English
Related papers

Related papers: Fusing Data with Correlations

200 papers

Document-level relation extraction (DocRE) is a task that focuses on identifying relations between entities within a document. However, existing DocRE models often overlook the correlation between relations and lack a quantitative analysis…

Information Retrieval · Computer Science 2023-10-23 Yusheng Huang , Zhouhan Lin

Flow matching has recently emerged as a promising alternative to diffusion-based generative models, particularly for text-to-image generation. Despite its flexibility in allowing arbitrary source distributions, most existing approaches rely…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Junwan Kim , Jiho Park , Seonghu Jeon , Seungryong Kim

Question answering models can use rich knowledge sources -- up to one hundred retrieved passages and parametric knowledge in the large-scale language model (LM). Prior work assumes information in such knowledge sources is consistent with…

Computation and Language · Computer Science 2022-10-26 Hung-Ting Chen , Michael J. Q. Zhang , Eunsol Choi

Relation extraction is a Natural Language Processing task that aims to extract relationships from textual data. It is a critical step for information extraction. Due to its wide-scale applicability, research in relation extraction has…

Computation and Language · Computer Science 2024-11-27 Anushka Swarup , Avanti Bhandarkar , Olivia P. Dizon-Paradis , Ronald Wilson , Damon L. Woodard

Unlike extractive summarization, abstractive summarization has to fuse different parts of the source text, which inclines to create fake facts. Our preliminary study reveals nearly 30% of the outputs from a state-of-the-art neural…

Information Retrieval · Computer Science 2017-11-15 Ziqiang Cao , Furu Wei , Wenjie Li , Sujian Li

Knowledge about entities and their interrelations is a crucial factor of success for tasks like question answering or text summarization. Publicly available knowledge graphs like Wikidata or DBpedia are, however, far from being complete. In…

Information Retrieval · Computer Science 2021-02-16 Nicolas Heist , Heiko Paulheim

Effective utilization of time series data is often constrained by the scarcity of data quantity that reflects complex dynamics, especially under the condition of distributional shifts. Existing datasets may not encompass the full range of…

Computational Engineering, Finance, and Science · Computer Science 2024-06-11 Haibei Zhu , Yousef El-Laham , Elizabeth Fons , Svitlana Vyetrenko

Recent work in machine learning for information extraction has focused on two distinct sub-problems: the conventional problem of filling template slots from natural language text, and the problem of wrapper induction, learning simple…

Information Retrieval · Computer Science 2012-06-06 Radhouane Boughamoura , Mohamed Nazih Omri , Habib Youssef

Recommender systems are crucial tools to overcome the information overload brought about by the Internet. Rigorous tests are needed to establish to what extent sophisticated methods can improve the quality of the predictions. Here we…

Information Retrieval · Computer Science 2007-09-19 Marcel Blattner , Alexander Hunziker , Paolo Laureti

A common challenge in the natural sciences is to disentangle distinct, unknown sources from observations. Examples of this source separation task include deblending galaxies in a crowded field, distinguishing the activity of individual…

Machine Learning · Computer Science 2025-10-08 Sebastian Wagner-Carena , Aizhan Akhmetzhanova , Sydney Erickson

As an essential component of human cognition, cause-effect relations appear frequently in text, and curating cause-effect relations from text helps in building causal networks for predictive tasks. Existing causality extraction techniques…

Information Retrieval · Computer Science 2021-11-02 Jie Yang , Soyeon Caren Han , Josiah Poon

Citation parsing is fundamental for search engines within academia and the protection of intellectual property. Meticulous extraction is further needed when evaluating the similarity of documents and calculating their citation impact.…

Digital Libraries · Computer Science 2018-05-23 Niall Martin Ryan

The theory of belief functions manages uncertainty and also proposes a set of combination rules to aggregate opinions of several sources. Some combination rules mix evidential information where sources are independent; other rules are…

Artificial Intelligence · Computer Science 2015-03-18 Mouna Chebbah , Arnaud Martin , Boutheina Ben Yaghlane

Information flow analysis has largely ignored the setting where the analyst has neither control over nor a complete model of the analyzed system. We formalize such limited information flow analyses and study an instance of it: detecting the…

Cryptography and Security · Computer Science 2014-05-13 Michael Carl Tschantz , Amit Datta , Anupam Datta , Jeannette M. Wing

Query expansion is an effective approach for mitigating vocabulary mismatch between queries and documents in information retrieval. One recent line of research uses language models to generate query-related contexts for expansion. Along…

Computation and Language · Computer Science 2022-10-14 Linqing Liu , Minghan Li , Jimmy Lin , Sebastian Riedel , Pontus Stenetorp

Online encyclopedia such as Wikipedia has become one of the best sources of knowledge. Much effort has been devoted to expanding and enriching the structured data by automatic information extraction from unstructured text in Wikipedia.…

Information Retrieval · Computer Science 2014-06-26 Kezun Zhang , Yanghua Xiao , Hanghang Tong , Haixun Wang , Wei Wang

Based on literature review about existing diffusion models and flow matching with a neural network to predict a predefined target from noisy data, a unified representation is first proposed for these models using two simple linear equations…

Machine Learning · Computer Science 2026-03-10 Zhengguo Li , Chaobing Zheng , Wei Wang

Citations are the cornerstone of knowledge propagation and the primary means of assessing the quality of research, as well as directing investments in science. Science is increasingly becoming "data-intensive", where large volumes of data…

Digital Libraries · Computer Science 2017-09-28 Gianmaria Silvello

Data integration systems allow users to access data sitting in multiple sources by means of queries over a global schema, related to the sources via mappings. Data sources often contain sensitive information, and thus an analysis is needed…

Logic in Computer Science · Computer Science 2020-12-15 Michael Benedikt , Pierre Bourhis , Louis Jachiet , Michaël Thomazo

Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms…

Machine Learning · Computer Science 2024-10-04 Yujin Choi , Jinseong Park , Hoki Kim , Jaewook Lee , Saerom Park