Multi-Dimensional Explanation of Target Variables from Documents

Authors: Diego Antognini, Claudiu Musat, Boi Faltings12507-12515

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate MTM on two datasets and show, using standard metrics and human annotations, that the resulting masks are more accurate and coherent than those generated by the state-of-the-art methods. Moreover, MTM is the first to also achieve the highest F1 scores for all the target variables simultaneously.
Researcher Affiliation Collaboration 1Ecole Polytechnique F ed erale de Lausanne, Switzerland 2Swisscom, Switzerland
Pseudocode No The paper provides a model overview and architecture diagram (Figure 2) and mathematical formulations, but no structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes (Mc Auley, Leskovec, and Jurafsky 2012) provided 1.5 million English beer reviews from Beer Advocat. For the hotel domain, we sampled 140 000 hotel reviews from (Antognini and Faltings 2020), that contains 50 million reviews from Trip Advisor.
Dataset Splits Yes We split the data into 80/10/10 for the train, validation, and test sets.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions software components like 'word2vec', 'Adam', and 'dropout' but does not specify their version numbers, which is required for reproducibility.
Experiment Setup Yes We used a dropout (Srivastava et al. 2014) of 0.1, clipped the gradient norm at 1.0, added a L2-norm regularizer with a factor of 10 6, and trained using early stopping. We used Adam (Kingma and Ba 2015) with a learning rate of 0.001. The temperature τ for the Gumbel-Softmax distributions was fixed at 0.8. The two regularizers and the prior of our model were λsel = 0.03, λcont = 0.03, and λp = 0.15 for the Beer dataset and λsel = 0.02, λcont = 0.02, and λp = 0.10 for the Hotel one. We ran all experiments for a maximum of 50 epochs with a batch-size of 256.