Semantic Representation of Negation Using Focus Detection
Blanco, Eduardo and Moldovan, Dan

Article Structure

Abstract

Negation is present in all human languages and it is used to reverse the polarity of part of statements that are otherwise affirmative by default.

Introduction

Understanding the meaning of text is a long term goal in the natural language processing community.

Related Work

Negation has been widely studied outside of computational linguistics.

Negation in Natural Language

Simply put, negation is a process that turns a statement into its opposite.

Approach to Semantic Representation of Negation

Negation does not stand on its own.

Learning Algorithm

We propose a supervised learning approach.

Experiments and Results

As a learning algorithm, we use bagging with C4.5 decision trees.

Conclusions

In this paper, we present a novel way to semantically represent negation using focus detection.

Topics

POS tags

Appears in 6 sentences as: POS tag (1) POS tags (5)
In Semantic Representation of Negation Using Focus Detection
  1. Features (1—5) are extracted for each role and capture their presence, first POS tag and word, length and position within the roles present for that instance.
    Page 7, “Learning Algorithm”
  2. Al—postag is extracted for the following POS tags : DT, JJ, PRP, CD, RB, VB and WP; Al—keywo rd for the following words: any, anybody, anymore, anyone, anything, anytime, anywhere, certain, enough, fall, many, much, other, some, specifics, too and until.
    Page 7, “Learning Algorithm”
  3. These lists of POS tags and keywords were extracted after manual examination of training examples and aim at signaling whether this role correspond to the focus.
    Page 7, “Learning Algorithm”
  4. Examples of A1 corresponding to the focus and including one of the POS tags or keywords are:
    Page 7, “Learning Algorithm”
  5. VP—words (VP —postag) captures the full sequence of words ( POS tags ) from the beginning of the VP until the main verb.
    Page 8, “Learning Algorithm”
  6. Features (15—16) check for POS tags as the presence of certain tags usually signal that the verb is not the focus of negation (e. g., [Thas]MDIS, he asserts, [Lloyd ’s ] A0 [ [ ca ]MMODn’t [react] V [WJMMNR [t0 competitionJA1JVP)-
    Page 8, “Learning Algorithm”

See all papers in Proc. ACL 2011 that mention POS tags.

See all papers in Proc. ACL that mention POS tags.

Back to top.

role labelers

Appears in 5 sentences as: role labelers (2) Role labels (1) role labels (2)
In Semantic Representation of Negation Using Focus Detection
  1. State-of-the-art semantic role labelers (e.g., the ones trained over PropBank) do not completely represent the meaning of negated statements.
    Page 2, “Negation in Natural Language”
  2. For all statements s, current role labelers would only encode it is not the case that s. However, examples (1—7)
    Page 2, “Negation in Natural Language”
  3. Role labels (A0, MTMP, etc.)
    Page 6, “Approach to Semantic Representation of Negation”
  4. Before annotation began, all semantic information was removed by mapping all role labels to ARG.
    Page 6, “Approach to Semantic Representation of Negation”
  5. Because PropBank adds semantic role annotation on top of the Penn TreeB ank, we have available syntactic annotation and semantic role labels for all instances.
    Page 7, “Learning Algorithm”

See all papers in Proc. ACL 2011 that mention role labelers.

See all papers in Proc. ACL that mention role labelers.

Back to top.

semantic relations

Appears in 5 sentences as: Semantic Relations (1) Semantic relations (1) semantic relations (3)
In Semantic Representation of Negation Using Focus Detection
  1. Substantial progress has been made, though, especially on detection of semantic relations , ontologies and reasoning methods.
    Page 1, “Introduction”
  2. Negation has been largely ignored within the area of semantic relations .
    Page 1, “Introduction”
  3. In this Section, we outline how to incorporate negation into semantic relations .
    Page 4, “Approach to Semantic Representation of Negation”
  4. 4.1 Semantic Relations
    Page 4, “Approach to Semantic Representation of Negation”
  5. Semantic relations capture connections between concepts and label them according to their nature.
    Page 4, “Approach to Semantic Representation of Negation”

See all papers in Proc. ACL 2011 that mention semantic relations.

See all papers in Proc. ACL that mention semantic relations.

Back to top.

semantic representation

Appears in 5 sentences as: semantic representation (2) semantic representations (1) semantically represent (2)
In Semantic Representation of Negation Using Focus Detection
  1. The main contributions are: (l) interpretation of negation using focus detection; (2) focus of negation annotation over all PropBank negated sen-tencesl; (3) feature set to detect the focus of negation; and (4) model to semantically represent negation and reveal its underlying positive meaning.
    Page 3, “Negation in Natural Language”
  2. Several options arise to thoroughly represent s. First, we find it useful to consider the semantic representation of the affirmative counterpart: AGENT(the cow, ate), THEME(grass, ate), and INSTRUMENT(With a fork, ate).
    Page 4, “Approach to Semantic Representation of Negation”
  3. Table 2 depicts five different possible semantic representations .
    Page 4, “Approach to Semantic Representation of Negation”
  4. It corresponds to the semantic representation of the affirmative counterpart after applying the pseudo-relation NOT over the focus of the negation.
    Page 4, “Approach to Semantic Representation of Negation”
  5. In this paper, we present a novel way to semantically represent negation using focus detection.
    Page 8, “Conclusions”

See all papers in Proc. ACL 2011 that mention semantic representation.

See all papers in Proc. ACL that mention semantic representation.

Back to top.

semantic role

Appears in 5 sentences as: semantic role (3) semantic roles (3)
In Semantic Representation of Negation Using Focus Detection
  1. State-of-the-art semantic role labelers (e.g., the ones trained over PropBank) do not completely represent the meaning of negated statements.
    Page 2, “Negation in Natural Language”
  2. Instead, we use generic semantic roles .
    Page 4, “Approach to Semantic Representation of Negation”
  3. Given s: The cow didn’t eat grass with a fork, typical semantic roles encode AGENT(the cow, eat), THEME(grass, eat), INSTRUMENT(With a fork, eat) and NEGATION(n’t, eat).
    Page 4, “Approach to Semantic Representation of Negation”
  4. Like typical semantic roles , option (2) does not reveal the implicit positive meaning carried by statement s. Options (3—5) encode different interpretations:
    Page 4, “Approach to Semantic Representation of Negation”
  5. Because PropBank adds semantic role annotation on top of the Penn TreeB ank, we have available syntactic annotation and semantic role labels for all instances.
    Page 7, “Learning Algorithm”

See all papers in Proc. ACL 2011 that mention semantic role.

See all papers in Proc. ACL that mention semantic role.

Back to top.

feature set

Appears in 3 sentences as: feature set (3)
In Semantic Representation of Negation Using Focus Detection
  1. The main contributions are: (l) interpretation of negation using focus detection; (2) focus of negation annotation over all PropBank negated sen-tencesl; (3) feature set to detect the focus of negation; and (4) model to semantically represent negation and reveal its underlying positive meaning.
    Page 3, “Negation in Natural Language”
  2. The held-out portion is used to tune the feature set and results are reported for the test split only, i.e., using unseen instances.
    Page 7, “Learning Algorithm”
  3. We improve BASIC with an extended feature set which targets especially A1 and the verb (Table 5).
    Page 7, “Learning Algorithm”

See all papers in Proc. ACL 2011 that mention feature set.

See all papers in Proc. ACL that mention feature set.

Back to top.

natural language

Appears in 3 sentences as: natural language (3)
In Semantic Representation of Negation Using Focus Detection
  1. Understanding the meaning of text is a long term goal in the natural language processing community.
    Page 1, “Introduction”
  2. Within natural language processing, negation has drawn attention mainly in sentiment analysis (Wilson et al., 2009; Wiegand et al., 2010) and the biomedical domain.
    Page 2, “Related Work”
  3. None of the above references aim at detecting or annotating the focus of negation in natural language .
    Page 2, “Related Work”

See all papers in Proc. ACL 2011 that mention natural language.

See all papers in Proc. ACL that mention natural language.

Back to top.

PDF available from www.aclweb.org.
Send us an email