XplaiNLI: eXplainable Natural Language Inference
XplainNLI is an interactive, user-friendly, visualization interface for NLI. It computes inference with a deep learning (DL), a symbolic and a hybrid approach and attempts to explain which features lead to the decision of each component. The user can define their own heuristics as potential explanations for the decisions and also annotate the pair with the correct label. More details in our paper:
Kalouli, A.-L., R. Sevastjanova, R. Crouch, V. de Paiva and M. El-Assady. 2020. XplaiNLI: Explainable Natural Language Inferencethrough Visual Analytics. In Proceedings of the COLING 2020 System Demonstrations.
Note that XplaiNLI targets explainability, rather than performance. If you are interested in the performance of our system, check out our demo on Hy-NLI
Download
The source code of XplaiNLI is publicly available on github .
Demo
Enter a sentence pair below:
You can also choose from the given examples:
Explanation
After exploring the visualization, click on the inference label that you think is correct for this pair. Thanks for your feedback!
WARNING: The visualization has only been tested on Safari, Firefox and Chrome.
Publications
- Hy-NLI : a Hybrid system for state-of-the-art Natural Language Inference Kalouli, A.-L. 2021. Dissertation. Konstanz: University of Konstanz
- Explainable Natural Language Inference through Visual Analytics . Kalouli, A.-L., R. Sevastjanova, R. Crouch, V. de Paiva and M. El-Assady. 2020. In Proceedings of the COLING 2020 System Demonstrations.
- Hy-NLI: a Hybrid system for Natural Language Inference . Kalouli, A.-L., R. Crouch and V. de Paiva. 2020. In Proceedings of COLING 2020.
- explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning. Spinner T., U. Schlegel, H. Schaefer, and M. El-Assady. 2020. IEEE Transactions on Visualization and Computer Graphics.
- GKR: Bridging the gap between symbolic/structural and distributional meaning representations Kalouli, A.-L., R. Crouch and V. de Paiva. 2019, 1st International Workshop on Designing Meaning Representations (DMR) @ACL 2019.
- lingvis.io - A Linguistic Visual Analytics Framework El-Assady M., W. Jentner, F. Sperrle, R. Sevastjanova, A. Hautli-Janisz, M. Butt and D. Keim. 2019. ACL 2019 System Demo.
- GKR: the Graphical Knowledge Representation for semantic parsing Kalouli, A.-L. and R. Crouch. 2018. SEMBEaR @NAACL 2018.
- Named Graphs for Semantic Representations Crouch, R. and A.-L. Kalouli. 2018. *SEM 2018.
- Graph Knowledge Representations for SICK Kalouli, A.-L., R. Crouch, V. de Paiva and L. Real. 2018. 5th Workshop on Natural Language and Computer Science @FLoC 2018
Contact
- Katerina: katerina (dot) kalouli (at) hotmail (dot) com (check out my homepage for more similar projects)
- Rita: rita (dot) sevastjanova (at) uni (dash) konstanz(dot) de
- Dick: dick (dot) crouch (at) gmail (dot)com
- Menna: mennatallah (dot) el-assady (at) uni (dash) konstanz(dot) de
- Valeria: valeria (dot) depaiva (at) gmail (dot) com