Distant IE by Bootstrapping Using Lists and Document Structure
Authors: Lidong Bing, Mingyang Ling, Richard Wang, William Cohen
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments are conducted on two corpora, for diseases and drugs, and the results show that this approach significantly improves over a classical distant-supervision approach. |
| Researcher Affiliation | Collaboration | Carnegie Mellon University, Pittsburgh, PA 15213 US Development Center, Baidu USA, Sunnyvale, CA 94089 {lbing@cs, mingyanl@andrew, wcohen@cs}.cmu.edu richardwang@baidu.com |
| Pseudocode | No | No structured pseudocode or algorithm blocks were found. Algorithms are described in prose. |
| Open Source Code | No | The paper links to ProPPR, a tool used in their work ("3https://github.com/Team Cohen/Pro PPR"), but does not provide a link or statement for the open-source code of their specific methodology, DIEBOLDS. |
| Open Datasets | Yes | Our target drug corpus, called Daily Med, is downloaded from dailymed.nlm.nih.gov which contains 28,590 XML documents... Our target disease corpus, called Wiki Disease, is extracted from a Wikipedia dump of May 2015... The structured drug corpus, called Web MD, is collected from www.webmd.com... The structured disease corpus, called Mayo Clinic, is collected from www.mayoclinic.org. |
| Dataset Splits | Yes | These triples are split into development set and validating set in the ratio of 9:1. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments were provided. |
| Software Dependencies | No | The paper mentions various software components and tools such as "GDep parser", "Multi Rank Walk (MRW)", "Pro PPR", and "SVM classifier (Chang and Lin 2001)" (with a link to LIBSVM), but does not provide specific version numbers for these or other software dependencies. |
| Experiment Setup | Yes | We adopt an existing multi-class label propagation method, namely, Multi Rank Walk (MRW) (Lin and Cohen 2010)... (In the experiments we use α = 0.1.) |