2 |
Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
HittER: Hierarchical Transformers for Knowledge Graph Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
AttentionRank: Unsupervised Keyphrase Extraction using Self and Cross Attentions ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Extracting Event Temporal Relations via Hyperbolic Geometry ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity Typing ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Entity Relation Extraction as Dependency Parsing in Visually Rich Documents ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Lifelong Event Detection with Knowledge Transfer ...
|
|
|
|
Abstract:
Anthology paper link: https://aclanthology.org/2021.emnlp-main.428/ Abstract: Traditional supervised Information Extraction (IE) methods can extract structured knowledge elements from unstructured data, but they are limited to a pre-defined target ontology. In reality, the ontology of interest may change over time, adding emergent new types or more fine-grained subtypes. We propose a new lifelong learning framework to address this challenge. We focus on lifelong event detection as an exemplar case and propose a new problem formulation that is also generalizable to other IE tasks. In event detection and more general IE tasks, rich correlations or semantic relatedness exist among hierarchical knowledge element types. In our proposed framework, knowledge is being transferred between learned old event types and new event types. Specifically, we update old knowledge with the mentions of new event types. Experimental results show that our framework outperforms competitive baselines with a 5.1% absolute gain in the ...
|
|
Keyword:
Computational Linguistics; Information Extraction; Machine Learning; Machine Learning and Data Mining; Natural Language Processing
|
|
URL: https://dx.doi.org/10.48448/p2tr-jd17 https://underline.io/lecture/37546-lifelong-event-detection-with-knowledge-transfer
|
|
BASE
|
|
Hide details
|
|
18 |
SUBSUME: A Dataset for Subjective Summary Extraction from Wikipedia Documents ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Few-Shot Named Entity Recognition: An Empirical Baseline Study ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Low-resource Taxonomy Enrichment with Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|