Dialog Frame Parser: Frame-semantic parser in Dialog

The model architecture itself is an extension of the frameBERT model.

About

The Dialog Frame Parser is a BERT-based frame-semantic parser to understand the meaning of dialog in terms of FrameNet.

frame (frame semantics) is a schematic representation of a situation or an event. For an example sentence, "The center's director pledged a thorough review of safety precedures", frameBERT identifies several frames such as Being_born and Death for lexical units (e.g., center.n, director.n and pledge.v).

dialog is a collection of multiple utterances. An utterance consists of a speaker and an utterance text.

The following is an example of a dialog.

prerequisite

• python 3
• pytorch (Link)
• transformers (Link)
• Korean FrameNet (Link)
• keras (Link)

Getting Started

Step 1: Install

git clone https://github.com/machinereading/Dialog_Frame_Parser.git

Step 2: Prepare the data

The sample data can be found input_data directory.

Step 3: Train the model

python train.py

• You can edit model_dir and data_path in 32-33 lines in train.py.

Step 4: Evaluate the model

python evaluate.py

• You can edit model_dir and data_path in 21-22 lines in evaluate.py.

Licenses

• CC BY-NC-SA Attribution-NonCommercial-ShareAlike
• If you want to commercialize this resource, please contact to us

Publisher

Machine Reading Lab @ KAIST

Contact

CHEOLHUN HEO. fairy_of_9@kaist.ac.kr

Acknowledgement

This work was supported by Institute for Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No.2017-0-01780, The technology development for event recognition/relational reasoning and learning knowledge based system for video understanding)