Papers by Michael Hahn
“Beste Grüße, Maria Meyer” — Pseudonymization of Privacy-Sensitive Information in Emails (2022.lrec-1)
Copied to clipboard
| Challenge: | exploding amount of user-generated content has spurred research to deal with documents from various digital communication formats. |
| Approach: | They propose to identify text spans that carry information revealing an individual’s identity and substitute them with synthetically generated surrogates. |
| Outcome: | The proposed model is based on a German-language email corpus and evaluates its training data on pseudonymized data. |
Theoretical Limitations of Self-Attention in Neural Sequence Models (2020.tacl-1)
Copied to clipboard
| Challenge: | Existing work suggests that the computational capabilities of self-attention to model hierarchical structures are limited. |
| Approach: | They investigate the computational power of self-attention to model formal languages . they show strong theoretical limitations of self attention to model periodic finite-state languages unless the number of layers or heads increases with input length. |
| Outcome: | The proposed models can model periodic finite-state languages, nor hierarchical structure unless the number of layers or heads increases with input length. |
An Information-Theoretic Characterization of Morphological Fusion (2021.emnlp-main)
Copied to clipboard
| Challenge: | Linguistic typology generally divides synthetic languages into groups based on their morphological fusion. |
| Approach: | They propose to quantify the degree of fusion of morphological features in a surface form . they recapitulate the usual linguistic classifications for concatenative systems . |
| Outcome: | The proposed measure recapitulates the usual classifications for concatenative systems and provides new measures for nonconcatenating ones. |
Tug-of-war between idioms’ figurative and literal interpretations in LLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | We find that idioms have non-compositional figurative interpretations that diverge from the idiomatic literal interpretation. |
| Approach: | They employ causal tracing to analyze how pretrained causal transformers deal with idiom ambiguity. |
| Outcome: | The proposed model leverages the idiom's context and refines it if it conflicts with the retrieved interpretation. |
Systematicity between Forms and Meanings across Languages Supports Efficient Communication (2026.acl-long)
Copied to clipboard
| Challenge: | Languages vary in how meanings map to word forms, but this theory does not account for systematic relations within word forms. |
| Approach: | They propose a model that measures the learnability of meaning-to-form mappings by inverse of simplicity. |
| Outcome: | The proposed model captures fine-grained regularities in linguistic form, allowing better discrimination between attested and unattested systems. |
RNNs can generate bounded hierarchical languages with optimal memory (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that RNNs can efficiently generate bounded hierarchical languages with high syntactic fidelity, but their success is not well-understood theoretically. |
| Approach: | They propose a language of well-nested brackets and m-bounded nesting depth . they prove that an RNN with O(m log k) hidden units suffices, an exponential reduction in memory, by an explicit construction. |
| Outcome: | The proposed language is well-nested brackets and has m-bounded nesting depth . it shows that an RNN with O(m log k) hidden units suffices, an exponential reduction in memory, by an explicit construction. |
A Cross-Linguistic Pressure for Uniform Information Density in Word Order (2023.tacl-1)
Copied to clipboard
Thomas Hikaru Clark, Clara Meister, Tiago Pimentel, Michael Hahn, Ryan Cotterell, Richard Futrell, Roger Levy
| Challenge: | a recent study has compared real and counterfactual word orders, but one functional pressure has been overlooked . a study of 10 typologically diverse languages shows that real word orders have greater uniformity than reverse word orders . |
| Approach: | They propose to test whether a pressure for UID may have influenced word order patterns cross-linguistically. |
| Outcome: | The proposed model shows that real orders have greater uniformity than reverse orders among SVO languages. |
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies explore the ability of language models to solve multi-hop reasoning tasks without chain of thought. |
| Approach: | They propose to use GPT2-style language models to train k-hop reasoning models . they show that the required training data grows exponentially in k . |
| Outcome: | The proposed models can learn implicit reasoning without chain-of-thoughts, the authors show . their training data grows exponentially in k, and the required number of transformer layers grows linearly in the model. |
System-Mediated Attention Imbalances Make Vision-Language Models Say Yes (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing mitigation strategies tend towards an image-centric interpretation of these imbalances, prioritising increased image attention while giving less consideration to the roles of the other modalities. |
| Approach: | They propose a more holistic, system-mediated account which attributes imbalances to functionally redundant system weights that reduce attention to image and textual inputs. |
| Outcome: | The proposed framework offers a useful empirical perspective on the yes-bias, a common form of hallucination in which VLMs indiscriminately respond ‘yes’. |
More frequent verbs are associated with more diverse valency frames: Efficient principles at the lexicon-grammar interface (2024.acl-long)
Copied to clipboard
| Challenge: | Existing evidence has focused on word-internal properties, such as Zipf's observation that more frequent words are optimized in form to minimize communicative cost. |
| Approach: | They propose to examine the hypothesis that efficient lexicon organization is also reflected in valency, or the combinations and orders of additional words and phrases a verb selects for in a sentence. |
| Outcome: | The proposed hypothesis is consistent with communicative efficiency principles. |
Sensitivity as a Complexity Measure for Sequence Classification Tasks (2021.tacl-1)
Copied to clipboard
| Challenge: | Existing complexity metrics provide limited practical insight into complexity differences between tasks. |
| Approach: | They propose a theoretical framework for understanding and predicting the complexity of sequence classification tasks using a new extension of the theory of Boolean function sensitivity. |
| Outcome: | The proposed framework predicts the complexity of sequence classification tasks using a new method . it shows that low-sensitivity functions are easier to learn for LSTMs than lexical classifiers . |