Related papers: Geo-Encoder: A Chunk-Argument Bi-Encoder Framework…
Most Chinese Grapheme-to-Phoneme (G2P) systems employ a three-stage framework that first transforms input sequences into character embeddings, obtains linguistic information using language models, and then predicts the phonemes based on…
Retrieval-Augmented Generation (RAG) systems are increasingly vital for navigating the ever-expanding body of scientific literature, particularly in high-stakes domains such as chemistry. Despite the promise of RAG, foundational design…
In monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance due to the effectiveness of cross-encoder re-ranker.…
Position encoding is the primary mechanism which induces notion of sequential order for input tokens in transformer architectures. Even though this formulation in the original transformer paper has yielded plausible performance for general…
Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity between a query and documents. However, the scalar similarity…
Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong generalization ability on recent benchmarks of image-based 3D…
Opinion summarization is the task of creating summaries capturing popular opinions from user reviews. In this paper, we introduce Geodesic Summarizer (GeoSumm), a novel system to perform unsupervised extractive opinion summarization.…
Graph foundation models represent a transformative paradigm for learning transferable representations across diverse graph domains. Recent methods leverage large language models to unify graph and text modalities into a shared…
This research presents an Encoded Spatial Multi-Tier Federated Learning approach for a comprehensive evaluation of aggregated models for geospatial data. In the client tier, encoding spatial information is introduced to better predict the…
Visual transformers have driven major progress in remote sensing image analysis, particularly in object detection and segmentation. Recent vision-language and multimodal models further extend these capabilities by incorporating auxiliary…
Chinese text segmentation is a well-known and difficult problem. On one side, there is not a simple notion of "word" in Chinese language making really hard to implement rule-based systems to segment written texts, thus lexicons and…
Framing is an essential device in news reporting, allowing the writer to influence public perceptions of current affairs. While there are existing automatic news framing detection datasets in various languages, none of them focus on news…
Depth estimation from a single image is an important task that can be applied to various fields in computer vision, and has grown rapidly with the development of convolutional neural networks. In this paper, we propose a novel structure and…
LLMs excel at linguistic tasks but lack the inner geospatial capabilities needed for time-critical disaster response, where reasoning about road networks, coordinates, and access to essential infrastructure such as hospitals, shelters, and…
This work addresses the task of overhead image segmentation when auxiliary ground-level images are available. Recent work has shown that performing joint inference over these two modalities, often called near/remote sensing, can yield…
Worldwide geo-localization involves determining the exact geographic location of images captured globally, typically guided by geographic cues such as climate, landmarks, and architectural styles. Despite advancements in geo-localization…
Chinese Grammatical Error Correction (CGEC) aims to automatically detect and correct grammatical errors contained in Chinese text. In the long term, researchers regard CGEC as a task with a certain degree of uncertainty, that is, an…
Referring Expression Comprehension and Segmentation are critical tasks for assessing the integration of language understanding and image comprehension, serving as benchmarks for Multimodal Large Language Models (MLLMs) capabilities. To…
This paper presents the ReCO, a human-curated ChineseReading Comprehension dataset on Opinion. The questions in ReCO are opinion based queries issued to the commercial search engine. The passages are provided by the crowdworkers who extract…
Current neural re-rankers often struggle with complex information needs and long, content-rich documents. The fundamental issue is not computational--it is intelligent content selection: identifying what matters in lengthy, multi-faceted…