Target-dependent sentiment classification in news articles reporting on political events. Includes a high-quality data set of over 11k sentences and a state-of-the-art classification model.
Add batching to sentiment classification. Training does not use batching yet (_create_item_for_model() and _create_target_inputs() in dataset.py need to be adjusted for that).
Add batching to sentiment classification. Training does not use batching yet (_create_item_for_model() and _create_target_inputs() in dataset.py need to be adjusted for that).
Also small bugfixes.