A neural-symbolic joint reasoning approach for Natural Language Inference (NLI). Modeling NLI as inference path planning through a search engine. Sequence chunking and neural paraphrase detection for syntactic variation. SOTA result on SICK and MED.
natural-language-processing
language-model
natural-language-inference
neural-symbolic-reasoning
phrase-alignment
computational-semantics
bert-embeddings
-
Updated
Jun 9, 2021 - Jupyter Notebook