aboutsummaryrefslogtreecommitdiff
path: root/Plan.md
diff options
context:
space:
mode:
authorxPaulienx2017-09-29 11:37:25 +0200
committerGitHub2017-09-29 11:37:25 +0200
commit01853a90ec43a0279a00e0b9272b4cfdc9ec90a3 (patch)
treebad57e82affbc54f26b34a482da783c23a2da4b3 /Plan.md
parentInstallation instructions (diff)
Update Plan.md
Diffstat (limited to 'Plan.md')
-rw-r--r--Plan.md7
1 files changed, 7 insertions, 0 deletions
diff --git a/Plan.md b/Plan.md
index f0be4fb..c06cba9 100644
--- a/Plan.md
+++ b/Plan.md
@@ -32,8 +32,15 @@ Our hypothesis is that not all of the fields are of similar importance.
As such, our idea is to use some kind of Hill-Climbing algorithm to determine just what combination of fields (or possible weights) produces the best output.
## Nordlys
+Nordlyss is a toolkit for entity-oriented and semantic search. It currently supports four entity-oriented tasks, which could be useful for our project. These entity-oriented tasks are:
+- `Entity cataloging`
+- `Entity retrieval`
+- `Entity linking in queries`
+- `Target type identification`
The Nordlys toolkit was used to create the results described above, as such, it provides us with the means to reproduce these results.
In addition, Nordlys provides a Python interface that can be used to implement the Hill Climbing algorithm.
The data that is used by the results is also bundled with the Nordlys Python package, and has already been indexed.
This allows us to use the Python package without having to convert/index the data ourselves.
+
+