USCDataScience / parser-indexer-py

Python tools for parsing documents and building the inverted index with enriched metadata. Java version with slightly different features - https://github.com/USCDataScience/parser-indexer
Apache License 2.0
9 stars 3 forks source link

Support cross-sentence relation extraction with jSRE #34

Open wkiri opened 3 years ago

wkiri commented 3 years ago

We discussed trying a simple approach to enable jSRE to propose cross-sentence relations. Given a window parameterized by k, this approach will concatenate the current sentence +/- k sentences into a pseudo-sentence by removing terminal punctuation and adding a semi-colon, or the word "and", to join sentences together. (May also need to lower-case the first word in the concatenated sentence?)

Then, entities that are candidates for a jSRE relation can be gathered from the entire pseudo-sentence instead of just the current sentence. We are interested in comparing this approach to Yuan's cross-sentence relation extraction methods.

wkiri commented 3 years ago

One idea is to create a superclass like RelationExtractionParser to handle the "k" window argument for simple concatenation.