Skip to content

Codebase for the paper (Accepted at COLING2025 main): RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents

Notifications You must be signed in to change notification settings

sayantan11995/Context_based_Quote_Extraction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

Paragraph Ranking

Dataset: [[ctx_id, [pos_doc_id], [neg_doc_id * (n-1), pos_doc_id]], ..] => dataset_n_neg.pkl labels: {'ctx_id1': [pos_doc_id1, pos_doc_id2, pos_doc_id3], 'ctx_id2': [pos_doc_id1, pos_doc_id2], ..} => labels_n_neg.pkl ctxid_to_text: {ctx_id1: ctx1, ctx_id2: ctx2, ..} docid_to_text: {doc_id1: doc1, doc_id2: doc2, ..}

Full system eval data

full_system_data_: {ctxid: [quote_id, para_id]}

About

Codebase for the paper (Accepted at COLING2025 main): RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages