If No Media Were Allowed inside the Venue, Was Anybody Allowed? Page: 862
The following text was automatically extracted from the image on this page using optical character recognition software:
a,>a T m 1 a"Oa~a C o
a c~a E 8M L , o- N 0
- - U o
I ii 111111! !II!' "7m
a, ma" >. L N_ .>, d > ,a a'a a, ma O 1 NN
m ~ ~ w aO6-- . L ooLo o-
M~~a E,- ID t E3O-c
a ~ E~ - o_
Figure 1: Most frequent nouns (left) and adjectives (right) tokens that are negated (neg dependency) in
OntoNotes. Total number of noun and adjective tokens modified by a negation cue is 1,866 and 979.
Focus of Negation and Positive Interpretations.
Identifying the focus of negation is equivalent to
revealing positive interpretations-everything but
the focus is actually positive. The definition of
focus does not specify annotation guidelines, and
most existing efforts are grounded on semantic
roles. Blanco and Moldovan (2011) annotate fo-
cus on the negations marked with ARGM-NEG role
in PropBank (Palmer et al., 2005). They select
a single focus per negation, specifically, they se-
lect the role that reveals the "most useful [positive]
information." Anand and Martell (2012) refine
these annotations and differentiate positive inter-
pretations arising from focus identification, scalar
implicature and neg-raising predicates. Blanco
and Sarabi (2016) propose a similar approach that
scores the likelihood of several potential foci per
negation. The main limitations of all these previ-
ous works is that selecting as focus a semantic role
is only suitable when the negation cue modifies
a predicate, and roles often yield coarse-grained
interpretations. Sarabi and Blanco (2016) bypass
these drawbacks by working with syntactic depen-
dencies to refine coarse-grained interpretations.
All these previous efforts to reveal positive in-
terpretations from negation target exclusively ver-
bal negation, i.e., when the negation cue modifies
a verb. While verbal negation is more frequent
(64.4% of neg dependencies in OntoNotes, Sec-
tion 4), in this paper we target two understudied
yet important negations: when the negation cue
modifies a noun or adjective (19.6% and 10.3% of
neg dependencies). Our approach is not grounded
on semantic roles but syntactic dependencies. Do-
ing so allows us to tackle negation when the nega-
tion cue modifies nouns or adjectives.
4 Corpus Creation
We create a corpus of negations and their posi-
tive interpretations following three steps. First,
we select negations whose negation cue syntac-
tically modifies either a noun or adjective. Sec-
ond, we automatically generate potential positive
from those negations by manipulating syntactic
dependencies and part-of-speech tags. Third, we
gather manual annotations to validate and score
potential interpretations. While asking annotators
to suggest positive interpretations would poten-
tially yield more natural interpretations, we found
experimentally that a generate-and-rank approach
yields higher quality annotations.
Negation in OntoNotes. Instead of building our
corpus from plain text, we decided to work on
top of OntoNotes (Hovy et al., 2006), a publicly
available corpus including texts in several genres
(news, transcripts, magazines, etc.).2 OntoNotes
includes, among other gold linguistic annotations,
part-of-speech tags and parse trees. We trans-
formed the parse trees into syntactic dependencies
using Stanford CoreNLP (Manning et al., 2014).
We reduce the problem of finding negations
to retrieving syntactic dependencies neg, which
stands for negation modifier. Doing so ignores
negation cues that are prefixes or suffixes (e.g.,
unlimited, motionless), but also simplifies the
process. There are 9,507 neg syntactic depen-
dencies in OntoNotes; 6,120 of them modify
verbs (64.4%), 1,866 nouns (19.6%), 979 adjec-
tives (10.3%), and 543 other part-of-speech tags
(5.7%). Since verbal negation has been tackled
2We use the CoNLL-2011 Shared Task distribution (Prad-
han et al., 2011), http://conll.cemantix.org/2011/
Here’s what’s next.
This paper can be searched. Note: Results may vary based on the legibility of text within the document.
Tools / Downloads
Get a copy of this page or view the extracted text.
Citing and Sharing
Basic information for referencing this web page. We also provide extended guidance on usage rights, references, copying or embedding.
Reference the current page of this Paper.
Sarabi, Zahra & Blanco, Eduardo. If No Media Were Allowed inside the Venue, Was Anybody Allowed?, paper, April 2017; Stroudsburg, Pennsylvania. (digital.library.unt.edu/ark:/67531/metadc993391/m1/3/: accessed November 19, 2018), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT College of Engineering.