Grammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing
Sun, Weiwei and Du, Yantao and Kou, Xin and Ding, Shuoyang and Wan, Xiaojun

Article Structure

Abstract

This paper is concerned with building linguistic resources and statistical parsers for deep grammatical relation (GR) analysis of Chinese texts.

Introduction

Grammatical relations (GRs) represent functional relationships between language units in a sentence.

GB-grounded GR Extraction

In this section, we discuss the construction of the GR annotations.

Transition-based GR Parsing

The availability of large-scale treebanks has contributed to the blossoming of statistical approaches to build accurate shallow constituency and dependency parsers.

Experiments

4.1 Experimental setup

Related Work

Wide-coverage in-depth and accurate linguistic processing is desirable for many practical NLP applications, such as machine translation (Wu et al., 2010) and information extraction (Miyao et al., 2008).

Conclusion

Recent years witnessed rapid progress made on deep linguistic processing for English, and initial attempts for Chinese.

Topics

dependency parsing

Appears in 15 sentences as: dependency parser (2) dependency parsers (2) Dependency Parsing (1) dependency parsing (10)
In Grammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing
  1. Different from popular shallow dependency parsing that focus on tree-shaped structures, our GR annotations are represented as general directed graphs that express not only 10-cal but also various long-distance dependencies, such as coordinations, control/raising constructions, topicalization, relative clauses and many other complicated linguistic phenomena that goes beyond shallow syntax (see Fig.
    Page 1, “Introduction”
  2. Previous work on dependency parsing mainly focused on structures that can be represented in terms of directed trees.
    Page 1, “Introduction”
  3. Allowing non-projective dependencies generally makes parsing either by graph-based or transition-based dependency parsing harder.
    Page 4, “GB-grounded GR Extraction”
  4. The availability of large-scale treebanks has contributed to the blossoming of statistical approaches to build accurate shallow constituency and dependency parsers .
    Page 5, “Transition-based GR Parsing”
  5. In particular, transition-based dependency parsing method is studied.
    Page 5, “Transition-based GR Parsing”
  6. 3.1 Data-Driven Dependency Parsing
    Page 5, “Transition-based GR Parsing”
  7. Data-driven, grammar-free dependency parsing has received an increasing amount of attention in the past decade.
    Page 5, “Transition-based GR Parsing”
  8. transition-based (Yamada and Matsumoto, 2003; Nivre, 2008) and graph-based (McDonald, 2006; Torres Martins et al., 2009) models have attracted the most attention of dependency parsing in recent years.
    Page 5, “Transition-based GR Parsing”
  9. Following (Nivre, 2008), we define a transition system for dependency parsing as a quadruple S = (C, T, cs, Ct), where
    Page 5, “Transition-based GR Parsing”
  10. To build accurate deep dependency parsers , we utilize a large set of features for disambiguation.
    Page 7, “Transition-based GR Parsing”
  11. There is a dual effect of the increase of the parameter k to our transition-based dependency parser .
    Page 7, “Experiments”

See all papers in Proc. ACL 2014 that mention dependency parsing.

See all papers in Proc. ACL that mention dependency parsing.

Back to top.

dependency tree

Appears in 6 sentences as: dependency tree (4) dependency trees (2)
In Grammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing
  1. There are two differences of the head word passing between our GR extraction and a “normal” dependency tree extraction.
    Page 4, “GB-grounded GR Extraction”
  2. These measures correspond to attachment scores (LASflJAS) in dependency tree parsing.
    Page 4, “GB-grounded GR Extraction”
  3. graphs than syntactic dependency trees .
    Page 5, “GB-grounded GR Extraction”
  4. Transition-based parsers utilize transition systems to derive dependency trees together with treebank-induced statistical models for predicting transitions.
    Page 5, “Transition-based GR Parsing”
  5. Developing features has been shown crucial to advancing the state-of-the-art in dependency tree parsing (Koo and Collins, 2010; Zhang and Nivre, 2011).
    Page 7, “Transition-based GR Parsing”
  6. Our work stands in between traditional dependency tree parsing and deep linguistic processing.
    Page 9, “Conclusion”

See all papers in Proc. ACL 2014 that mention dependency tree.

See all papers in Proc. ACL that mention dependency tree.

Back to top.

Manual evaluation

Appears in 6 sentences as: Manual Evaluation (1) Manual evaluation (3) manual evaluation (2)
In Grammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing
  1. The reliability of this linguistically-motivated GR extraction procedure is highlighted by manual evaluation .
    Page 1, “Abstract”
  2. Manual evaluation highlights the reliability of our linguistically-motivated GR extraction algorithm: The overall dependency-based precision and recall are 99.17 and 98.87.
    Page 1, “Introduction”
  3. Table 1: Manual evaluation of 209 sentences.
    Page 4, “GB-grounded GR Extraction”
  4. 2.3 Manual Evaluation
    Page 4, “GB-grounded GR Extraction”
  5. To have a precise understanding of whether our extraction algorithm works well, we have selected 20 files that contains 209 sentences in total for manual evaluation .
    Page 4, “GB-grounded GR Extraction”
  6. Manual evaluation demonstrate the effectiveness of our method.
    Page 9, “Conclusion”

See all papers in Proc. ACL 2014 that mention Manual evaluation.

See all papers in Proc. ACL that mention Manual evaluation.

Back to top.

treebank

Appears in 6 sentences as: Treebank (1) treebank (4) treebanks (1)
In Grammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing
  1. To acquire high-quality GR corpus, we propose a linguistically-motivated algorithm to translate a Government and Binding (GB; Chomsky, 1981; Camie, 2007) grounded phrase structure treebank , i.e.
    Page 1, “Introduction”
  2. Chinese Treebank (CTB; Xue et al., 2005) to a deep dependency bank where GRs are explicitly represented.
    Page 1, “Introduction”
  3. structure treebank , namely CTB.
    Page 2, “GB-grounded GR Extraction”
  4. Our treebank conversion algorithm borrows key insights from Lexical Functional Grammar (LFG; Bresnan and Kaplan, 1982; Dalrymple, 2001).
    Page 3, “GB-grounded GR Extraction”
  5. There are two sources of errors in treebank conversion: (1) inadequate conversion rules and (2) wrong or inconsistent original annotations.
    Page 4, “GB-grounded GR Extraction”
  6. The availability of large-scale treebanks has contributed to the blossoming of statistical approaches to build accurate shallow constituency and dependency parsers.
    Page 5, “Transition-based GR Parsing”

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

See all papers in Proc. ACL that mention treebank.

Back to top.

CCG

Appears in 5 sentences as: CCG (5)
In Grammatical Relations in Chinese: GB-Ground Extraction and Data-Driven Parsing
  1. This difference is consistent with the result obtained by a shift-reduce CCG parser (Zhang and Clark, 2011).
    Page 8, “Experiments”
  2. CCG and HP SG parsers also favor the dependency-based metrics for evaluation (Clark and Curran, 2007b; Miyao and Tsujii, 2008).
    Page 9, “Experiments”
  3. Previous work on Chinese CCG and HP SG parsing unanimously agrees that obtaining the deep analysis of Chinese is more challenging (Yu et al., 2011; Tse and Curran, 2012).
    Page 9, “Experiments”
  4. CCG , HP SG, LFG and TAG, provides valuable, richer linguistic information, and researchers thus draw more and more attention to it.
    Page 9, “Related Work”
  5. Phrase structure trees in CTB have been semiautomatically converted to deep derivations in the CCG (Tse and Curran, 2010), LFG (Guo et al., 2007), TAG (Xia, 2001) and HPSG (Yu et al., 2010) formalisms.
    Page 9, “Related Work”

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

See all papers in Proc. ACL that mention CCG.

Back to top.

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