Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem
Packard, Woodley and Bender, Emily M. and Read, Jonathon and Oepen, Stephan and Dridan, Rebecca

Article Structure

Abstract

In this work, we revisit Shared Task 1 from the 2012 *SEM Conference: the automated analysis of negation.

Introduction

Recently, there has been increased community interest in the theoretical and practical analysis of what Morante and Sporleder (2012) call modality and negation, i.e.

Related Work

Read et al.

System Description

The new system described here is what we call the MRS Crawler.

Experiments

We evaluated the performance of our system using the Shared Task development and evaluation data (respectively CDD and CDE in Table 1).

Discussion and Comparison

The example in (1) nicely illustrates the strengths of the MRS Crawler and of the abstraction provided by the deep linguistic analysis made possible by the ERG.

Conclusion and Outlook

Our motivation in this work was to take the design of the 2012 *SEM Shared Task on negation analysis at face value—as an overtly semantic problem that takes a central role in our longterm pursuit of language understanding.

Topics

Shared Task

Appears in 20 sentences as: Shared Task (20)
In Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem
  1. In this work, we revisit Shared Task 1 from the 2012 *SEM Conference: the automated analysis of negation.
    Page 1, “Abstract”
  2. Owing to its immediate utility in the cura-tion of scholarly results, the analysis of negation and so-called hedges in biomedical research literature has been the focus of several workshops, as well as the Shared Task at the 2011 Conference on Computational Language Learning (CoNLL).
    Page 1, “Introduction”
  3. 1Our running example is a truncated variant of an item from the Shared Task training data.
    Page 1, “Introduction”
  4. Though the task-specific concept of scope of negation is not the same as the notion of quantifier and operator scope in mainstream underspecified semantics, we nonetheless find that reviewing the 2012 *SEM Shared Task annotations with reference to an explicit encoding of semantic predicate-argument structure suggests a simple and straightforward operationalization of their concept of negation scope.
    Page 2, “Introduction”
  5. Our contributions are threefold: Theoretically, we correlate the structures at play in the Morante and Daelemans (2012) view on negation with formal semantic analyses; methodologically, we demonstrate how to approach the task in terms of underspecified, logical-form semantics; and practically, our combined system retroactively ‘wins’ the 2012 *SEM Shared Task .
    Page 2, “Introduction”
  6. (2012) describe some amount of tailoring of the Boxer lexicon to include more of the Shared Task scope cues among those that produce the negation operator in the DRSs, but otherwise the system appears to directly take the notion of scope of negation from the DRS and project it out to the string, with one caveat: As with the logical-forms representations we use, the DRS logical forms do not include function words as predicates in the semantics.
    Page 2, “Related Work”
  7. Since the Shared Task gold standard annotations included such arguably semantically vacuous (see Bender, 2013, p. 107) words in the scope, further heuristics are needed to repair the string-based annotations coming from the DRS-based system.
    Page 2, “Related Work”
  8. From these underspecified representations of possible scopal configurations, a scope resolution component can spell out the full range of fully-connected logical forms (Koller and Thater, 2005), but it turns out that such enumeration is not relevant here: the notion of scope encoded in the Shared Task annotations is not concerned with the relative scope of quantifiers and negation, such as the two possible readings of (2) represented informally below:5
    Page 3, “System Description”
  9. However, as shown below, the information about fixed scopal elements in an underspecified MRS is sufficient to model the Shared Task annotations.
    Page 3, “System Description”
  10. 5 In other words, a possible semantic interpretation of the (string-based) Shared Task annotation guidelines and data is in terms of a quantifier-free approach to meaning representation, or in terms of one where quantifier scope need not be made explicit (as once suggested by, among others, Alshawi, 1992).
    Page 3, “System Description”
  11. From this interpretation, it follows that the notion of scope assumed in the Shared Task does not encompass interactions of negation operators and quantifiers.
    Page 3, “System Description”

See all papers in Proc. ACL 2014 that mention Shared Task.

See all papers in Proc. ACL that mention Shared Task.

Back to top.

meaning representations

Appears in 6 sentences as: meaning representation (1) meaning representations (5)
In Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem
  1. derives the notion of negation scope assumed in this task from the structure of logical-form meaning representations .
    Page 1, “Abstract”
  2. Our system implements these findings through a notion of functor-argument ‘crawling’, using as our starting point the underspecified logical-form meaning representations provided by a general-purpose deep parser.
    Page 2, “Introduction”
  3. This system operates over the normalized semantic representations provided by the LinGO English Resource Grammar (ERG; Flickinger, 2000).3 The ERG maps surface strings to meaning representations in the format of Minimal Recursion Semantics (MRS; Copestake et al., 2005).
    Page 2, “System Description”
  4. 5 In other words, a possible semantic interpretation of the (string-based) Shared Task annotation guidelines and data is in terms of a quantifier-free approach to meaning representation , or in terms of one where quantifier scope need not be made explicit (as once suggested by, among others, Alshawi, 1992).
    Page 3, “System Description”
  5. (2011), on the one hand, and the broad-coverage, MRS meaning representations of the ERG, on the other hand.
    Page 9, “Conclusion and Outlook”
  6. Unlike the rather complex top-performing systems from the original 2012 competition, our MRS Crawler is defined by a small set of general rules that operate over general-purpose, explicit meaning representations .
    Page 9, “Conclusion and Outlook”

See all papers in Proc. ACL 2014 that mention meaning representations.

See all papers in Proc. ACL that mention meaning representations.

Back to top.

logical forms

Appears in 4 sentences as: logical form (1) logical forms (3)
In Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem
  1. (2012) describe some amount of tailoring of the Boxer lexicon to include more of the Shared Task scope cues among those that produce the negation operator in the DRSs, but otherwise the system appears to directly take the notion of scope of negation from the DRS and project it out to the string, with one caveat: As with the logical-forms representations we use, the DRS logical forms do not include function words as predicates in the semantics.
    Page 2, “Related Work”
  2. From these underspecified representations of possible scopal configurations, a scope resolution component can spell out the full range of fully-connected logical forms (Koller and Thater, 2005), but it turns out that such enumeration is not relevant here: the notion of scope encoded in the Shared Task annotations is not concerned with the relative scope of quantifiers and negation, such as the two possible readings of (2) represented informally below:5
    Page 3, “System Description”
  3. Both systems map from logical forms with explicit representations of scope of negation out to string-based annotations in the format provided by the Shared Task gold standard.
    Page 9, “Discussion and Comparison”
  4. The main points of difference are in the robustness of the system and in the degree of tailoring of both the rules for determining scope on the logical form level and the rules for handling semantically vacuous elements.
    Page 9, “Discussion and Comparison”

See all papers in Proc. ACL 2014 that mention logical forms.

See all papers in Proc. ACL that mention logical forms.

Back to top.

semantic representations

Appears in 4 sentences as: semantic representations (4)
In Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem
  1. This system operates over the normalized semantic representations provided by the LinGO English Resource Grammar (ERG; Flickinger, 2000).3 The ERG maps surface strings to meaning representations in the format of Minimal Recursion Semantics (MRS; Copestake et al., 2005).
    Page 2, “System Description”
  2. Our crawling rules operate on semantic representations , but the annotations are with reference to the surface string.
    Page 4, “System Description”
  3. In terms of our operations defined over semantic representations , this is rendered as follows: all arguments of the negated verb are selected by argument crawling, all in-tersective modifiers by label crawling, and functor crawling (Fig.
    Page 5, “System Description”
  4. Since these structures are analogous in the semantic representations , the same operations that handle negated verbs also handle negated predicative adjectives correctly.
    Page 5, “System Description”

See all papers in Proc. ACL 2014 that mention semantic representations.

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

Back to top.

gold standard

Appears in 3 sentences as: gold standard (3)
In Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem
  1. Since the Shared Task gold standard annotations included such arguably semantically vacuous (see Bender, 2013, p. 107) words in the scope, further heuristics are needed to repair the string-based annotations coming from the DRS-based system.
    Page 2, “Related Work”
  2. Of the 173 negation cue instances in CDD, Crawler by itself makes 94 scope predictions that exactly match the gold standard .
    Page 7, “Experiments”
  3. Both systems map from logical forms with explicit representations of scope of negation out to string-based annotations in the format provided by the Shared Task gold standard .
    Page 9, “Discussion and Comparison”

See all papers in Proc. ACL 2014 that mention gold standard.

See all papers in Proc. ACL that mention gold standard.

Back to top.

gold-standard

Appears in 3 sentences as: gold-standard (3)
In Simple Negation Scope Resolution through Deep Parsing: A Semantic Solution to a Semantic Problem
  1. (2012), who report results for each subproblem using gold-standard inputs; in this setup, scope resolution showed by far the lowest performance levels.
    Page 1, “Introduction”
  2. The ranking approach showed a modest advantage over the heuristics (with F1 equal to 77.9 and 76.7, respectively, when resolving the scope of gold-standard cues in evaluation data).
    Page 2, “Related Work”
  3. In future work, we will seek to better understand the division of labor between the systems involved through contrastive error analysis and possibly another oracle experiment, constructing gold-standard MRSs for part of the data.
    Page 9, “Conclusion and Outlook”

See all papers in Proc. ACL 2014 that mention gold-standard.

See all papers in Proc. ACL that mention gold-standard.

Back to top.

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