Papers with similarity measures
Similarity Measures for the Detection of Clinical Conditions with Verbal Fluency Tasks (N18-2)
Copied to clipboard
| Challenge: | Semantic Verbal Fluency tests have been used in the diagnosis of certain clinical conditions, like Dementia. |
| Approach: | They investigate three similarity measures for automatically identifying switches in semantic chains: semantic similarity from a manually constructed resource, word association strength and semantic relatedness, both calculated from corpora. |
| Outcome: | The proposed classifiers outperform those that use a gold standard taxonomy for clinical conditions. |
FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation (2025.findings-acl)
Copied to clipboard
Qianli Wang, Nils Feldhus, Simon Ostermann, Luis Felipe Villa-Arenas, Sebastian Möller, Vera Schmitt
| Challenge: | Existing frameworks for counterfactual examples are lacking for many tasks. |
| Approach: | They propose a faithful approach for leveraging important words from feature attribution methods to generate counterfactual examples in a zero-shot setting. |
| Outcome: | The proposed framework outperforms state-of-the-art frameworks on many tasks. |
DMix: Adaptive Distance-aware Interpolative Mixup (2022.acl-short)
Copied to clipboard
| Challenge: | Interpolation-based regularisation methods such as Mixup have shown to be effective for various tasks and modalities. |
| Approach: | They propose an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embedding space. |
| Outcome: | The proposed method achieves state-of-the-art on sentence classification over existing methods on 8 benchmark datasets across English, Arabic, Turkish, and Hindi languages while achieving benchmark F1 scores in 3 times less number of iterations. |
Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show that domain-specific BERT models can be improved when in-domain data is used for pretraining. |
| Approach: | They propose to use Twitter and forum text as pretraining sources for two BERT models and use similarity measures to nominate in-domain data for pretraining. |
| Outcome: | The proposed method can be used to improve performance on downstream tasks by using in-domain data. |
RollingLDA: An Update Algorithm of Latent Dirichlet Allocation to Construct Consistent Time Series from Textual Data (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating time series on textual data are not efficient . |
| Approach: | They propose a rolling version of the Latent Dirichlet Allocation, called RollingLDA . they compute similarity of sequentially obtained topic and word distributions over consecutive time periods . |
| Outcome: | The proposed method is based on the popular model Latent Dirichlet Allocation . it is able to build time series consistent with previous states of the model . |
Can Machine Translation Bridge Multilingual Pretraining and Cross-lingual Transfer Learning? (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models that pretrain for cross-lingual tasks do not improve cross-linguistic learning. |
| Approach: | They propose to employ machine translation as a continued training objective to enhance language representation learning by bridging multilingual pretraining and cross-lingual applications. |
| Outcome: | The proposed model performance is compared with existing models and their latent representations. |
Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks (2020.acl-main)
Copied to clipboard
| Challenge: | Multitask learning and transfer learning are techniques to overcome data scarcity . finding suitable auxiliary datasets for multitask learning is a trial-and-error approach . |
| Approach: | They propose to automatically assess the similarity of sequence tagging datasets to identify beneficial auxiliary data for MTL or TL setups. |
| Outcome: | The proposed methods can compute similarity between two sequence tagging datasets . they show that the same measures correlate with the change in test score of the auxiliary dataset . |
GradSim: Gradient-Based Language Grouping for Effective Multilingual Training (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that not all languages positively influence each other . multilingual training can help in those cases by sharing knowledge across languages . |
| Approach: | They propose a gradient similarity-based language grouping method for multilingual training that is better correlated with cross-lingual model performance. |
| Outcome: | The proposed method leads to the largest performance gains on a multilingual dataset and is better correlated with cross-lingual model performance. |
Building Sentiment Lexicons for Mainland Scandinavian Languages Using Machine Translation and Sentence Embeddings (2022.lrec-1)
Copied to clipboard
| Challenge: | a simple but effective method to build sentiment lexicons for the three Mainland Scandinavian languages is proposed . a number of experiments with Scandinavian language datasets yield state-of-the-art results using a rule-based sentiment analysis algorithm. |
| Approach: | They propose a simple but effective method to build sentiment lexicons for the three Mainland Scandinavian languages. |
| Outcome: | The proposed method is based on the English Sentiwordnet and a thesaurus in one of the target languages. |
ContraSim – Analyzing Neural Representations Based on Contrastive Learning (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing similarity measures perform mediocrely on standard benchmarks . |
| Approach: | They develop a similarity measure based on contrastive learning that learns a parameterized measure by using both similar and dissimilar examples. |
| Outcome: | The proposed measure achieves much higher accuracy than previous similarity measures . it is more suitable for the analysis of neural networks, revealing new insights . |
Avoidance Decoding for Diverse Multi-Branch Story Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have attempted to increase the diversity of generated texts through decoding-time methods. |
| Approach: | They propose a decoding strategy that penalizes similarity to previously generated logits to encourage more diverse multi-branch stories. |
| Outcome: | The proposed method achieves up to **2.6** times higher output diversity and reduces repetition by an average of 30% compared to strong baselines, while effectively mitigating text degeneration. |
CateEA: Enhancing Entity Alignment via Implicit Category Supervision (2025.coling-main)
Copied to clipboard
| Challenge: | Existing Entity Alignment methods neglect the inherent semantic information of entities, limiting alignment precision and robustness. |
| Approach: | They propose to combine implicit category information into multi-modal representations by generating pseudo-category labels from entity embeddings and integrating them into a multi-task learning framework. |
| Outcome: | Experiments on benchmark datasets show that CateEA outperforms state-of-the-art methods in various settings. |
Similarity Analysis of Contextual Word Representation Models (2020.acl-main)
Copied to clipboard
| Challenge: | Existing and novel similarity measures are used to analyze contextual word representations . different architectures have rather similar representations, but different individual neurons. |
| Approach: | They propose a method to analyze contextual word representation models using similarity analysis. |
| Outcome: | The proposed approach can be used to analyze model similarity without external annotations. |
What do Toothbrushes do in the Kitchen? How Transformers Think our World is Structured (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent research reveals that transformer-based models are biased towards extracting knowledge about object relations. |
| Approach: | They propose to use transformer-based models to extract knowledge about object relations to investigate whether they can be used to extract object relations. |
| Outcome: | The proposed models outperform static models in many respects and perform much worse than similarity measures and classifiers. |
Demonstration Selection Strategies for Numerical Time Series Data-to-Text (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Demonstration selection is a critical step in in-context learning, where a prompt is fed into large language models. |
| Approach: | They propose to use sequence similarity-based selection and task-specific knowledge-based demonstration selection methods to select similar instances from an example bank. |
| Outcome: | The proposed methods outperform baseline selections and often surpass fine-tuned models on two benchmark datasets and human judges confirm their performance. |
Disentangling language change: sparse autoencoders quantify the semantic evolution of indigeneity in French (2025.naacl-long)
Copied to clipboard
Jacob A. Matthews, Laurent Dubreuil, Imane Terhmina, Yunci Sun, Matthew Wilkens, Marten Van Schijndel
| Challenge: | Existing methods to measure semantic change with contextual word embeddings (CWEs) are not suitable for highly imbalanced datasets and pose challenges for interpretation. |
| Approach: | They propose an interpretable, feature-level approach to analyzing language change using k-sparse autoencoders to trace the semantic evolution of the term "indigène(s)" between 1825 and 1950. |
| Outcome: | The proposed approach can learn interpretable features from over 210,000 CWEs generated using sentences from the French National Library. |
Learning Event-aware Measures for Event Coreference Resolution (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing models for event coreference resolution are based on entity-level tasks, but event coreferent resolution is a challenge. |
| Approach: | They propose a model that learns and integrates multiple representations from event alone and event pair on the basis of event but not entity as before. |
| Outcome: | The proposed model achieves new state-of-the-art on the ACE 2005 benchmark, demonstrating the effectiveness of the proposed framework. |
Zero-shot Learning for Multilingual Discourse Relation Classification (2024.lrec-main)
Copied to clipboard
| Challenge: | Discourse analysis is a hard task, but data is limited for other languages. |
| Approach: | They propose to use zero-shot learning to combine discourse relation data . they compare two versions of the same text with different labels . |
| Outcome: | The proposed method can be applied to languages, frameworks, or similarity measures. |