Papers by Michael Strube

24 papers
A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classification (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing models for fine-grained entity typing have a hierarchical structure . prior work has integrated only explicit hierarchic information by formulating a hierarchy-aware loss or by representing instances and labels in a joint Euclidean embedding space.
Approach: They propose a fully hyperbolic model for multi-class multi-label classification that performs all operations in hyperbolical space.
Outcome: The proposed model performs all operations in hyperbolic space on two challenging datasets and shows it is comparable to state-of-the-art methods on fine-grained classification with remarkable reduction of parameter size.
BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages (L18-1)

Copied to clipboard

Challenge: In an evaluation using fine-grained entity typing as testbed, BPEmb performs competitively . pre-trained subword embeddings for BPE units are commonly available .
Approach: They present a collection of pre-trained subword embeddings in 275 languages . they use fine-grained entity typing as testbed to evaluate BPEmb .
Outcome: The proposed method performs better than other methods, but requires less resources and no tokenization.
Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation (2023.acl-long)

Copied to clipboard

Challenge: Discourse connectives are words or phrases that signal the presence of a discourse relation.
Approach: They propose a model that generates discourse connectives between arguments and predicts discourse relations based on the generated connectives.
Outcome: The proposed model outperforms baselines on three datasets and is highly accurate.
Centering-based Neural Coherence Modeling with Hierarchical Discourse Segments (2020.emnlp-main)

Copied to clipboard

Challenge: Prior studies of coherence focused on identifying semantic relations between adjacent sentences.
Approach: They propose a coherence model which takes discourse structural information into account without relying on human annotations.
Outcome: The proposed model performs state-of-the-art on automated essay scoring and assessing writing quality tasks.
DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence (2023.eacl-main)

Copied to clipboard

Challenge: DiscoScore is a parametrized discourse metric that uses BERT to model discourse coherence . it is weak when operated at system level, and is therefore not reliable in a way to spot improvements .
Approach: They propose a parametrized discourse metric which uses BERT to model discourse coherence from different perspectives.
Outcome: The proposed model outperforms existing models on document-level machine translation and summarization.
What Causes the Failure of Explicit to Implicit Discourse Relation Recognition? (2024.naacl-long)

Copied to clipboard

Challenge: Prior work claimed that explicit classifiers perform poorly in implicit scenarios . a label shift occurs after connectives are removed, but no empirical evidence supports this claim .
Approach: They propose to prove that the discourse relations expressed by some explicit instances will change when connectives disappear.
Outcome: The proposed methods outperform strong baselines on PDTB 2.0, PDTT 3.0, and the GUM dataset.
A Neural Local Coherence Model for Text Quality Assessment (D18-1)

Copied to clipboard

Challenge: Existing approaches to local coherence modeling capture text relatedness at the level of sentence-to-sentence transitions.
Approach: They propose a local coherence model that captures the flow of what connects adjacent sentences . they represent the semantics of a sentence by a vector and capture its state at each word .
Outcome: The proposed model is beneficial for readability assessment and essay scoring tasks.
Incorporating Centering Theory into Neural Coreference Resolution (2022.naacl-main)

Copied to clipboard

Challenge: Recent years, transformer-based coreference resolution systems have achieved remarkable improvements on the CoNLL dataset.
Approach: They propose to incorporate centering transitions derived from centering theory into a neural coreference model by using a graph.
Outcome: The proposed model improves on pronoun resolution in long documents, formal well-structured text, and clusters with scattered mentions.
Adapting Deep Learning Methods for Mental Health Prediction on Social Media (D19-55)

Copied to clipboard

Challenge: a quarter of the population in Europe suffers from an episode of a mental disorder in their life, according to the World Health Organization . text analysis of rich resources like social media can contribute to deeper understanding of mental health and provide means for their early detection.
Approach: They propose to use a hierarchical attention network to predict if a user suffers from one of nine disorders to adapt a deep neural model to the task.
Outcome: The proposed model outperforms previous benchmarks for four out of nine disorders in a binary classification task on social media.
A Large Harvested Corpus of Location Metonymy (2020.lrec-1)

Copied to clipboard

Challenge: Existing datasets of metonymy are either too small in size or lack sufficient coverage.
Approach: They propose a new corpus of location metonymy called WiMCor that is large in size and has high coverage.
Outcome: The proposed corpus is large in size and has high coverage.
Cross-lingual Science Journalism: Select, Simplify and Rewrite Summaries for Non-expert Readers (2023.acl-long)

Copied to clipboard

Challenge: CSJ is a task of text simplification and cross-lingual scientific summarization to facilitate science journalists’ work.
Approach: They propose to combine CSJ tasks SELECT, SIMPLIFY and REWRITE to produce cross-lingual simplified science summaries for non-expert readers.
Outcome: The proposed task outperforms existing solutions on Wikipedia and can serve as a strong baseline for future work.
Incremental Neural Lexical Coherence Modeling (2020.coling-main)

Copied to clipboard

Challenge: Recent work on pretrained language models has led to significant improvements in a range of NLP tasks.
Approach: They propose a coherence model which interprets sentences incrementally to capture lexical relations between them.
Outcome: The proposed model interprets sentences incrementally to capture lexical relations between them.
Consistent Discourse-level Temporal Relation Extraction Using Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have spurred research on temporal relation extraction tasks.
Approach: They propose a framework to improve LLMs’ temporal relation extraction capabilities using context selection, prompts inspired by Allen’s interval algebra and reflection-based consistency learning.
Outcome: The proposed framework improves LLMs’ extraction capabilities by focusing on context selection, prompts inspired by Allen’s interval algebra and reflection-based consistency learning.
Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection (P19-1)

Copied to clipboard

Challenge: Existing methods to evaluate maximum spans tangle coreference evaluation with mention boundary detection . however, this method is costly and does not scale to large corpora.
Approach: They propose an algorithm for automatically extracting minimum spans to benefit from minimum span evaluation in all corpora.
Outcome: The proposed algorithm is consistent with those manually annotated by experts.
Graph-based Clustering for Detecting Semantic Change Across Time and Languages (2024.eacl-long)

Copied to clipboard

Challenge: Existing approaches to detect semantic change using contextualized embeddings are underperforming . a graph-based clustering approach captures nuanced changes in word senses across time and languages .
Approach: They propose a graph-based clustering approach to capture nuanced changes in word senses across time and languages.
Outcome: The proposed approach surpasses previous approaches in the SemEval2020 binary classification task across four languages.
Discourse Relation-Enhanced Neural Coherence Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing work on coherence modeling has focused on integrating entity-based models.
Approach: They propose a model that integrates text- and relation-based features for coherence assessment using position-aware attention and a visible matrix.
Outcome: The proposed model improves baselines on two benchmarks and shows that relation features are important for coherence modeling.
Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers (D18-1)

Copied to clipboard

Challenge: Recent coreference resolvers have notable improvements on the CoNLL evaluation sets, but struggle to generalize properly to new datasets.
Approach: They investigate the role of linguistic features in building more generalizable coreference resolvers . they show that employing features and subsets of their values that are informative for coreference resolution improves generalization .
Outcome: The proposed system achieves state-of-the-art results on WikiCoref, compared with a system trained on CoNLL.
Modeling Structural Similarities between Documents for Coherence Assessment with Graph Convolutional Networks (2023.acl-long)

Copied to clipboard

Challenge: Existing methods focus on a single document’s coherence patterns, ignoring the underlying correlation between documents.
Approach: They propose a GCN-based coherence model that captures structural similarities between documents by mining subgraph patterns and a heterogeneous graph for the training corpus.
Outcome: The proposed model outperforms baseline models on discourse coherence and automated essay scoring tasks.
Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation (P19-1)

Copied to clipboard

Challenge: Pretrained contextual and non-contextual subword embeddings are available in over 250 languages, allowing massively multilingual NLP.
Approach: They compare pretrained contextual and non-contextual subword embeddings with a contextual representation method, namely BERT, on multilingual named entity recognition and part-of-speech tagging.
Outcome: The proposed method outperforms non-contextual embeddings on multilingual named entity recognition and part-of-speech tagging.
Investigating Multilingual Coreference Resolution by Universal Annotations (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing systems for multilingual coreference resolution have been challenging due to linguistic diversity and complexity of different languages.
Approach: They propose a multilingual coreference dataset with universal morphosyntactic and coreference annotations.
Outcome: The proposed dataset improves the baseline system by 0.9% . the proposed dataset is based on the framework of Universal Dependencies 2 .
Linguistic Cues for LLM-based Implicit Discourse Relation Classification (2026.findings-eacl)

Copied to clipboard

Challenge: Large language models (LLMs) have been successful in many NLP tasks, but they struggle to capture subtle lexical relations between arguments.
Approach: They propose a strategy that enriches arguments with explicit lexical-level semantic cues before fine-tuning.
Outcome: The proposed approach improves F1 scores in cross-domain scenarios by more than 10 points compared to baselines.
Entity-based Neural Local Coherence Modeling (2022.acl-long)

Copied to clipboard

Challenge: Recent neural coherence models encode the input document using large-scale pretrained language models.
Approach: They propose an entity-based neural local coherence model which is linguistically more sound than previous models.
Outcome: The proposed model outperforms existing models on three downstream tasks.
Joint Modeling of Entities and Discourse Relations for Coherence Assessment (2025.emnlp-main)

Copied to clipboard

Challenge: Existing work on coherence modeling focuses on entity features or discourse relation features, with little attention given to combining the two.
Approach: They propose two methods for jointly modeling entities and discourse relations for coherence assessment.
Outcome: The proposed methods significantly improve the performance of coherence models on three benchmark datasets.
Transparent, Efficient, and Robust Word Embedding Access with WOMBAT (C18-2)

Copied to clipboard

Challenge: WOMBAT is a Python tool that supports accessing word embeddings from code.
Approach: WOMBAT is a Python tool which supports NLP practitioners in accessing word embeddings from code.
Outcome: WOMBAT is a Python tool which supports accessing word embeddings from code.

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