A Text Embedding Model with Contrastive Example Mining for Point-of-Interest Geocoding (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies have focused on coarse-grained locations, but we focus on fine-grain POIs, which have many candidates with similar names. |
| Approach: | They develop a text embedding-based geocoding model and investigate (1) entry encoding representations and (2) hard negative mining approaches suitable for enhancing the model’s disambiguation ability. |
| Outcome: | The proposed model significantly improves its disambiguation ability and entry encoding representations. |
Similar Papers
Improving Toponym Resolution by Predicting Attributes to Constrain Geographical Ontology Entries (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing approaches to geocoding only encode location mentions and their context . |
| Approach: | They propose a prompt-based approach to geocoding where the machine learning algorithm encodes only the location mention and its context. |
| Outcome: | The proposed model achieves state-of-the-art performance on multiple datasets. |
Coordinates from Context: Using LLMs to Ground Complex Location References (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing geocoding tools can only link locations already in a geographic database, which often do not include compositional locations. |
| Approach: | They propose a geocoding strategy that leverages LLMs' geospatial knowledge versus reasoning skills to improve performance for the task. |
| Outcome: | The proposed model improves performance and is comparable to larger models. |
Point-of-Interest Type Inference from Social Media Text (2020.aacl-main)
Copied to clipboard
| Challenge: | Using a dataset of 200,000 English tweets, we can predict the type of the place from which a tweet was sent from. |
| Approach: | They propose to analyze a dataset of 200,000 tweets from 2,761 points-of-interest in the U.S. and train classifiers to predict the type of the location a tweet was sent from. |
| Outcome: | The proposed method can predict the type of the location a tweet was sent from and reach a macro F1 of 43.67 across eight classes. |
Information Representation Fairness in Long-Document Embeddings: The Peculiar Interaction of Positional and Language Bias (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that embedding models exhibit systematic positional and language biases when documents are longer and consist of multiple segments. |
| Approach: | They propose a permutation-based evaluation framework to quantify embedding biases . they propose an inference-time attention calibration method that redistributes attention more evenly across document positions . |
| Outcome: | The proposed framework reduces the positional and language biases in embedding models . the proposed framework improves the discoverability of later segments . |
GeospaCy: A tool for extraction and geographical referencing of spatial expressions in textual data (2024.eacl-demo)
Copied to clipboard
| Challenge: | Spatial information in text enables to understand the geographical context and relationships within text for location-sensitive applications. |
| Approach: | They propose to use spatial information extracted from textual data to perform geoparsing and geocoding tasks. |
| Outcome: | The GeospaCy software tool is designed for the extraction and georeferencing of spatial information present in textual data. |
Composition-contrastive Learning for Sentence Embeddings (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work shows potential to learn vector representations from unlabelled data without task-specific fine-tuning. |
| Approach: | They propose to maximize alignment between textual embeddings and a composition of their phrasal constituents. |
| Outcome: | The proposed approach improves on similarity tasks comparable to state-of-the-art approaches. |
Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings (2025.acl-long)
Copied to clipboard
| Challenge: | Text embedding models are used for various natural language processing tasks such as sentiment analysis, text clustering, and content-based information retrieval. |
| Approach: | They propose a synthesis framework that leverages large language models to generate diverse negative samples with varying levels of similarity with the query. |
| Outcome: | The proposed framework achieves state-of-the-art performance surpassing existing synthesis strategies with synthetic data and when combined with public retrieval datasets. |
Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations (2025.findings-naacl)
Copied to clipboard
| Challenge: | a large body of work examines language models for biases concerning gender, race, occupation and religion . however, the impact of the encoded geographical knowledge on real-world applications has not been documented . |
| Approach: | They examine large language models for two common scenarios that require geographical knowledge: travel recommendations and geo-anchored story generation. |
| Outcome: | The results show that the language models are biased against poorer countries and poorer socioeconomic conditions. |
LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients (2025.emnlp-industry)
Copied to clipboard
Egor Fadeev, Dzhambulat Mollaev, Aleksei Shestov, Dima Korolev, Omar Zoloev, Ivan A Kireev, Andrey Savchenko, Maksim Makarenko
| Challenge: | Large language models (LLMs) are computationally expensive and impractical for real-world pipelines. |
| Approach: | They propose a contrastive learning framework that aligns raw event embeddings with description-based semantic embedds from frozen LLMs. |
| Outcome: | The proposed framework outperforms state-of-the-art techniques for learning event sequence representations on real-world financial datasets while remaining deployable in latency-sensitive environments. |
Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding (2022.findings-acl)
Copied to clipboard
| Challenge: | Unsupervised contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data. |
| Approach: | They propose a momentum contrastive learning model with negative sample queue for sentence embedding with a simulated model with EMA update mechanism. |
| Outcome: | The proposed model achieves a Spearman’s correlation of 77.27% on the semantic text similarity task and a maximum traceable distance metric. |