doheejin/ProTACT
This repository is the implementation of the ProTACT architecture, introduced in the paper "Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring" (ACL Findings 2023).
This project helps educators or assessment specialists automatically grade student essays, especially when new essay prompts are used. It takes student essays and their corresponding prompts as input and outputs detailed scores for various writing traits (like coherence, grammar, or argumentation), even for essays written in response to prompts the system hasn't seen before. The end-user persona would be an educator, curriculum designer, or standardized testing organization responsible for evaluating written assignments.
No commits in the last 6 months.
Use this if you need to efficiently and consistently score large volumes of student essays for multiple writing traits, especially when you introduce new essay topics that don't have existing graded examples.
Not ideal if you only need a single, holistic score for essays written using prompts that have been previously graded and used for training.
Stars
23
Forks
6
Language
Python
License
BSD-3-Clause
Category
Last pushed
Feb 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/doheejin/ProTACT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gunthercox/chatterbot-corpus
A multilingual dialog corpus
EdinburghNLP/awesome-hallucination-detection
List of papers on hallucination detection in LLMs.
jfainberg/self_dialogue_corpus
The Self-dialogue Corpus - a collection of self-dialogues across music, movies and sports
jkkummerfeld/irc-disentanglement
Dataset and model for disentangling chat on IRC
Tomiinek/MultiWOZ_Evaluation
Unified MultiWOZ evaluation scripts for the context-to-response task.