CARLA
Stanza
CARLA | Stanza | |
---|---|---|
2 | 8 | |
263 | 7,047 | |
0.4% | 1.1% | |
0.0 | 9.8 | |
7 months ago | 6 days ago | |
Python | Python | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
CARLA
-
[R] CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
Abstract: Counterfactual explanations provide means for prescriptive model explanations by suggesting actionable feature changes (e.g., increase income) that allow individuals to achieve favourable outcomes in the future (e.g., insurance approval). Choosing an appropriate method is a crucial aspect for meaningful counterfactual explanations. As documented in recent reviews, there exists a quickly growing literature with available methods. Yet, in the absence of widely available open–source implementations, the decision in favour of certain models is primarily based on what is readily available. Going forward – to guarantee meaningful comparisons across explanation methods – we present CARLA (Counterfactual And Recourse Library), a python library for benchmarking counterfactual explanation methods across both different data sets and different machine learning models. In summary, our work provides the following contributions: (i) an extensive benchmark of 11 popular counterfactual explanation methods, (ii) a benchmarking framework for research on future counterfactual explanation methods, and (iii) a standardized set of integrated evaluation measures and data sets for transparent and extensive comparisons of these methods. We have open sourced CARLA and our experimental results on GitHub, making them available as competitive baselines. We welcome contributions from other research groups and practitioners.
-
University of Tübingen Researchers Open-Source ‘CARLA’, A Python Library for Benchmarking Counterfactual Explanation Methods Across Data Sets and Machine Learning Models
4 Min Read| Paper | Github
Stanza
- Down and Out in the Magic Kingdom
-
Parts of speech tagged for German
I use Python's spacy library: https://spacy.io/models/de or stanza: https://stanfordnlp.github.io/stanza/ each with their respective language models.
-
Off the shelf sentence parsers?
stanza has a constituency parser. There's a model compatible with the dev branch with an accuracy of 95.8 on PTB, using Roberta as a bottom layer, so it's pretty decent at this point. (The currently released model is not as accurate, but it's easy to get the better model to you.) There's also Tregex as a Java addon which can very easily search for a noun phrase highest up in the tree: NP !>> NP will search for a noun phrase which is not dominated by any higher up noun phrase.
- The Spacy NER model for Spanish is terrible
- Spacy vs NLTK for Spanish Language Statistical Tasks
-
Stanza not tokenising sentences as expected
I am using Stanza to tokenise the sentences:
- Stanza – A Python NLP Package for Many Human Languages
What are some alternatives?
carla - Open-source simulator for autonomous driving research.
spaCy - 💫 Industrial-strength Natural Language Processing (NLP) in Python
shapash - 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
NLTK - NLTK Source
rliable - [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.
BERT-NER - Pytorch-Named-Entity-Recognition-with-BERT
alibi - Algorithms for explaining machine learning models
Jieba - 结巴中文分词
pytorch-lightning - Build high-performance AI models with PyTorch Lightning (organized PyTorch). Deploy models with Lightning Apps (organized Python to build end-to-end ML systems). [Moved to: https://github.com/Lightning-AI/lightning]
flair - A very simple framework for state-of-the-art Natural Language Processing (NLP)
DiCE - Generate Diverse Counterfactual Explanations for any machine learning model.
pytext - A natural language modeling framework based on PyTorch