Easy-to-Hard Learning for Information Extraction

by   Chang Gao, et al.

Information extraction (IE) systems aim to automatically extract structured information, such as named entities, relations between entities, and events, from unstructured texts. While most existing work addresses a particular IE task, universally modeling various IE tasks with one model has achieved great success recently. Despite their success, they employ a one-stage learning strategy, i.e., directly learning to extract the target structure given the input text, which contradicts the human learning process. In this paper, we propose a unified easy-to-hard learning framework consisting of three stages, i.e., the easy stage, the hard stage, and the main stage, for IE by mimicking the human learning process. By breaking down the learning process into multiple stages, our framework facilitates the model to acquire general IE task knowledge and improve its generalization ability. Extensive experiments across four IE tasks demonstrate the effectiveness of our framework. We achieve new state-of-the-art results on 13 out of 17 datasets. Our code is available at <https://github.com/DAMO-NLP-SG/IE-E2H>.


page 1

page 2

page 3

page 4


Towards Generalizable and Robust Text-to-SQL Parsing

Text-to-SQL parsing tackles the problem of mapping natural language ques...

Learning to Minimize the Remainder in Supervised Learning

The learning process of deep learning methods usually updates the model'...

Dynamic Difficulty Awareness Training for Continuous Emotion Prediction

Time-continuous emotion prediction has become an increasingly compelling...

Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference

This paper focuses on the prevalent performance imbalance in the stages ...

Improving Open Information Extraction via Iterative Rank-Aware Learning

Open information extraction (IE) is the task of extracting open-domain a...

Exploring Task Difficulty for Few-Shot Relation Extraction

Few-shot relation extraction (FSRE) focuses on recognizing novel relatio...

Learning to Anticipate Future with Dynamic Context Removal

Anticipating future events is an essential feature for intelligent syste...

Please sign up or login with your details

Forgot password? Click here to reset