DCN+: Mixed Objective And Deep Residual Coattention for Question Answering

Authors: Caiming Xiong, Victor Zhong, Richard Socher

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

Reproducibility Variable Result LLM Response
Research Type Experimental On the Stanford Question Answering Dataset, our model achieves state-of-the-art results with 75.1% exact match accuracy and 83.1% F1, while the ensemble obtains 78.9% exact match accuracy and 86.0% F1. We train and evaluate our model on the Stanford Question Answering Dataset (SQu AD). We show our test performance of our model against other published models, and demonstrate the importance of our proposals via ablation studies on the development set.
Researcher Affiliation Industry Caiming Xiong , Victor Zhong , Richard Socher Salesforce Research Palo Alto, CA 94301, USA {cxiong, vzhong, rsocher}@salesforce.com
Pseudocode No The paper includes figures illustrating network architecture (Figure 1) and computation flow (Figure 2), but it does not contain any explicitly labeled 'Pseudocode' or 'Algorithm' blocks, nor does it present structured steps for a method in a code-like format.
Open Source Code No The paper does not contain any explicit statements about releasing source code or provide a link to a code repository for the methodology described.
Open Datasets Yes We train and evaluate our model on the Stanford Question Answering Dataset (SQu AD) (Rajpurkar et al., 2016)
Dataset Splits Yes We train and evaluate our model on the Stanford Question Answering Dataset (SQu AD). We show our test performance of our model against other published models, and demonstrate the importance of our proposals via ablation studies on the development set.
Hardware Specification No The paper does not provide any specific hardware details such as GPU models, CPU types, or memory specifications used for running the experiments.
Software Dependencies No The paper mentions 'Py Torch' for implementation and 'ADAM' for optimization, and uses 'the reversible tokenizer from Stanford Core NLP', but it does not specify version numbers for any of these software components or libraries.
Experiment Setup Yes The model is trained using ADAM (Kingma & Ba, 2014) with default hyperparameters. Hyperparameters of our model are identical to the DCN. We implement our model using Py Torch. We perform word dropout on the document which zeros a word embedding with probability 0.075.