Pattern Dictionary of English Prepositions
Litkowski, Ken

Article Structure

Abstract

We present a new lexical resource for the study of preposition behavior, the Pattern Dictionary of English Prepositions (PDEP).

Introduction

Recent studies (Zapirain et al.

The Pattern Dictionary of English Prepositions

Litkowski and Hargraves (2005) and Litkowski and Hargraves (2006) describe The Preposition Project (TPP) as an attempt to describe preposition behavior using a sense inventory made available for public use from the Oxford Dictionary of English (Stevenson and Soanes, 2003) by tagging sentences drawn from FrameNet.

See http://clg.wlv.ac.uk/proiects/DVC

4 PDEP is implemented as a combination of HTML and J avascript.

Assessment of Lexical Resources

Since the PDEP system enables exploration of features from WordNet, FrameNet, and VerbNet, we are able to make some assessment of these resources.

Class Analyses

In SemEval 2007, Yuret (2007) investigated the possibility of using the substitutable prepositions as the basis for disambiguation (as part of more general lexical sample substitution).

Topics

WordNet

Appears in 8 sentences as: WordNet (10)
In Pattern Dictionary of English Prepositions
  1. The features make extensive use of WordNet .
    Page 1, “Abstract”
  2. Section 4 describes how we are able to investigate the relationship of WordNet , FrameNet, and VerbNet to this effort and how this examination of preposition behavior can be used in working with these resources.
    Page 1, “Introduction”
  3. The feature extraction rules are (1) word class (we), (2) part of speech (pos), (3) lemma (1), (4) word (w), (5) WordNet lexical name (In), (6) WordNet synonyms (s), (7) WordNet hypernyms (h), (8) whether the word is capitalized (c), and (9) affixes (af).
    Page 5, “See http://clg.wlv.ac.uk/proiects/DVC”
  4. For features such as the WordNet lexical name, synonyms and hypernyms, the number of values may be much larger.
    Page 5, “See http://clg.wlv.ac.uk/proiects/DVC”
  5. Since the PDEP system enables exploration of features from WordNet , FrameNet, and VerbNet, we are able to make some assessment of these resources.
    Page 7, “Assessment of Lexical Resources”
  6. WordNet played a statistically significant role in the systems developed by Tratz (2011) and Srikumar and Roth (2013).
    Page 7, “Assessment of Lexical Resources”
  7. This includes the WordNet lexicographer’s file name (e.g., noun.time), synsets, and hypernyms.
    Page 7, “Assessment of Lexical Resources”
  8. We are examining the WordNet detour to FrameNet, as described in Burchardt et al.
    Page 9, “Class Analyses”

See all papers in Proc. ACL 2014 that mention WordNet.

See all papers in Proc. ACL that mention WordNet.

Back to top.

semantic relation

Appears in 6 sentences as: semantic relation (4) semantic relations (2)
In Pattern Dictionary of English Prepositions
  1. Section 5 describes how we can use PDEP for the analysis of semantic role and semantic relation inventories.
    Page 1, “Introduction”
  2. In TPP, each sense was characterized with its complement and attachment (or governor) properties, its class and semantic relation , substitutable prepositions, its syntactic positions, and any FrameNet frame and frame element usages (where available).
    Page 1, “The Pattern Dictionary of English Prepositions”
  3. A key element of Srikumar and Roth was the use of these classes to model semantic relations across prepositions (e.g., grouping all the Temporal senses of the SemEval prepositions).
    Page 3, “See http://clg.wlv.ac.uk/proiects/DVC”
  4. Srikumar and Roth (2013) broadened this perspective by considering a class-based approach by collapsing semantically-related senses across prepositions, thereby deriving a semantic relation inventory.
    Page 8, “Class Analyses”
  5. While their emphasis was on modeling semantic relations , they achieved an accuracy of 83.53 percent for preposition disambiguation.
    Page 8, “Class Analyses”
  6. As mentioned above, PDEP has a field for the Srikumar semantic relation , initially populated for the SemEval prepositions, and being extended to cover all other prepositions.
    Page 8, “Class Analyses”

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

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

Back to top.

semantic role

Appears in 6 sentences as: semantic role (5) semantic roles (1)
In Pattern Dictionary of English Prepositions
  1. (2013); Srikumar and Roth (2011)) have shown the value of prepositional phrases in joint modeling with verbs for semantic role labeling.
    Page 1, “Introduction”
  2. Section 5 describes how we can use PDEP for the analysis of semantic role and semantic relation inventories.
    Page 1, “Introduction”
  3. The occurrence of these invalid instances provides an opportunity for improving taggers, parsers, and semantic role labelers.
    Page 7, “See http://clg.wlv.ac.uk/proiects/DVC”
  4. We believe these analyses may provide a comprehensive characterization of particular semantic roles that can be used for various NLP applications.
    Page 8, “Class Analyses”
  5. Since dictionary publishers have not previously devoted much effort in analyzing preposition behavior, we believe PDEP may serve an important role, particularly for various NLP applications in which semantic role labeling is important.
    Page 9, “Class Analyses”
  6. We expect that desired improvements will come from usage in various NLP tasks, particularly word-sense disambiguation and semantic role labeling.
    Page 9, “Class Analyses”

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

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

Back to top.

hypernyms

Appears in 5 sentences as: hypernyms (5)
In Pattern Dictionary of English Prepositions
  1. The feature extraction rules are (1) word class (we), (2) part of speech (pos), (3) lemma (1), (4) word (w), (5) WordNet lexical name (In), (6) WordNet synonyms (s), (7) WordNet hypernyms (h), (8) whether the word is capitalized (c), and (9) affixes (af).
    Page 5, “See http://clg.wlv.ac.uk/proiects/DVC”
  2. For features such as the WordNet lexical name, synonyms and hypernyms , the number of values may be much larger.
    Page 5, “See http://clg.wlv.ac.uk/proiects/DVC”
  3. This includes the WordNet lexicographer’s file name (e.g., noun.time), synsets, and hypernyms .
    Page 7, “Assessment of Lexical Resources”
  4. We make extensive use of the file name, but less so from the synsets and hypernyms .
    Page 7, “Assessment of Lexical Resources”
  5. However, in general, we find that the file names are too coarse-grained and the synsets and hypernyms too fine-grained for generalizations on the selectors for the complements and the governors.
    Page 7, “Assessment of Lexical Resources”

See all papers in Proc. ACL 2014 that mention hypernyms.

See all papers in Proc. ACL that mention hypernyms.

Back to top.

role labeling

Appears in 4 sentences as: role labelers (1) role labeling (3)
In Pattern Dictionary of English Prepositions
  1. (2013); Srikumar and Roth (2011)) have shown the value of prepositional phrases in joint modeling with verbs for semantic role labeling .
    Page 1, “Introduction”
  2. The occurrence of these invalid instances provides an opportunity for improving taggers, parsers, and semantic role labelers .
    Page 7, “See http://clg.wlv.ac.uk/proiects/DVC”
  3. Since dictionary publishers have not previously devoted much effort in analyzing preposition behavior, we believe PDEP may serve an important role, particularly for various NLP applications in which semantic role labeling is important.
    Page 9, “Class Analyses”
  4. We expect that desired improvements will come from usage in various NLP tasks, particularly word-sense disambiguation and semantic role labeling .
    Page 9, “Class Analyses”

See all papers in Proc. ACL 2014 that mention role labeling.

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

Back to top.

semantic role labeling

Appears in 4 sentences as: semantic role labelers (1) semantic role labeling (3)
In Pattern Dictionary of English Prepositions
  1. (2013); Srikumar and Roth (2011)) have shown the value of prepositional phrases in joint modeling with verbs for semantic role labeling .
    Page 1, “Introduction”
  2. The occurrence of these invalid instances provides an opportunity for improving taggers, parsers, and semantic role labelers .
    Page 7, “See http://clg.wlv.ac.uk/proiects/DVC”
  3. Since dictionary publishers have not previously devoted much effort in analyzing preposition behavior, we believe PDEP may serve an important role, particularly for various NLP applications in which semantic role labeling is important.
    Page 9, “Class Analyses”
  4. We expect that desired improvements will come from usage in various NLP tasks, particularly word-sense disambiguation and semantic role labeling .
    Page 9, “Class Analyses”

See all papers in Proc. ACL 2014 that mention semantic role labeling.

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

Back to top.

synsets

Appears in 3 sentences as: synsets (3)
In Pattern Dictionary of English Prepositions
  1. This includes the WordNet lexicographer’s file name (e.g., noun.time), synsets , and hypernyms.
    Page 7, “Assessment of Lexical Resources”
  2. We make extensive use of the file name, but less so from the synsets and hypernyms.
    Page 7, “Assessment of Lexical Resources”
  3. However, in general, we find that the file names are too coarse-grained and the synsets and hypernyms too fine-grained for generalizations on the selectors for the complements and the governors.
    Page 7, “Assessment of Lexical Resources”

See all papers in Proc. ACL 2014 that mention synsets.

See all papers in Proc. ACL that mention synsets.

Back to top.

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