summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorcarhaas <carhaas1@gmail.com>2014-09-09 09:33:58 +0200
committercarhaas <carhaas1@gmail.com>2014-09-09 09:33:58 +0200
commit03ba5d8a8178f136dbddf818ae4d8c2403415a5e (patch)
treefbd75892fbde70f2d1c2edc2233d56cfcb7dfa5a
parent4dd862953695849412cef0d8d840266a0a8c86cf (diff)
update with Free917 info
-rw-r--r--README.md6
1 files changed, 3 insertions, 3 deletions
diff --git a/README.md b/README.md
index c804a8c..7c600d3 100644
--- a/README.md
+++ b/README.md
@@ -9,7 +9,7 @@ Code for grounded SMT on geoquery data or Free917 data.
Dependencies
------------
-Geoquery:
+###Geoquery:
_WASP_-1.0 includes the geoquery knowledge base and scripts for querying it.
The evaluation scripts were slightly modified to produce full outputs.
These scripts can be found in data/geoquery/wasp/, and they go into wasp-1.0/data/geo-funql/eval/.
@@ -22,12 +22,12 @@ as described in *Semantic parsing as machine translation* (Andreas et al, ACL 20
Our fork can be found here [3]. This software depends on more stuff, e.g. the Moses decoder
and SRILM.
-Free917:
+###Free917:
The parser used for Free917 is _sempre_,
as described in *Semantic Parsing on Freebase from Question-Answer Pairs* (Berant et al, EMNLP 2013).
It can be downloaded here [4] and further dependencies can be found in QUICKSTART.md.
-Both:
+###Both:
For translation we use the _cdec_ toolkit, [5].
As semantic parsing is quite slow and rebol does it quite often,