Annotation This volume brings together revised versions of a selection of papers presented at the Sixth International Conference on Recent Advances in Natural Language Processing (RANLP) held in Borovets, Bulgaria, 27 29 September 2007. These papers cover a wide variety of Natural Language Processing (NLP) topics: ontologies, named entity extraction, translation and transliteration, morphology (derivational and inflectional), part-of-speech tagging, parsing (incremental processing, dependency parsing), semantic role labeling, word sense disambiguation, temporal representations, inference and metaphor, semantic similarity, coreference resolution, clustering (topic modeling, topic tracking), summarization, cross-lingual retrieval, lexical and syntactic resources, multi-modal processing. The aim of this volume is to present new results in NLP based on modern theories and methodologies, making it of interest to researchers in NLP and, more specifically, to those who work in Computational Linguistics, Corpus Linguistics, and Machine Translation

nexusstc/Recent Advances in Natural Language Processing V: Selected papers from RANLP 2007/27219f258781d0a588e059c5616a22e5.pdf

lgli/Recent Advances in Natural Language Processing V.pdf

lgrsnf/Recent Advances in Natural Language Processing V.pdf

zlib/Languages/Grammar, dictionaries & phrasebooks/Nicolas Nicolov (Ed.), Galia Angelova (Ed.), Ruslan Mitkov (Ed.)/Recent Advances in Natural Language Processing V: Selected Papers from RANLP 2007_2363196.pdf

Nicolas Nicolov; Galia Angelova; International Conference on Recent Advances in Natural Language Processing RANLP

International Conference on Recent Advances in Natural Language Processing (6, 2007, Borovec)

NICOLOV, Nicolas, Galia ANGELOVA and Ruslan MITKOV (eds.)

edited by Nicolas Nicolov, Galia Angelova, Ruslan Mitkov

Nicolov, Nicolas, Angelova, Galia, Mitkov, Ruslan

Ranlp 2007 (2007 : Borovet︠s︡, Bulgaria)

Benjamins, John

Amsterdam studies in the theory and history of linguistic science. Series IV, Current issues in linguistic theory -- v. 309, Amsterdam studies in the theory and history of linguistic science -- v. 309., Amsterdam, Philadelphia, Netherlands, 2009

Amsterdam studies in the theory and history of linguistic science. Series 4, Current issues in linguistic theory -- v. 309, Philadelphia, Pa, Pennsylvania, 2009

Amsterdam studies in the theory and history of linguistic science, Amsterdam, cop. 2009

Recent advances in natural language processing, 309, Amsterdam, 2009

Current Issues in Linguistic Theory 309, 1st, 2009

John Benjamins Publishing Co., Amsterdam, 2009

0

lg1194797

producers:
3-Heights(TM) PDF Producer 1.9.24.1 (http://www.pdf-tools.com); modified using iTextSharp 5.0.0 (c) 1T3XT BVBA

{"container_title":"Current Issues in Linguistic Theory","edition":"1","isbns":["9027248257","9027290911","9789027248251","9789027290915"],"issns":["0304-0763"],"last_page":338,"publisher":"John Benjamins Publishing Company","series":"Current Issues in Linguistic Theory 309"}

Papers presented at the Sixth International Conference on "Recent advances in natural language processing" (RANLP) held in Borovets, Bulgaria, 27-29 Sept. 2007.
Includes bibliographical references and index.

Includes bibliographical references and index.

CILT 309
Recent Advances in Natural Language Processing V 2
Editorial page 3
Title page 4
LCC data 5
CONTENTS 6
Editors’ Foreword 8
Ontotherapy, or How to Stop Worrying About What There Is 12
1 Introduction 12
2 Ontologies and conceptual relations 15
3 Ontological basics: a reminder 17
4 Is Wordnet an ontology? 20
5 Guarino’s program for reforming Wordnet 23
6 Empirical issues 26
7 What there is 28
8 Conclusions 29
Acknowledgements. 29
REFERENCES 29
Constraint-Driven Transliteration Discovery 32
1 Introduction 32
2 Related work 34
3 Constraint-driven transliteration model 35
4 Experiments and analysis 41
5 Conclusion 48
Acknowledgements. 49
REFERENCES 49
Towards Radically Incremental Parsing of Natural Language 52
1 Introduction 52
2 Incremental sentence processing 53
3 The Argument Dependency Model 55
4 Incremental processing with CDG 57
5 Experiments 61
6 Conclusions 65
Acknowledgements 66
REFERENCES 66
Unsupervised Graph-based Word Sense Disambiguation 68
1 Introduction 68
2 Graph-based centrality for word sense disambiguation 69
3 Measures of word semantic similarity 71
4 Graph-based centrality algorithms 72
5 An example 74
6 Experiments and results 74
7 Conclusions 81
Acknowledgments 81
REFERENCES 82
Collaborative Entity Extraction and Translation 84
1 Introduction 84
2 Task and terminology 85
3 Motivation for using bitexts 86
4 General approach 87
5 Inference rules 89
6 System pipeline 90
7 Experiments on Chinese to English 90
8 Related work 93
9 Conclusion and future work 93
Acknowledgements 94
REFERENCES 94
Generating Models for Temporal Representations 96
1 Introduction 96
2 Modelling tense and aspect 97
3 Computing semantic representations 100
4 A first-order theory of time and events 101
5 Building non-minimal models 105
6 Conclusion 108
REFERENCES 108
The Complexity of Everyday Language 110
1 Preamble 110
2 Meaning representations 111
3 Examples 112
4 Linking natural language and domain knowledge 120
REFERENCES 123
Detecting Topic Drift 124
1 Introduction 124
2 Related work 125
3 Background 126
4 Compound Topic Models 129
5 Indicators of drift 131
6 Visualization 132
7 Results and discussion 132
8 Conclusions 139
Acknowledgements 140
REFERENCES 140
Feature Construction for Memory-Based Semantic Role Labeling of Catalan and Spanish 142
1 Introduction 142
2 Catalan and Spanish SRL-annotated corpora 143
3 Description of the base semantic role labeling system 143
4 Results 146
5 Analysis of the predictive power of features 147
6 Feature construction by splitting and combining multi-valued features 148
7 Conclusions 152
Acknowledgements 152
REFERENCES 152
A Maximization-Minimization Approach for Update Text Summarization 154
1 Introduction 154
2 Method 155
3 Experimental settings 158
4 Experiments 160
5 Discussion and conclusion 163
Acknowledgments 164
REFERENCES 164
Integrating Derivational Morphology into Syntax 166
1 Introduction 166
2 Related work 168
3 Inflectional groups as lexical units 168
4 Inflectional groups in practice 173
5 Current implementation 178
6 Conclusions and future work 179
Acknowledgements 180
REFERENCES 180
Biomedical Named Entity Recognition Using Discriminative Training 182
1 Introduction 182
2 Related work 183
3 The basic HMM system 184
4 The Perceptron HMM algorithm 185
5 MIRA update 186
6 Features 187
7 Results and discussion 187
8 Conclusion and future work 189
Acknowledgements 190
REFERENCES 190
Completing Lists of Entities 192
1 Introduction 192
2 Background 193
3 List completion 194
4 Discussion 201
5 Conclusion 201
Acknowledgments 202
REFERENCES 202
Character N-Grams as Text Alignment Unit: CLIR Applications 204
1 Introduction 204
2 Description of the system 205
3 Evaluation 209
4 Conclusions 213
Acknowledgements 214
REFERENCES 214
K-best, Locally Pruned, Transition-based Dependency Parsing Using Robust Risk Minimization 216
1 Introduction 216
2 Dependency structure 217
3 Robust risk minimization 218
4 Parsing algorithm 220
5 Features and learning parameters 224
6 Evaluation 224
7 Conclusion 226
Acknowledgements 226
REFERENCES 227
Minimal Sets of Minimal Speech Acts 228
1 Introduction 228
2 Logical forms 229
3 Epistemic inference and planning 230
4 Actions with no preconditions 234
5 Conclusions 236
REFERENCES 237
Semantic Similarity of Short Texts 238
1 Introduction 238
2 Related work 239
3 Proposed method 240
4 Evaluation and experimental results 245
5 Conclusion 246
REFERENCES 246
News from OPUS — A Collection of Multilingual Parallel Corpora with Tools and Interfaces 248
1 Introduction 248
2 Recently added corpora 249
3 Tools and interfaces 255
4 Conclusions 257
REFERENCES 258
Reusing Contemporary Language Resources to PoS Tag Non-contemporary Literary Texts 260
1 Introduction 260
2 The data 261
3 Existing resources 262
4 The methodology 263
5 Testing the methodology 266
6 An alternative strategy 267
7 Conclusion and future work 268
Acknowledgements 269
REFERENCES 269
Domain Independent Mappings and Source Domain Reasoning for the Semantics of Metaphor 270
1 Introduction 270
2 Missing correspondents 271
3 Source domain reasoning and VNMAs 272
4 VNMAs 274
5 Metaphor in a semantic framework 275
6 Concluding remarks 278
REFERENCES 279
ConceptNet: A Lexical Resource for Common Sense Knowledge 280
1 The common sense computing problem 280
2 The Open Mind Common Sense project 281
3 ConceptNet 282
4 Similar resources 285
5 Comparison to other resources 286
6 Inference 288
7 Discussion 290
Acknowledgments 290
REFERENCES 290
Confidence Measures and Thresholding in Coreference Resolution 292
1 Introduction 292
2 Baseline system 293
3 Experimental preliminaries 294
4 Use of a confidence measure and a single threshold 295
5 Addition of multiple thresholds 296
6 Extended comparison of different systems 298
7 Conclusions and future work 300
Acknowledgements 300
REFERENCES 300
The Influence of Pronominal Anaphora Resolution on Term-based Summarisation 302
1 Introduction 302
2 Background 303
3 Method 303
4 Corpus 305
5 Evaluation and discussion 306
6 Conclusions 309
REFERENCES 310
Morpheme-based Language Modeling for an Inflectional Language — Amharic 312
1 Introduction 312
2 Data preparation 314
3 Experiments — I 315
4 Experiments — II 317
5 Conclusion 319
REFERENCES 320
Issues in Realizing the Overall Message of a Bar Chart 322
1 Introduction 322
2 The overall message of an information graphic 323
3 Measurement axis descriptor 324
4 Examples of referent identification 329
5 Evaluation of the implemented system 329
6 Conclusion 331
Acknowledgements 331
REFERENCES 331
The BulTreeBank: Parsing and Conversion 332
1 Introduction 332
2 The BulTreeBank 333
3 Parsing measures 334
4 Dependency parsing 334
5 Constituency parsing 336
6 Conversion 336
7 Conclusion 339
REFERENCES 340
List and Addresses of Contributors 342
Index of Subjects and Terms 346
The series CURRENT ISSUES IN LINGUISTIC THEORY 350

Editors' Foreword -- Ontotherapy, Or How To Stop Worrying About What There Is / Yorick Wilks -- Constraint-driven Transliteration Discovery / Dan Goldwasser ... [et Al.] -- Towards Radically Incremental Parsing Of Natural Language / Wolfgang Menzel -- Unsupervised Graph-based Word Sense Disambiguation / Ravi Sinha & Rada Mihalcea -- Collaborative Entity Extraction And Translation / Heng Ji & Ralph Grishman -- Generating Models For Temporal Representations / Patrick Blackburn & Sébastien Hinderer -- The Complexity Of Everyday Language / Allan Ramsay -- Detecting Topic Drift / Dan Knights, Mike Mozer & Nicolas Nicolov -- Feature Construction For Memory-based Semantic Role Labeling Of Catalan And Spanish / Roser Morante & Antal Van Den Bosch -- A Maximization-minimization Approach For Update Summarization / Florian Boudin & Juan Manuel Torres-moreno -- Integrating Derivational Morphology Into Syntax / Özlem Çetinoğlu & Kemal Oflazer -- Biomedical Named Entity Recognition Using Discriminative Training / Sittichai Jiampojamarn, Grzegorz Kondrak & Colin Cherry -- Completing Lists Of Entities / Sisay Fissaha Adafre, Maarten De Rijke & Erik Tjong Kim Sang -- Character N-grams As Text Alignment Unit: Clir Applications / Jesús Vilares, Michael P. Oakes & Manuel Vilares -- K-best, Locally Pruned, Transition-based Dependency Parsing Using Robust Risk Minimization / Jinho D. Choi & Nicolas Nicolov -- Minimal Sets Of Minimal Speech Acts / Debora Field & Allan Ramsay -- Semantic Similarity Of Short Texts / Aminul Islam & Diana Inkpen -- News From Opus: A Collection Of Multilingual Parallel Corpora With Tools And Interfaces / Jörg Tiedemann -- Reusing Contemporary Language Resources To Pos Tag Non-contemporary Literary Texts / Costanza Navarretta -- Domain Independent Mappings And Source Domain Reasoning For The Semantics Of Metaphor / Rodrigo Agerri ... [et Al.] -- Conceptnet: A Lexical Resource For Common Sense Knowledge / Catherine Havasi, Robert Speer & Jason Alonso -- Confidence Measures And Thresholding In Coreference Resolution / John Chen ... [et Al.] -- The Influence Of Pronominal Anaphora Resolution On Term-based Summarisation / Constantin Orăsan -- Morpheme-based Language Modeling For An Inflectional Language, Amharic / Martha Yifiru Tachbelie & Wolfgang Menzel -- Issues In Realizing The Overall Message Of A Bar Chart / Seniz Demir, Sandra Carberry & Stephanie Elzer -- The Bultreebank: Parsing And Conversion / Atanas Chanev ... [et Al.] -- List And Addresses Of Contributors -- Index Of Subjects And Terms. Edited By Nicolas Nicolov, Galia Angelova, Ruslan Mitkov. Papers Presented At The Sixth International Conference On Recent Advances In Natural Language Processing (ranlp) Held In Borovets, Bulgaria, 27-29 Sept. 2007. Includes Bibliographical References And Index.

Editors' foreword -- Ontotherapy, or how to stop worrying about what there is / Yorick Wilks -- Constraint-driven transliteration discovery / Dan Goldwasser, Ming-Wei Chang, Yuancheng Tu & Dan Roth -- Towards radically incremental parsing of natural language / Wolfgang Menzel -- Unsupervised graph-based word sense disambiguation / Ravi Sinha & Rada Mihalcea -- Collaborative entity extraction and translation / Heng Ji & Ralph Grishman -- Generating models for temporal representations / Patrick Blackburn & Sébastien Hinderer -- The complexity of everyday language / Allan Ramsay -- Detecting topic drift / Dan Knights, Mike Mozer & Nicolas Nicolov -- Feature construction for memory-based semantic role labeling of Catalan and Spanish / Roser Morante & Antal van den Bosch -- A maximization-minimization approach for update summarization / Florian Boudin & Juan Manuel Torres-Moreno -- Integrating derivational morphology into syntax / Ozlem Çetinoğlu & Kemal Oflazer -- Biomedical named entity recognition using discriminative training / Sittichai Jiampojamarn, Grzegorz Kondrak & Colin Cherry -- Completing lists of entities / Sisay Fissaha Adafre, Maarten de Rijke & Erik Tjong Kim Sang -- Character n-grams as text alignment unit: CLIR applications / Jesús Vilares, Michael P. Oakes & Manuel Vilares -- K-best, locally pruned, transition-based dependency parsing using robust risk minimization / Jinho D. Choi & Nicolas Nicolov -- Minimal sets of minimal speech acts / Debora Field & Allan Ramsay -- Semantic similarity of short texts / Aminul Islam & Diana Inkpen -- News from opus: A collection of multilingual parallel corpora with tools and interfaces / Jörg Tiedemann -- Reusing contemporary language resources to PoS tag non-contemporary literary texts / Costanza Navarretta -- Inference and domain independent mappings in metaphor understanding / Rodrigo Agerri, John Barnden, Mark Lee & Alan Wallington -- ConceptNet: A lexical resource for common sense knowledge / Catherine Havasi, Robert Speer & Jason Alonso -- Confidence measures and thresholding in coreference resolution / John Chen, Laurie Crist, Len Eynon, Cassandre Creswell, Amit Mhatre & Rohini Srihari -- The influence of pronominal anaphora resolution on term-based summarisation / Constantin Orasan -- Morpheme-based language modeling for an inflectional language, Amharic / Martha Yifiru Tachbelie & Wolfgang Menzel -- Issues in realizing the overall message of a bar chart / Seniz Demir, Sandra Carberry & Stephanie Elzer -- The BulTreeBank: Parsing and conversion / Atanas Chanev, Kiril Simov, Petya Osenova & Svetoslav Marinov -- List and Addresses of Contributors -- Index of Subjects and Terms

2014-07-21