Papers with similarity computation
CELI: Simple yet Effective Approach to Enhance Out-of-Domain Generalization of Cross-Encoders. (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing cross-encoders do not capture all information into the [CLS] token . Xiong et al., 2021) find that the out-of-domain approach is less robust. |
| Approach: | They introduce a cross-encoder with late interaction that incorporates a late interaction layer into existing models. |
| Outcome: | The proposed method improves BEIR by 5% without compromising in-domain effectiveness or search latency. |
A Graph Interaction Framework on Relevance for Multimodal Named Entity Recognition with Multiple Images (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to determine whether images are related to named entities are not effective in multi-image scenarios. |
| Approach: | They propose a graph interaction framework on relevance for Multimodal Named Entity Recognition with multiple images to integrate human abilities into the model. |
| Outcome: | The proposed framework achieves state-of-the-art on benchmark datasets and compares with CLIP and CLIP-based approaches. |
Text Style Transfer via Optimal Transport (2022.naacl-main)
Copied to clipboard
| Challenge: | Text style transfer (TST) is a task that aims to change the style of a text from source to target while preserving its content. |
| Approach: | They propose a method to incorporate syntactic and semantic information into similarity computation between the source and the converted text. |
| Outcome: | The proposed method is superior in both supervised and unsupervised settings. |
MMQA: A Multi-domain Multi-lingual Question-Answering Framework for English and Hindi (L18-1)
Copied to clipboard
| Challenge: | Existing work on multi-domain, multi-lingual question answering is limited to the same language. |
| Approach: | They curate 500 articles in six different domains from the web and create question-answer pairs . they develop a deep learning based model for classifying an input question into coarse and finer categories . |
| Outcome: | The proposed model accuracies 90.12% and 80.30% for coarse and finer classes . the proposed model is the first attempt to create multi-domain, multi-lingual question answering evaluation involving English and Hindi. |
Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for dense retrieval use pseudo-relevance feedback to model dimension importance . however, they learn global transformations shared across queries and do not model dimension-aware dimension importance. |
| Approach: | They propose a Query-Aware Adaptive Dimension Selection framework that learns to predict per-dimension importance directly from query embedding. |
| Outcome: | The proposed framework improves retrieval effectiveness over the full-dimensional and PRF-based models. |
This Reads Like That: Deep Learning for Interpretable Natural Language Processing (2023.emnlp-main)
Copied to clipboard
| Challenge: | In this work, we explore the extension of prototypical networks to natural language processing. |
| Approach: | They propose a weighted similarity measure that enhances the similarity computation by focusing on informative dimensions of pre-trained sentence embeddings. |
| Outcome: | The proposed method improves predictive performance on AG News and RT Polarity datasets and the rationale-based recurrent convolutions. |