A Zero-Shot Monolingual Dual Stage Information Retrieval System for Spanish Biomedical Systematic Literature Reviews (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have shown that most SRs are skewed towards English databases, excluding databases in Languages other than English (LoE). |
| Approach: | They propose a zero-shot dual information retrieval baseline system that integrates traditional retrieval methods with pre-trained language models and cross-attention re-rankers for enhanced accuracy in Spanish biomedical literature retrieval. |
| Outcome: | The proposed system improves on three real-life case studies in Spanish biomedical literature retrieval using the LILACS database, which is known for its coverage of Latin American and Caribbean biomedically literature. |
Similar Papers
AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Effective zero-shot dense retrieval in the medical domain remains difficult due to the scarcity of relevance-labeled data. |
| Approach: | They propose a framework that leverages large language models to generate hypothetical documents . they also propose 'CMIRB' to provide a rigorous evaluation suite . |
| Outcome: | The proposed framework outperforms HyDE in retrieval accuracy and generalization . it leverages large language models to generate hypothetical documents conditioned on a query . |
Boosting Zero-shot Cross-lingual Retrieval by Training on Artificially Code-Switched Data (2023.findings-acl)
Copied to clipboard
| Challenge: | Using zero-shot rankers, cross-lingual IR models are limited by their language coverage. |
| Approach: | They propose to train ranking models on artificially code-switched data instead of using a dictionary. |
| Outcome: | The proposed approach is robust towards the ratio of code-switched tokens and extends to unseen languages. |
LGAR: Zero-Shot LLM-Guided Neural Ranking for Abstract Screening in Systematic Literature Reviews (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for abstract screening focus on binary classification settings; existing question answering (QA) based ranking approaches suffer from error propagation. |
| Approach: | They propose a systematic literature review (SLR) method that uses large language models to evaluate the SLR's inclusion and exclusion criteria. |
| Outcome: | The proposed method outperforms existing question answering (QA) based methods by 5-10 pp. in mean precision. |
Benchmarking and Building Zero-Shot Hindi Retrieval Model with Hindi-BEIR and NLLB-E5 (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for evaluating retrieval models in Hindi are lacking . despite efforts to build multilingual retrieval systems, this is still a work in progress . |
| Approach: | They evaluate Hindi retrieval models on the Hindi-BEIR benchmark and introduce a multilingual model that leverages a zero-shot approach to support Hindi without the need for Hindi training data. |
| Outcome: | The proposed model leverages a zero-shot approach to support Hindi without the need for Hindi training data. |
GENRA: Enhancing Zero-shot Retrieval with Rank Aggregation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been shown to perform zero-shot document retrieval, a process that typically consists of two steps: retrieving relevant documents, and re-ranking them based on their relevance to the query. |
| Approach: | They propose a new approach to zero-shot document retrieval that incorporates rank aggregation to improve retrieval effectiveness. |
| Outcome: | The proposed approach improves existing methods on benchmark datasets and shows that it can perform zero-shot retrieval. |
Biomedical Document Retrieval for Clinical Decision Support System (P18-3)
Copied to clipboard
| Challenge: | Thousands of articles are being added into biomedical literature each year. |
| Approach: | They compare statistical and NLP based approaches for biomedical document retrieval . they model biomedically document retrievals as a learning to rank problem . |
| Outcome: | The proposed approach is based on statistical and NLP methods and will be applied to biomedical document retrieval and ranking systems. |
ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrieval (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to improve retrieval effectiveness in high-resource languages are limited due to the lack of high-quality labeled data in non-English languages. |
| Approach: | They propose a modular dense retrieval model that learns from the rich data of a single high-resource language and effectively zero-shot transfers to a wide array of languages. |
| Outcome: | The proposed model performs well against state-of-the-art multilingual retrieval models trained on more extensive datasets in various languages. |
When Specialization Helps: Using Pooled Contextualized Embeddings to Detect Chemical and Biomedical Entities in Spanish (D19-57)
Copied to clipboard
| Challenge: | Existing work on pharmacological entities requires manual annotation of these units. |
| Approach: | They propose an approach to task 1 of the PharmaCoNER Challenge to recognize pharmacological entities on a spanish corpus. |
| Outcome: | The proposed approach achieves 89.76% score on a spanish corpus based on pre-trained embeddings and 90.52% score on domain-specific embeddables. |
Biomedical Named Entity Recognition with Multilingual BERT (D19-57)
Copied to clipboard
| Challenge: | a multilingual model is not specifically tailored to either the language nor the application domain. |
| Approach: | They propose a CRF-based baseline approach and multilingual BERT to the task . they achieve an F-score of 88% on the development data and 87% on the test set with BERT . |
| Outcome: | The proposed model achieves an F score of 88% on the development data and 87% on the test set with BERT. |
Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on cross-language entity linking grounds mentions written in multiple languages to a monolingual knowledge base is lacking. |
| Approach: | They propose a task that uses multilingual BERT representations of both the mention and context as input and explore zero-shot language transfer. |
| Outcome: | The proposed model performs well in both monolingual and multilingual settings. |