This paper describes the system that we submitted to the \Learning Language in Logic" Challenge of extracting directed genic interactions from sentences in Medline abstracts. The system uses Markov Logic, a framework that combines log-linear models and First Order Logic, to create a set of weighted clauses which can classify pairs of gene named entities as genic interactions. These clauses are based on chains of syntactic and semantic relations in the parse or Discourse Representation Structure (drs) of a sentence, respectively. Our submitted results achieved 52.6% F-Measure on the dataset without and 54.3% on the dataset with coreferences. After adding explicit clauses which model noninteraction we were able to improve these numbers to 68.4% and 64.7%, respectively.
[1]
Uwe Reyle,et al.
From discourse to logic
,
1993
.
[2]
Mark Steedman,et al.
The syntactic process
,
2004,
Language, speech, and communication.
[3]
Jorge Nocedal,et al.
On the limited memory BFGS method for large scale optimization
,
1989,
Math. Program..
[4]
Tomek Strzalkowski,et al.
From Discourse to Logic
,
1991
.
[5]
James R. Curran,et al.
Parsing the WSJ Using CCG and Log-Linear Models
,
2004,
ACL.
[6]
Ben Taskar,et al.
Markov Logic: A Unifying Framework for Statistical Relational Learning
,
2007
.
[7]
Johan Bos.
Towards Wide-Coverage Semantic Interpretation
,
2005
.