Enhancing Semantic Role Labeling for Tweets Using Self-Training

  title={Enhancing Semantic Role Labeling for Tweets Using Self-Training},
  author={Xiaohua Liu and Kuanyu Li and Ming Zhou and Zhongyang Xiong},
Semantic Role Labeling (SRL) for tweets is a meaningful task that can benefit a wide range of applications such as finegrained information extraction and retrieval from tweets. One main challenge of the task is the lack of annotated tweets, which is required to train a statistical model. We introduce self-training to SRL, leveraging abundant unlabeled tweets to alleviate its depending on annotated tweets. A novel strategy of tweet selection is presented, ensuring the chosen tweets are both… CONTINUE READING

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • We evaluate our method on a human annotated data set and show that bootstrapping improve a baseline by 3.4% F1.


Publications referenced by this paper.
Showing 1-10 of 30 references

Semantic Role Labeling for News Tweets

COLING • 2010
View 14 Excerpts
Highly Influenced

Markov logic networks

Machine Learning • 2006
View 8 Excerpts
Highly Influenced

mantic role labeling as sequential tagging

L. Màrquez, P. Comas, J. Giménez, N. Català
View 5 Excerpts
Highly Influenced