Multi-Document Abstractive Summarization Using ILP Based Multi-Sentence Compression
Authors: Siddhartha Banerjee, Prasenjit Mitra, Kazunari Sugiyama
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on the DUC 2004 and 2005 multi-document summarization datasets show that our proposed approach outperforms all the baselines and state-of-the-art extractive summarizers as measured by the ROUGE scores. |
| Researcher Affiliation | Academia | Siddhartha Banerjee The Pennsylvania State University University Park, PA, USA sub253@ist.psu.edu Prasenjit Mitra QCRI Doha, Qatar pmitra@qf.org.qa Kazunari Sugiyama National University of Singapore Singapore sugiyama@comp.nus.sg |
| Pseudocode | No | The paper describes procedural steps in paragraph form but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link regarding the open-sourcing of the code for the described methodology. |
| Open Datasets | Yes | We evaluated our approach on the DUC 2004 and 2005 datasets on multi-document summarization. We use ROUGE (Recall-Oriented Understudy of Gisting Evaluation) [Lin, 2004] for automatic evaluation of summaries (compared against human-written model summaries) as it has been proven effective in measuring qualities of summaries and correlates well to human judgments. http://duc.nist.gov/data.html |
| Dataset Splits | No | The paper mentions evaluating on the DUC 2004 and 2005 datasets but does not specify any training, validation, and test splits for their own model's development or reproduction. It notes that a 3-gram language model was 'trained on the English Gigaword corpus', but this refers to a component, not the overall experimental dataset splitting. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments, such as CPU or GPU models. |
| Software Dependencies | No | The paper mentions using a '3gram language model that is trained on the English Gigaword corpus' with a link to http://www.keithv.com/software/giga/, and refers to the 'Stanford Dependency Parser [Chen and Manning, 2014]'. However, it does not provide specific version numbers for the overall software environment or libraries used to implement their system. |
| Experiment Setup | Yes | The damping factor d is usually set to 0.85, and we set d to this value in our implementation. We set the minimum path length (in words) to eight to avoid incomplete sentences. Finally, we retain a maximum of 200 randomly selected paths from each cluster to reduce computational overload of the ILP based approach. |