Distant Supervision for Relation Extraction with Sentence-Level Attention and Entity Descriptions

Authors: Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct three experiments on a widely used dataset and the experimental results show that our approach outperforms all the baseline systems significantly.
Researcher Affiliation Academia Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao National Laboratory of Pattern Recognition (NLPR) Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China {guoliang.ji, kliu, shizhu.he, jzhao}@nlpr.ia.ac.cn
Pseudocode No The paper describes its models and formulas but does not include a clearly labeled 'Pseudocode' or 'Algorithm' block.
Open Source Code No The paper does not provide a specific link to the source code for its methodology or explicitly state that the code is being released.
Open Datasets Yes We evaluate our approach using the dataset developed by (Riedel, Yao, and Mc Callum 2010) by aligning Freebase5 relations with the New York Times (NYT) corpus.
Dataset Splits Yes In our experiments, we tune all of the models using three-fold validation on the training set.
Hardware Specification No The paper does not explicitly describe the specific hardware (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions training word embeddings with 'word2vec' and provides a general link, but it does not specify version numbers for word2vec or any other ancillary software components.
Experiment Setup Yes The best configurations are: kw = 50, kd = 5, w = 3, n = 200, λ = 0.01, the batch size is 50. Following (Hinton et al. 2012), we set the dropout rate 0.5.