Skip to content
Implementation of NAACL'19 Strong and Simple Baselines for Multimodal Utterance Embeddings
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
pom add pom data Jun 4, 2019

An implementation of baselines for multimodal utterance embedding, as described in

Based on original SIF implementation) by Arora et al. (2016, 2017).

Requires Python 3.


Processed data for the MOSI and POM datasets used in the code can be obtained from here, and should be saved in the folder data/. Alternatively, you can get the raw data here.


configs/ contains JSON files that holds the hyperparameters of the model. To generate some config files, run python configs/ These will be saved in configs/multimodal_search.

Then, to run MMB2,

python configs/multimodal_search/config_0.json $DATASET

where $DATASET is mosi or pom.

For MMB1, set the --unimodal flag:

python configs/multimodal_search/config_0.json $DATASET --unimodal

Run python --help for more options`.


This code is released under the MIT License. See LICENSE for more details.

You can’t perform that action at this time.