Semi-Supervised Learning for Neural Keyphrase Generation

08/21/2018
by   Hai Ye, et al.
0

We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance on this task (Meng et al., 2017), model training often relies on large amounts of labeled data, which is only applicable to resource-rich domains. In this paper, we propose semi-supervised keyphrase generation methods by leveraging both labeled data and large-scale unlabeled samples for learning. Two strategies are proposed. First, unlabeled documents are first tagged with synthetic keyphrases obtained from unsupervised keyphrase extraction methods or a selflearning algorithm, and then combined with labeled samples for training. Furthermore, we investigate a multi-task learning framework to jointly learn to generate keyphrases as well as the titles of the articles. Experimental results show that our semi-supervised learning-based methods outperform a state-of-the-art model trained with labeled data only.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/22/2018

Semi-Supervised Sequence Modeling with Cross-View Training

Unsupervised representation learning algorithms such as word2vec and ELM...
research
03/26/2019

Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression

In the task of Autonomous aerial filming of a moving actor (e.g. a perso...
research
07/26/2018

Concurrent Learning of Semantic Relations

Discovering whether words are semantically related and identifying the s...
research
07/22/2023

Collaboratively Learning Linear Models with Structured Missing Data

We study the problem of collaboratively learning least squares estimates...
research
10/19/2021

Neural Medication Extraction: A Comparison of Recent Models in Supervised and Semi-supervised Learning Settings

Drug prescriptions are essential information that must be encoded in ele...
research
06/18/2021

Evolving GANs: When Contradictions Turn into Compliance

Limited availability of labeled-data makes any supervised learning probl...

Please sign up or login with your details

Forgot password? Click here to reset