ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling
Laparra, Egoitz and Rigau, German

Article Structure

Abstract

This paper presents a novel deterministic algorithm for implicit Semantic Role Labeling.

Introduction

Traditionally, Semantic Role Labeling (SRL) systems have focused in searching the fillers of those explicit roles appearing within sentence boundaries (Gildea and Jurafsky, 2000, 2002; Carreras and Marquez, 2005; Surdeanu et al., 2008; Hajic et al., 2009).

Related Work

The first attempt for the automatic annotation of implicit semantic roles was proposed by Palmer et al.

Datasets

In our experiments, we have focused on the dataset developed in Gerber and Chai (2010, 2012).

ImpAr algorithm

4.1 Discoursive coherence of predicates

Evaluation

In order to evaluate the performance of the ImpAr algorithm, we have followed the evaluation method presented by Gerber and Chai (2010, 2012).

Discussion

6.1 Component Analysis

Conclusions and Future Work

In this work we have presented a robust deterministic approach for implicit Semantic Role Labeling.

Acknowledgment

We are grateful to the anonymous reviewers for their insightful comments.

Topics

coreference

Appears in 9 sentences as: coreference (7) coreferent (1) coreferential (1)
In ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling
  1. This work applied selectional restrictions together with coreference chains, in a very specific domain.
    Page 2, “Related Work”
  2. These early works agree that the problem is, in fact, a special case of anaphora or coreference resolution.
    Page 2, “Related Work”
  3. Silberer and Frank (2012) adapted an entity-based coreference resolution model to extend automatically the training corpus.
    Page 2, “Related Work”
  4. They uses a set of syntactic, semantic and coreferential features to train a logistic regres-
    Page 2, “Related Work”
  5. All the works presented in this section agree that implicit arguments must be modeled as a particular case of coreference together with features that include lexical-semantic information, to build selectional preferences.
    Page 3, “Related Work”
  6. Filling the implicit arguments of a predicate has been identified as a particular case of coreference , very close to pronoun resolution (Silberer and Frank, 2012).
    Page 4, “ImpAr algorithm”
  7. For each missing argument, the gold-standard includes the whole coreference chain of the filler.
    Page 6, “Evaluation”
  8. Therefore, the scorer selects from all coreferent mentions the highest Dice value.
    Page 6, “Evaluation”
  9. For instance, our system can also profit from additional annotations like coreference , that has proved its utility in previous works.
    Page 9, “Conclusions and Future Work”

See all papers in Proc. ACL 2013 that mention coreference.

See all papers in Proc. ACL that mention coreference.

Back to top.

Semantic Role

Appears in 8 sentences as: Semantic Role (4) semantic role (2) semantic roles (2)
In ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling
  1. This paper presents a novel deterministic algorithm for implicit Semantic Role Labeling.
    Page 1, “Abstract”
  2. Traditionally, Semantic Role Labeling (SRL) systems have focused in searching the fillers of those explicit roles appearing within sentence boundaries (Gildea and Jurafsky, 2000, 2002; Carreras and Marquez, 2005; Surdeanu et al., 2008; Hajic et al., 2009).
    Page 1, “Introduction”
  3. for Implicit Semantic Role Labelling
    Page 1, “Introduction”
  4. The first attempt for the automatic annotation of implicit semantic roles was proposed by Palmer et al.
    Page 2, “Related Work”
  5. SEMAFOR (Chen et al., 2010) is a supervised system that extended an existing semantic role labeler to enlarge the search window to other sentences, replacing the features defined for regular arguments with two new semantic features.
    Page 2, “Related Work”
  6. In this work we have presented a robust deterministic approach for implicit Semantic Role Labeling.
    Page 8, “Conclusions and Future Work”
  7. We have shown the importance of this phenomenon for recovering the implicit information about semantic roles .
    Page 8, “Conclusions and Future Work”
  8. As input it only needs the document with explicit semantic role labeling and Super-Sense annotations.
    Page 8, “Conclusions and Future Work”

See all papers in Proc. ACL 2013 that mention Semantic Role.

See all papers in Proc. ACL that mention Semantic Role.

Back to top.

gold-standard

Appears in 6 sentences as: gold-standard (6)
In ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling
  1. The following example includes the gold-standard annotations for a traditional SRL process:
    Page 1, “Introduction”
  2. For every argument position in the gold-standard the scorer expects a single predicted constituent to fill in.
    Page 6, “Evaluation”
  3. The function above relates the set of tokens that form a predicted constituent, Predicted, and the set of tokens that are part of an annotated constituent in the gold-standard , True.
    Page 6, “Evaluation”
  4. For each missing argument, the gold-standard includes the whole coreference chain of the filler.
    Page 6, “Evaluation”
  5. Recall is equal to the sum of the prediction scores divided by the number of actual annotations in the gold-standard .
    Page 6, “Evaluation”
  6. But the actual gold-standard annotation is: [argl buyers that weren’t disclosed].
    Page 8, “Discussion”

See all papers in Proc. ACL 2013 that mention gold-standard.

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

Back to top.

Role Labeling

Appears in 6 sentences as: role labeler (1) Role Labeling (3) role labeling (1) Role Labelling (1)
In ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling
  1. This paper presents a novel deterministic algorithm for implicit Semantic Role Labeling .
    Page 1, “Abstract”
  2. Traditionally, Semantic Role Labeling (SRL) systems have focused in searching the fillers of those explicit roles appearing within sentence boundaries (Gildea and Jurafsky, 2000, 2002; Carreras and Marquez, 2005; Surdeanu et al., 2008; Hajic et al., 2009).
    Page 1, “Introduction”
  3. for Implicit Semantic Role Labelling
    Page 1, “Introduction”
  4. SEMAFOR (Chen et al., 2010) is a supervised system that extended an existing semantic role labeler to enlarge the search window to other sentences, replacing the features defined for regular arguments with two new semantic features.
    Page 2, “Related Work”
  5. In this work we have presented a robust deterministic approach for implicit Semantic Role Labeling .
    Page 8, “Conclusions and Future Work”
  6. As input it only needs the document with explicit semantic role labeling and Super-Sense annotations.
    Page 8, “Conclusions and Future Work”

See all papers in Proc. ACL 2013 that mention Role Labeling.

See all papers in Proc. ACL that mention Role Labeling.

Back to top.

Semantic Role Labeling

Appears in 6 sentences as: semantic role labeler (1) Semantic Role Labeling (3) semantic role labeling (1) Semantic Role Labelling (1)
In ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling
  1. This paper presents a novel deterministic algorithm for implicit Semantic Role Labeling .
    Page 1, “Abstract”
  2. Traditionally, Semantic Role Labeling (SRL) systems have focused in searching the fillers of those explicit roles appearing within sentence boundaries (Gildea and Jurafsky, 2000, 2002; Carreras and Marquez, 2005; Surdeanu et al., 2008; Hajic et al., 2009).
    Page 1, “Introduction”
  3. for Implicit Semantic Role Labelling
    Page 1, “Introduction”
  4. SEMAFOR (Chen et al., 2010) is a supervised system that extended an existing semantic role labeler to enlarge the search window to other sentences, replacing the features defined for regular arguments with two new semantic features.
    Page 2, “Related Work”
  5. In this work we have presented a robust deterministic approach for implicit Semantic Role Labeling .
    Page 8, “Conclusions and Future Work”
  6. As input it only needs the document with explicit semantic role labeling and Super-Sense annotations.
    Page 8, “Conclusions and Future Work”

See all papers in Proc. ACL 2013 that mention Semantic Role Labeling.

See all papers in Proc. ACL that mention Semantic Role Labeling.

Back to top.

manual annotations

Appears in 4 sentences as: manual annotation (1) manual annotations (2) manually annotated (1)
In ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling
  1. However, current automatic systems require large amounts of manually annotated training data for each predicate.
    Page 1, “Introduction”
  2. The effort required for this manual annotation explains the absence of generally applicable tools.
    Page 1, “Introduction”
  3. Instead, the supervised approach would need a large amount of manual annotations for every predicate to be processed.
    Page 7, “Evaluation”
  4. That is, it can be applied where there is no available manual annotations to train.
    Page 8, “Conclusions and Future Work”

See all papers in Proc. ACL 2013 that mention manual annotations.

See all papers in Proc. ACL that mention manual annotations.

Back to top.

WordNet

Appears in 3 sentences as: WordNet (3)
In ImpAr: A Deterministic Algorithm for Implicit Semantic Role Labelling
  1. VENSES++ (Tonelli and Delmonte, 2010) applied a rule based anaphora resolution procedure and semantic similarity between candidates and thematic roles using WordNet (Fellbaum, 1998).
    Page 2, “Related Work”
  2. named-entities and WordNet Super-Senses4.
    Page 5, “ImpAr algorithm”
  3. 4Lexicographic files according to WordNet terminology.
    Page 5, “ImpAr algorithm”

See all papers in Proc. ACL 2013 that mention WordNet.

See all papers in Proc. ACL that mention WordNet.

Back to top.

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