paper-with-me

Papers

A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution

2021-04-04 · NAACL 2021 4 · Tuan Lai, Heng Ji, Trung Bui, Quan Hung Tran, Franck Dernoncourt, Walter Chang

Event coreference resolution is an important research problem with many applications. Despite the recent remarkable success of pretrained language models, we argue that it is still highly beneficial to utilize symbolic features for the task. However, as the input for coreference resolution typically comes from upstream components in the information extraction pipeline, the automatically extracted symbolic features can be noisy and contain errors. Also, depending on the specific context, some features can be more informative than others. Motivated by these observations, we propose a novel context-dependent gated module to adaptively control the information flows from the input symbolic features. Combined with a simple noisy training method, our best models achieve state-of-the-art results on two datasets: ACE 2005 and KBP 2016.

📄 PDF Abstract BibTeX arXiv:2104.01697

Code (1)

laituan245/eventcoref 공식 구현 pytorch

Tasks

coreference-resolutionCoreference ResolutionEvent Coreference Resolution

Similar Papers 제목 키워드 기반

In-Context Symbolic Regression for Robustness-Improved Kolmogorov-Arnold Networks

2026-03-16 · Francesco Sovrano, Lidia Losavio, Giulia Vilone, Marc Langheinrich arxiv

Symbolic regression aims to replace black-box predictors with concise analytical expressions that can be inspected and validated in scientific machine learning. Kolmogorov-Arnold Networks (KANs) are well suited to this g…

Context-PIPs: Persistent Independent Particles Demands Spatial Context Features

2023-06-03 · Weikang Bian, Zhaoyang Huang, Xiaoyu Shi, Yitong Dong 외

We tackle the problem of Persistent Independent Particles (PIPs), also called Tracking Any Point (TAP), in videos, which specifically aims at estimating persistent long-term trajectories of query points in videos. Previo…

Point Tracking

Context-PIPs: Persistent Independent Particles Demands Context Features

2023-09-21 · NeurIPS 2023 11

We tackle the problem of Persistent Independent Particles (PIPs), also called Tracking Any Point (TAP), in videos, which specifically aims at estimating persistent long-term trajectories of query points in videos. Previo…

Symbolic Graph Reasoning Meets Convolutions

2018-12-01 · NeurIPS 2018 12 · Xiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin 외

Beyond local convolution networks, we explore how to harness various external human knowledge for endowing the networks with the capability of semantic global reasoning. Rather than using separate graphical models (e.g. …

image-classificationImage ClassificationSemantic Segmentation

SymDQN: Symbolic Knowledge and Reasoning in Neural Network-based Reinforcement Learning

2025-04-03 · Ivo Amador, Nina Gierasimczuk

We propose a learning architecture that allows symbolic control and guidance in reinforcement learning with deep neural networks. We introduce SymDQN, a novel modular approach that augments the existing Dueling Deep Q-Ne…

reinforcement-learningReinforcement LearningTensor Networks