A Treebank-based Investigation of IPP-triggering Verbs in Dutch

More documents

Recommendations

Info

esults with the baseline determined that coarse-grained representation of lexicon has a positive impact on parsing. The detailed morpho-syntactic information of POS tags plays an important role on parsing and missing this information drops its performance. Determining the type of head-daughter dependencies is a hard task which reduces parsing performance. 5 Acknowledgement Masood Ghayoomi is funded by the German research council DFG under the contract number MU 2822/3-1. References [1] M. Bijankhan. The role of corpora in writing grammar. Journal of Linguistics, 19(2):48–67, 2004. Tehran: Iran University Press. [2] P.F. Brown, P.V. deSouza, R.L. Mercer, V.J.D. Pietra, and J.C. Lai. Class-based n-gram models of natural language. Computational Linguistics, 18:467–479, 1992. [3] M. Candito and B. Crabbe. Improving generative statistical parsing with semisupervised word clustering. In Proc.s of the Int. Conf. on Parsing Technologies, 2009. [4] E. Charniak. A maximum-entropy-inspired parser. In Proc.s of the 1st NAACL Conf., NAACL 2000, pages 132–139, 2000. [5] M. Collins. Head-Driven Statistical Models for Natural Language Parsing. PhD thesis, University of Pennsylvania, 1999. [6] M. Ghayoomi. Bootstrapping the development of an HPSG-based treebank for Persian. Linguistic Issues in Language Technology, 7(1), 2012. [7] M. Ghayoomi. Word clustering for Persian statistical parsing. In JapTAL ’12: Proc.s of the 8th Int. Conf. on Advances in NLP, pages 126–137, 2012. [8] D. Klein and C.D. Manning. Accurate unlexicalized parsing. In Proc.s of the 41st Meeting of the ACL, pages 423–430, 2003. [9] T. Koo, X. Carreras, and M. Collins. Simple semi-supervised dependency parsing. In Proc.s of the ACL-08, 2008. [10] G. Leech and A. Wilson. Standards for Tagsets, pages 55–80. Text, speech, and language technology. Kluwer Academic Publishers, 9 edition, 1999. [11] M.P. Marcus, B. Santorini, and M.A. Marcinkiewicz. Building a large annotated corpus of English: the Penn treebank. Computational Linguistics, 19(2), 1993. [12] Y. Miyao. From Linguistic Theory to Syntactic Analysis: Corpus-Oriented Grammar Development and Feature Forest Model. PhD thesis, University of Tokyo, 2006. [13] C.J. Pollard and I.A. Sag. Head-Driven Phrase Structure Grammar. University of Chicago Press, 1994. [14] Ines Rehbein and Josef vanGenabith. Treebank annotation scheme and parser evaluation for German. In Proc.s of EMNLP-CoNLL, pages 630–639, 2007. [15] K. Simov, P. Osenova, A. Simov, and M. Kouylekov. Design and implementation of the bulgarian HPSG-based treebank. Research on Language and Computation, 2:495–522, 2004. [16] A. Stolcke. SRILM - An extensible language modeling toolkit. In Proc.s of the Int. Conf. on Spoken Language Processing, 2002. 114
Automatic Coreference Annotation in Basque Iakes Goenaga, Olatz Arregi, Klara Ceberio, Arantza Díaz de Ilarraza and Amane Jimeno University of the Basque Country UPV/EHU iakesg@gmail.com Abstract This paper presents a hybrid system for annotating nominal and pronominal coreferences by combining ML and rule-based methods. The system automatically annotates different types of coreferences; the results are then verified and corrected manually by linguists. The system provides automatically generated suggestions and a framework for easing the manual portion of the annotation process. This facilitates the creation of a broader annotated corpus, which can then be used to reiteratively improve our ML and rule-based techniques. 1 Introduction Coreference resolution task is crucial in natural language processing applications like Information Extraction, Question Answering or Machine Translation. Machine learning techniques as well as rule-based systems have been shown to perform well at resolving this task. Though machine-learning methods tend to dominate, in the CoNLL-2011 Shared Task 1 , the best results were obtained by a rulebased system (Stanford’s Multi-Pass Sieve Coreference Resolution System [13]). Supervised machine learning requires a large amount of training data, and the spread of machine learning approaches has been significantly aided by the public availability of annotated corpora produced by the 6th and 7th Message Understanding Conferences (MUC-6, 1995 and MUC-7, 1998) [17, 18], the ACE program [9], and the GNOME project [22]. In the case of minority and lesser-resourced languages, however, although the number of annotated corpora is increasing, the dearth of material continues to make applying these approaches difficult. Our aim is to improve this situation for Basque by both improving coreference resolution and facilitating the creation of a larger corpus for future work on similar tasks. We will design a semi-automatic hybrid system to speed up corpus tagging by facilitating human annotation. Our system will allow the annotation tool to 1 http://conll.cemantix.org/2011/task-description.html 115
Page 1 and 2:
A Treebank-based Investigation of I
Page 3 and 4:
participle and a (te-)infinitival c
Page 5 and 6:
Some verbs occur twice, since they
Page 7 and 8:
Profiling Feature Selection for Nam
Page 9 and 10:
prepositional objects (FOPP, OPP).
Page 11 and 12:
the limited size of annotated data
Page 13 and 14:
with high precision typically have
Page 15 and 16:
‘This was “not significantly”
Page 17 and 18:
The preposition durch typically has
Page 19 and 20:
Non-Projective Structures in Indian
Page 21 and 22:
the sequential order of nodes in a
Page 23 and 24:
extra-posed relative clause that ge
Page 25 and 26:
Experiments on Dependency Parsing o
Page 27 and 28:
for mitigating the effects of spars
Page 29 and 30:
obtained with MALTParser is 76.61%
Page 31 and 32:
as a standardised serialisation for
Page 33 and 34:
constituency and dependency, possib
Page 35 and 36:
SynAF and/or in . However, they sha
Page 37 and 38:
shows how some elements that are no
Page 39 and 40:
Example
Page 41 and 42:
‏ Example 8: represent
Page 43 and 44:

Page 45 and 46:
Chinese) as the direct object NP.
Page 47 and 48:
Example 15: Tokens and Word Forms
Page 49 and 50:
In a second experiment, a dataset w
Page 51 and 52:

Page 53 and 54:
[3] Leech G. N., Barnett, R. & Kahr
Page 55 and 56:
Effectively long-distance dependenc
Page 57 and 58: In French, another case of eLDD is
Page 59 and 60: elativization, it-clefts or questio
Page 61 and 62: 4.2.3 Annotation methodology Becaus
Page 63 and 64: Number of occurrences in FTB +SEQTB
Page 65 and 66: producing treebank based LFG approx
Page 67 and 68: Logical Form Representation for Lin
Page 69 and 70: gerundives for a total amount of so
Page 71 and 72: object+indirect object/object one.
Page 73 and 74: (VP (VB patch) ) ) ) (VP (VBZ is) (
Page 75 and 76: Types Adverb. Adject. Verbs Nouns T
Page 77 and 78: Eventually we may comment that ther
Page 79 and 80: DeepBank: A Dynamically Annotated T
Page 81 and 82: from another already existing one,
Page 83 and 84: to parse now does. The extra manual
Page 85 and 86: In the derivation show in Figure 1,
Page 87 and 88: 4 Patching Coverage Gaps with An Ap
Page 89 and 90: will enable further improvements in
Page 91 and 92: ParDeepBank: Multiple Parallel Deep
Page 93 and 94: 2 The ParDeepBank The PTB has emerg
Page 95 and 96: undergone extensive scientific scru
Page 97 and 98: the second combines the structures
Page 99 and 100: Sofia University). Each sentence wa
Page 101 and 102: data, and improvements in the infra
Page 103 and 104: The Effect of Treebank Annotation G
Page 105 and 106: ut without feature structures. This
Page 107: only the lexicon is fine-grained to
Page 111 and 112: manually annotated Czech sentences.
Page 113 and 114: citizens of Bilbao] are very involv
Page 115 and 116: 4.1.3 Coreference Selector Module T
Page 117 and 118: Nominal P R F1 MUC 75.33% 81.33% 78
Page 119 and 120: [9] G. Doddington, A. Mitchell, M.
Page 121 and 122: Analyzing the Most Common Errors in
Page 123 and 124: Graph 1 shows results of subsequent
Page 125 and 126: in the semantic type). This situati
Page 127 and 128: Will a Parser Overtake Achilles? Fi
Page 129 and 130: annotation is also based on a depen
Page 131 and 132: Set Name Sentences Tokens % Train/T
Page 133 and 134: dency relations (PRED, OBJ, SBJ, AD
Page 135 and 136: ton and Stacklazy), we trained a mo
Page 137 and 138: Feature Function Column Name Addres
Page 139 and 140: Using Parallel Treebanks for Machin
Page 141 and 142: phrases are generated by a shallow
Page 143 and 144: Figure 2: A Kybot p
Page 145 and 146: SUJ NP SENT MOD PP NP PP PP NP NP P
Page 147 and 148: Checkpoint Instances Google PT Our
Page 149 and 150: 6 Conclusions In this paper we have
Page 151 and 152: An integrated web-based treebank an
Page 153 and 154: 16] and we have earlier reported fr
Page 155 and 156: Figure 2: Screenshot of the interfa
Page 157 and 158: ple subcategorization frames may be
Page 159 and 160:
4 Integrated interface for annotati
Page 161 and 162:
of the 5th International Conference
Page 163 and 164:
Translational divergences and their
Page 165 and 166:
posed so far, Cyrus’ work did not
Page 167 and 168:
allowed an appropriate coverage of
Page 169 and 170:
damentales [...] 10 (the universal
Page 171 and 172:
for all lex_pair(s,t) do if head an
Page 173 and 174:
the treatment of typical translatio
Page 175 and 176:
Building a treebank of noisy user-g
Page 177 and 178:
Phenomenon Attested example Std. co
Page 179 and 180:
Figure 1: French Social Media Bank
Page 181 and 182:
Impact of treebank characteristics
Page 183 and 184:
Det Adj N (a) Danish Det Adj N (b)
Page 185 and 186:
sv: Bestämmelserna i detta avtal f
Page 187 and 188:
100 90 80 Unlabelled attachment 70
Page 189 and 190:
vidner , tilhørere og tiltalte wit
Page 191 and 192:
mance is not inconsiderable, as was
Page 193 and 194:
Genitives in Hindi Treebank: An Att
Page 195 and 196:
A genitive can occur with complex p
Page 197 and 198:
quite high. This motivates us towar
show all

A Treebank-based Investigation of IPP-triggering Verbs in Dutch

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?