Papers by Robert Frank
Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Sequence-to-sequence models fail to generalize in hierarchy-sensitive manner when performing syntactic transformations. |
| Approach: | They evaluate whether seq2seq models generalize hierarchically on two transformations . they use pre-trained models and their multilingual variants to test their generalization . |
| Outcome: | The proposed models generalize hierarchically on two transformations in English and German. |
Graph-tree Fusion Model with Bidirectional Information Propagation for Long Document Classification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for document classification struggle with token limits and fail to adequately model hierarchical relationships within documents. |
| Approach: | They propose a novel model leveraging a graph-tree structure to capture local and global dependencies. |
| Outcome: | The proposed model captures syntactic relationships and broader document contexts without token limits and can handle arbitrarily long contexts. |
End-to-End Graph-Based TAG Parsing with Neural Networks (N18-1)
Copied to clipboard
| Challenge: | Using BiLSTMs, highway connections, and character-level CNNs, we propose a graph-based Tree Adjoining Grammar (TAG) parser. |
| Approach: | They propose a graph-based Tree Adjoining Grammar parser that uses BiLSTMs, highway connections, and character-level CNNs. |
| Outcome: | The proposed parser outperforms the previously reported best by more than 2.2 LAS and UAS points. |
Is In-Context Learning a Type of Error-Driven Learning? Evidence from the Inverse Frequency Effect in Structural Priming (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent pre-trained large language models have shown the capacity to perform in-context learning (ICL) this capability could provide a way to bridge the divide between language models and humans. |
| Approach: | They propose a new way of diagnosing whether ICL is error-driven learning . they simulated structural priming with ICL and found the effect was stronger . |
| Outcome: | The proposed method is based on the inverse frequency effect (IFE) phenomenon is similar to error-driven learning in large language models . |
LECTURE4ALL: A Lightweight Approach to Precise Timestamp Detection in Online Lecture Videos (2025.acl-demo)
Copied to clipboard
Viktoria Wrobel, Simon Kazemi, Frank Hammerschmidt, Torben Hannemann, Gregor Stange, Seid Muhie Yimam, Robert Geislinger
| Challenge: | Lecture2Go provides a vast collection of recorded lectures, but locating specific content within videos can be time-consuming. |
| Approach: | They present an open-source web application to improve the search experience of educational video platforms. |
| Outcome: | The proposed solution improves the search experience of educational video platforms. |
Multi-stage Retrieve and Re-rank Model for Automatic Medical Coding Recommendation (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for ICD indexing have a heavy label distribution and a manual process . Xie and Xing (2017) propose a new approach to ICD re-ranking . |
| Approach: | They propose a "retrieve and re-rank" framework to allocate subsets of ICD codes to medical records . they leverage auxiliary knowledge of the electronic health records (EHR) and a discrete retrieval method . |
| Outcome: | The proposed method achieves state-of-the-art performance on the MIMIC-III benchmark. |
Does Syntax Need to Grow on Trees? Sources of Hierarchical Inductive Bias in Sequence-to-Sequence Networks (2020.tacl-1)
Copied to clipboard
| Challenge: | Inductive biases can arise from any aspect of the model architecture, study finds . we investigate which architectural factors affect how models generalize . |
| Approach: | They investigate which architectural factors affect generalization behavior of neural network models . they use English question formation and English tense reinflection as test cases . |
| Outcome: | The findings suggest that human-like generalization requires architectural syntactic structure. |
How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure (2023.tacl-1)
Copied to clipboard
| Challenge: | Competent speakers of a language know how likely a word w is to appear in a specific context . |
| Approach: | They use transformer-based large language models to generalize a novel noun argument . they show a bias to generalise based on linear order, instead of a linear order . |
| Outcome: | The proposed models perform well in generalizing the distribution of a novel noun argument between related contexts that were seen during pre-training. |
“A Buster Keaton of Linguistics”: First Automated Approaches for the Extraction of Vossian Antonomasia (D19-1)
Copied to clipboard
| Challenge: | Vossian Antonomasia is a stylistic device which attributes a property to a person by naming another person as a reference point. |
| Approach: | They propose a method for the extraction of Vossian Antonomasias that works completely automatically . they use named entity recognition, distant supervision and a bi-directional LSTM . |
| Outcome: | The proposed method outperforms the only existing semi-automatic method for VA identification by more than 30 percentage points in precision. |
Hierarchical Prompting Assists Large Language Model on Web Navigation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models struggle on processing complicated observations in interactive decision making tasks. |
| Approach: | They propose a hierarchical prompting approach that constructs an action-aware observation and a Summarizer prompt. |
| Outcome: | The proposed method outperforms the current state-of-the-art prompting mechanism by 6.2% on task success rate. |
Meaning Beyond Truth Conditions: Evaluating Discourse Level Understanding via Anaphora Accessibility (2025.acl-long)
Copied to clipboard
| Challenge: | Existing assessments of understanding at the lexical and sentence levels are limited to lexica and sentence level, but few of them target whether LLMs accurately represent and update states of natural language discourse. |
| Approach: | They propose anaphora accessibility as a diagnostic for assessing discourse understanding . they use a dataset inspired by theoretical research in dynamic semantics to evaluate human and LLM performance. |
| Outcome: | The proposed dataset shows that humans and LLMs align on some tasks and diverge on others. |
Syntax-aware Neural Semantic Role Labeling with Supertags (N19-1)
Copied to clipboard
| Challenge: | a new syntax-aware model for dependency-based semantic role labeling outperforms syntax-based models for English and Spanish. |
| Approach: | They propose a syntax-aware model for dependency-based semantic role labeling that outperforms syntax-based models for English and Spanish. |
| Outcome: | The proposed model outperforms syntax-agnostic models for English and Spanish. |
Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity (2022.tacl-1)
Copied to clipboard
| Challenge: | averaging hard attention is used to recognize formal languages that UHAT and GUHAT cannot recognize. |
| Approach: | They analyze three formal Transformer encoders that differ in the form of their self-attention mechanism . they find that UHAT and GUHAT Transformers can only recognize formal languages in AC0 . |
| Outcome: | The proposed models can recognize languages that UHAT and GUHAT cannot . the proposed models are based on the DYCK and PARITY languages . |
LIEDER: Linguistically-Informed Evaluation for Discourse Entity Recognition (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies have shown that large language models have basic, if imperfect, DE recognition abilities, but they lack the basic knowledge of the fundamental semantic properties that govern the introduction and subsequent reference to DEs. |
| Approach: | They propose a dataset that examines large language models’ knowledge of existence, uniqueness, plurality, and novelty. |
| Outcome: | The proposed dataset shows that large language models exhibit sensitivity to all of these properties except novelty, which demonstrates that they have yet to reach human-level language understanding abilities. |
KenMeSH: Knowledge-enhanced End-to-end Biomedical Text Labelling (2022.acl-long)
Copied to clipboard
| Challenge: | Medical Subject Headings (MeSH) are manually assigned to every biomedical article to facilitate retrieval of relevant information. |
| Approach: | They propose a model that combines new text features with a dynamic knowledge-enhanced mask attention that integrates document features with MeSH label hierarchy and journal correlation features to index MeSH terms. |
| Outcome: | The proposed model achieves state-of-the-art on a number of measures. |
Trustworthy Medical Question Answering: An Evaluation-Centric Survey (2025.emnlp-main)
Copied to clipboard
Yinuo Wang, Baiyang Wang, Robert Mercer, Frank Rudzicz, Sudipta Singha Roy, Pengjie Ren, Zhumin Chen, Xindi Wang
| Challenge: | achieving comprehensive trustworthiness in medical QA poses significant challenges due to complexity of healthcare data, critical nature of clinical scenarios, and multifaceted dimensions of trustworthy AI. |
| Approach: | They examine six key dimensions of trustworthiness in medical QA . they compare how each dimension is evaluated in existing LLM-based systems . |
| Outcome: | The findings show that large language models have improved patient safety and effectiveness . the models exhibit critical trust failures when deployed in clinical settings . |
Multilingual prediction of Alzheimer’s disease through domain adaptation and concept-based language modelling (N19-1)
Copied to clipboard
Kathleen C. Fraser, Nicklas Linz, Bai Li, Kristina Lundholm Fors, Frank Rudzicz, Alexandra König, Jan Alexandersson, Philippe Robert, Dimitrios Kokkinakis
| Challenge: | Existing work on speech and language models has been limited by the size of available datasets. |
| Approach: | They propose to augment a small French dataset with a much larger English dataset to augment the language model to model the order in which information units are produced by dementia patients and controls. |
| Outcome: | The proposed model improves classification performance in English and French separately. |
How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech (2023.acl-long)
Copied to clipboard
| Challenge: | LSTMs and Transformers perform well at capturing the surface statistics of child-directed speech, but both model types generalize in a way consistent with an incorrect linear rule than the correct hierarchical rule. |
| Approach: | They train LSTMs and Transformers on text from the CHILDES corpus and evaluate what they learn about English yes/no questions. |
| Outcome: | The proposed models perform well at capturing the surface statistics of child-directed speech, but generalize more consistent with an incorrect linear rule than the correct hierarchical rule. |