no code implementations • 31 Jan 2024 • Jessica Lin, Amir Zeldes
As NLP models become increasingly capable of understanding documents in terms of coherent entities rather than strings, obtaining the most salient entities for each document is not only an important end task in itself but also vital for Information Retrieval (IR) and other downstream applications such as controllable summarization.
1 code implementation • 3 Jun 2023 • Tatsuya Aoyama, Shabnam Behzad, Luke Gessler, Lauren Levine, Jessica Lin, Yang Janet Liu, Siyao Peng, YIlun Zhu, Amir Zeldes
We evaluate state-of-the-art NLP systems on GENTLE and find severe degradation for at least some genres in their performance on all tasks, which indicates GENTLE's utility as an evaluation dataset for NLP systems.
no code implementations • 12 Jan 2023 • Wenjie Xi, Arnav Jain, Li Zhang, Jessica Lin
Recently, Similarity-aware Time Series Classification (SimTSC) is proposed to address this problem by using a graph neural network classification model on the graph generated from pairwise Dynamic Time Warping (DTW) distance of batch data.
1 code implementation • 4 Jan 2023 • Li Zhang, Jiahao Ding, Yifeng Gao, Jessica Lin
During the process, data sharing is often involved to allow the third-party modelers to perform specific time series data mining (TSDM) tasks based on the need of data owner.
no code implementations • 28 Dec 2022 • Jessica Lin
While much attention has been paid to identifying explicit hate speech, implicit hateful expressions that are disguised in coded or indirect language are pervasive and remain a major challenge for existing hate speech detection systems.
no code implementations • 3 Nov 2022 • Li Zhang, Yan Zhu, Yifeng Gao, Jessica Lin
Inspired by a recent work that tracks how the nearest neighbor of a time series subsequence changes over time, we introduce a new TSC definition which is much more robust to noise in the data, in the sense that they can better locate the evolving patterns while excluding the non-evolving ones.
no code implementations • EMNLP (LAW, DMR) 2021 • Jessica Lin, Amir Zeldes
Previous work on Entity Linking has focused on resources targeting non-nested proper named entity mentions, often in data from Wikipedia, i. e. Wikification.
Ranked #1 on Entity Linking on GUM
no code implementations • 27 Dec 2020 • Kai Trepka, Govind Bindra, Haley Langan, Jessica Lin, Kristina Linko, Henry Tsang, Nare Janvelyan, Fanny Hiebel, Ye Tao
The controllable handling of an arbitrary single particle of matter with sub-100 nanometer (nm) dimensions is an essential but unsolved scientific challenge.
Materials Science Mesoscale and Nanoscale Physics
1 code implementation • 30 Jan 2020 • Li Zhang, Yifeng Gao, Jessica Lin
Finding anomalous subsequence in a long time series is a very important but difficult problem.
no code implementations • 29 Jan 2020 • Yifeng Gao, Jessica Lin, Constantin Brif
We demonstrate that the proposed ensemble approach can outperform existing grammar-induction-based approaches with different criteria for selection of parameter values.
1 code implementation • 20 Nov 2019 • Yifeng Gao, Jessica Lin
Despite the significant progress that has been made in recent single dimensional variable-length motif discovery work, detecting variable-length \textit{subdimensional motifs}---patterns that are simultaneously occurring only in a subset of dimensions in multivariate time series---remains a difficult task.