-
giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration
We introduce giotto-tda, a Python library that integrates high-performan...
read it
-
Dodrio: Exploring Transformer Models with Interactive Visualization
Why do large pre-trained transformer-based models perform so well across...
read it
-
EXPATS: A Toolkit for Explainable Automated Text Scoring
Automated text scoring (ATS) tasks, such as automated essay scoring and ...
read it
-
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Recent studies have revealed a security threat to natural language proce...
read it
-
DART: Open-Domain Structured Data Record to Text Generation
We introduce DART, a large dataset for open-domain structured data recor...
read it
-
EasyTransfer – A Simple and Scalable Deep Transfer Learning Platform for NLP Applications
The literature has witnessed the success of applying deep Transfer Learn...
read it
-
A Data-Centric Framework for Composable NLP Workflows
Empirical natural language processing (NLP) systems in application domai...
read it
The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
We present the Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models. We focus on core questions about model behavior: Why did my model make this prediction? When does it perform poorly? What happens under a controlled change in the input? LIT integrates local explanations, aggregate analysis, and counterfactual generation into a streamlined, browser-based interface to enable rapid exploration and error analysis. We include case studies for a diverse set of workflows, including exploring counterfactuals for sentiment analysis, measuring gender bias in coreference systems, and exploring local behavior in text generation. LIT supports a wide range of models–including classification, seq2seq, and structured prediction–and is highly extensible through a declarative, framework-agnostic API. LIT is under active development, with code and full documentation available at https://github.com/pair-code/lit.
READ FULL TEXT
Comments
There are no comments yet.