Skip to content
No description, website, or topics provided.
Branch: master
Clone or download
Latest commit 51a6049 Mar 5, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
README.md Update README.md Mar 5, 2019

README.md

test-repo

Document Retrieval google knowledge graph Doing graph search over structured knolwedge rather than traditional search

Approaches to Question Answering:

1.Knowledge Based Approach -Build a semantic representation of the query : Times, Dates, locations, entities, numeric quantities -Map from this semantics to query structured data or resources Eg: Geospatial databases, Ontologies(Wikipedia Infoboxes, dbPedia, WordNet, Yago)

  1. Text Based(Mainly Factoid) QA -Question Processing: Detect question type, answer type, focus, relations. Formulate queries to send to a search engine -Passage Retrieval: Retrieve ranked documents. Break into suitable passages and rerank -Answer Processing: Extract candidate answers(as named entities). Rank candidates(using evidence from relations in the text and external sources)

  2. Hybrid Approaches -Build a shallow representation of the query -Genearte answer candidates using IR methods: Augmented with ontologies and semi-structured data -Score each candidate using richer knowledge sources

Document Retreival Research Papers

Improving Document Ranking with Dual Word Embeddings https://www.microsoft.com/en-us/research/publication/improving-document-ranking-with-dual-word-embeddings/?from=http%3A%2F%2Fresearch.microsoft.com%2Fpubs%2F260867%2Fpp1291-nalisnick.pdf

A Dual Embedding Space Model for Document Ranking https://arxiv.org/abs/1602.01137

You can’t perform that action at this time.