vene/marseille
Mining Argument Structures with Expressive Inference (Linear and LSTM Engines)
Performs structured prediction of argument mining tasks (proposition classification and support relation extraction) using factor graphs solved with structured SVMs or RNNs, integrating Stanford CoreNLP and WING-NUS PDTB parser for preprocessing. Supports both linear models via pystruct/AD3 and neural approaches through DyNet, with a preprocessing pipeline for GloVe embeddings and dataset-specific feature extraction targeting CDCP and UKP argument mining benchmarks.
No commits in the last 6 months.
Stars
66
Forks
29
Language
Python
License
BSD-3-Clause
Category
Last pushed
Aug 01, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/vene/marseille"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
AMontgomerie/CEFR-English-Level-Predictor
NLP system for predicting the reading difficulty level of a text in terms of its CEFR level.
public-law/readability
How readable is your text? Provide a text input and get its grade level. Validated against the...
openderocknlp/vocabulary-level-grader
Analyzes the given text and determine what's the vocabulary level based on CEFR levels
intel/polite-guard
Source code for Intel's Polite Guard NLP project
debatelab/deepa2
Resources for creating, importing and using DeepA2 Argument Analysis Framework datasets