Discover maria-becker/LMs4Implicit-Knowledge-Generation Open Source

Stars
8
Rank 2,059,382 (Top 42 %)
Language
Python
Created about 3 years ago
Updated almost 3 years ago

maria-becker

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Code for equipping pretrained language models (BART, GPT-2, XLNet) with commonsense knowledge for generating implicit knowledge statements between two sentences, by (i) finetuning the models on corpora enriched with implicit information; and by (ii) constraining models with key concepts and commonsense knowledge paths connecting them.

CoCo-Ex

CoCo-Ex extracts meaningful concepts from natural language texts and maps them to conjunct concept nodes in ConceptNet, utilizing the maximum of relational information stored in the ConceptNet knowledge graph.

Python

IKAT-EN

English version of IKAT: A corpus consisting of high-quality human annotations of missing and implied information in argumentative texts. The data is further annotated with semantic clause types and commonsense knowledge relations.

Moralization

Jupyter Notebook

CO-NNECT

This repository contains our path generation framework Co-NNECT, in which we combine two models for establishing knowledge relations and paths between concepts from sentences, as a form of explicitation of implicit knowledge: COREC-LM (COmmonsense knowledge RElation Classification using Language Models), a relation classification system that we developed for classifying commonsense knowledge relations; and COMET, a target prediction system developed by Bosselut et al., 2019.

Python

IKAT-DE

German version of IKAT: A corpus consisting of high-quality human annotations of missing and implied information in argumentative texts. The data is further annotated with semantic clause types and commonsense knowledge relations.