clipboard
| Challenge: | a paradigm discovery problem is a task of learning an inflectional morphological system from unannotated sentences. |
| Approach: | They formalize the paradigm discovery problem and develop evaluation metrics for judging systems . they use word embeddings and string similarity to cluster forms by cell and by paradigm . |
| Outcome: | The proposed system suggests clustering by cell across different inflection classes is the most pressing challenge for future work. |