Papers with triplet loss
Harmonizing Diverse Models: A Layer-wise Merging Strategy for Consistent Generation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | RAG systems often generate inconsistent outputs for semantically equivalent inputs . this unpredictability undermines the reliability of RAG and poses challenges for adoption in high-stakes or knowledge-sensitive domains such as finance, healthcare, and scientific research. |
| Approach: | They propose a method that integrates knowledge from specialized models into a single model to improve output consistency. |
| Outcome: | The proposed model significantly improves output consistency, achieving approximately 47.5% improvement in response similarity over baseline. |
Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to retrieve hard negative sentences are limited in the scale of the dataset thus fail to identify negative samples of high difficulty for every image. |
| Approach: | They propose to use a model to generate synthetic negative sentences with higher difficulty by masking and refilling the images and performing word discrimination and word correction tasks to improve retrieval and generation. |
| Outcome: | The proposed model generates synthetic negative sentences with higher difficulty on MS-COCO and Flickr30K and is robust and faithful to state-of-the-art training. |
Improving Neural Models for Radiology Report Retrieval with Lexicon-based Automated Annotation (2022.naacl-main)
Copied to clipboard
| Challenge: | Conventional exact or approximate termbased retrieval methods lack the ability of semantic understanding of the clinical as well as language context. |
| Approach: | They combine clinical finding detection with supervised query match learning to train a model . findings are used as queries to train the Sentence-BERT model using triplet loss . |
| Outcome: | The proposed method outperforms existing methods on multiple retrieval benchmarks. |
A Deep Metric Learning Method for Biomedical Passage Retrieval (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for passage retrieval are based on metric learning . the proposed approach is particularly well suited for domain-specific passage retrievals where it is very important to take into account different sources of information. |
| Approach: | They propose a method that learns a metric for questions and passages based on their internal semantic interactions. |
| Outcome: | The proposed method outperforms triplet loss and state-of-the-art methods in a biomedical passage retrieval task and outperformed triplet losses by 10% and 26%. |
Anchoring Fine-tuning of Sentence Transformer with Semantic Label Information for Efficient Truly Few-shot Classification (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fewshot text classification require substantial computing power and data. |
| Approach: | They propose an efficient method to add task and label information to a sentence transformer model by contrastive learning and a triplet loss to enforce training instances to be closest to their own textual semantic label information. |
| Outcome: | The proposed method achieves strong performance in data-sparse scenarios compared to existing methods across SST-5, Emotion detection, and AG News data even with just two examples per class. |
Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss (2024.findings-acl)
Copied to clipboard
| Challenge: | Accurately modeling idiomatic or non-compositional language has been a longstanding challenge in natural language processing (NLP). |
| Approach: | They propose an approach to model idiomaticity effectively using a triplet loss that incorporates the asymmetric contribution of components words to an idiomatic meaning by using adaptive contrastive learning and resampling miners. |
| Outcome: | The proposed model outperforms previous models significantly on a SemEval challenge and outperformed previous alternatives in many metrics. |
LANID: LLM-assisted New Intent Discovery (2024.lrec-main)
Copied to clipboard
| Challenge: | Data annotation is expensive in Task-Oriented Dialogue systems. |
| Approach: | They propose a framework that leverages Large Language Models' zero-shot capability to enhance the performance of a smaller text encoder on the NID task. |
| Outcome: | The proposed framework surpasses all strong baselines in both unsupervised and semi-supervised settings. |
On an Intermediate Task for Classifying URL Citations on Scholarly Papers (2024.lrec-main)
Copied to clipboard
| Challenge: | Citations using URLs can be used as information source for research resource search engines. |
| Approach: | They propose a method to classify URL citations using a simple fine-tuning strategy. |
| Outcome: | The proposed method outperforms methods using a simple fine-tuning strategy with higher macro F-scores for different model sizes and architectures. |