Learning to Explain Ambiguous Headlines of Online News

Authors: Tianyu Liu, Wei Wei, Xiaojun Wan

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Utilizing automatic and manual evaluation metrics, we demonstrate the efficacy and the complementarity of the two methods, and the ambiguity-aware neural matching model achieves the state-of-the-art performance on this challenging task.
Researcher Affiliation Academia Tianyu Liu, Wei Wei, Xiaojun Wan Institute of Computer Science and Technology, Peking University The MOE Key Laboratory of Computational Linguistics, Peking University {ty liu, weiwei718, wanxiaojun}@pku.edu.cn
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper mentions using 'Matchzoo Toolkit' with a GitHub link, but this is a third-party tool used by the authors, not the open-source code for their specific methodology. There is no explicit statement about releasing their own implementation's source code.
Open Datasets Yes We use the data set of [Wei and Wan, 2017], which contains 645 pieces of news with ambiguous headline.
Dataset Splits Yes The final data set contains 1500 pieces of news with ambiguous headline, with 1000 for training, 100 for validation and 400 for test.
Hardware Specification No No specific hardware (e.g., GPU model, CPU type, memory size, or cloud instance details) used for experiments is mentioned in the paper.
Software Dependencies Yes We use the ROUGE-1.5.5 toolkit to perform evaluation for the results.
Experiment Setup Yes For A2DRMM, we use 2-layer feed-forward network based on a histogram with the number of bins set to 60. For the gating network of A2DRMM, when using ambiguity-augmented embedding as input, we added a hidden layer of 5 nodes. All other parameters for training are set by default.