| A new method for sentiment classification in text retrieval | p. 1 |
| Topic tracking based on linguistic features | p. 10 |
| The use of monolingual context vectors for missing translations in cross-language information retrieval | p. 22 |
| Automatic image annotation using maximum entropy model | p. 34 |
| Corpus-based analysis of Japanese relative clause constructions | p. 46 |
| Parsing biomedical literature | p. 58 |
| Parsing the Penn Chinese treebank with semantic knowledge | p. 70 |
| Using a partially annotated corpus to build a dependency parser for Japanese | p. 82 |
| Entropy as an indicator of context boundaries : an experiment using a Web search engine | p. 93 |
| Automatic discovery of attribute words from Web documents | p. 106 |
| Aligning needless in a haystack : paraphrase acquisition across the Web | p. 119 |
| Confirmed knowledge acquisition using mails posted to a mailing list | p. 131 |
| Automatic partial parsing rule acquisition using decision tree induction | p. 143 |
| Chunking using conditional random fields in Korean texts | p. 155 |
| High efficiency realization for a wide-coverage unification grammar | p. 165 |
| Linguistically-motivated grammar extraction, generalization and adaptation | p. 177 |
| PP-attachment disambiguation boosted by a gigantic volume of unambiguous examples | p. 188 |
| Adapting a probabilistic disambiguation model of an HPSG parser to a new domain | p. 199 |
| A hybrid approach to single and multiple PP attachment using WordNet | p. 211 |
| Period disambiguration with Maxent model | p. 223 |
| Acquiring synonyms from monolingual comparable texts | p. 233 |
| A method of recognizing entity and relation | p. 245 |
| Inversion transduction grammar constraints for mining parallel sentences from quasi-comparable corpora | p. 257 |
| Automatic term extraction based on perplexity of compound words | p. 269 |
| Document clustering with grouping and chaining algorithms | p. 280 |
| Using multiple discriminant analysis approach for linear text segmentation | p. 292 |
| Classifying Chinese texts in two steps | p. 302 |
| Assigning polarity scores to reviews using machine learning techniques | p. 314 |
| Analogy as functional recategorization : abstraction with HowNet semantics | p. 326 |
| PLSI utilization for automatic thesaurus construction | p. 334 |
| Analysis of an iterative algorithm for term-based ontology alignment | p. 346 |
| Finding taxonomical relation from an MRD for thesaurus extension | p. 357 |
| Relation extraction using support vector machine | p. 366 |
| Discovering relations between named entities from a large raw corpus using tree similarity-based clustering | p. 378 |
| Automatic relation extraction with model order selection and discriminative label identification | p. 390 |
| Mining inter-entity semantic relations using improved transductive learning | p. 402 |
| A preliminary work on classifying time granularities of temporal questions | p. 414 |
| Classification of multiple-sentence questions | p. 426 |
| A rule based syllabification algorithm for Sinhala | p. 438 |
| An ensemble of grapheme and phoneme for machine transliteration | p. 450 |
| Improving statistical word alignment with ensemble methods | p. 462 |
| Empirical study of utilizing morph-syntactic information in SMT | p. 474 |
| Instance-based generation for interactive restricted domain question answering systems | p. 486 |
| Answering definition questions using Web knowledge bases | p. 498 |
| Exploring syntactic relation patterns for question answering | p. 507 |
| Web-based unsupervised learning for query formulation in question answering | p. 519 |
| A chunking strategy towards unknown word detection in Chinese word segmentation | p. 530 |
| A lexicon-constrained character model for Chinese morphological analysis | p. 542 |
| Relative compositionality of multi-word expressions : a study of verb-noun (V-N) collocations | p. 553 |
| Automatic extraction of fixed multiword expressions | p. 565 |
| Phrase-based statistical machine translation : a level of detail approach | p. 576 |
| Why is zero marking important in Korean? | p. 588 |
| A phrase-based context-dependent joint probability model for named entity translation | p. 600 |
| Machine translation based on constraint-based synchronous grammar | p. 612 |
| A machine learning approach to sentence ordering for multidocument summarization and its evaluation | p. 624 |
| Significant sentence extraction by euclidean distance based on singular value decomposition | p. 636 |
| Two-phase biomedical named entity recognition using a hybrid method | p. 646 |
| Heuristic methods for reducing errors of geographic named entities learned by bootstrapping | p. 658 |
| Building a Japanese-Chinese dictionary using Kanji/Hanzi conversion | p. 670 |
| Automatic acquisition of basic katakana lexicon from a given corpus | p. 682 |
| CTEMP : a Chinese temporal parser for extracting and normalizing temporal information | p. 694 |
| French-English terminology extraction from comparable corpora | p. 707 |
| A twin-candidate model of coreference resolution with non-anaphor identification capability | p. 719 |
| Improving Korean speech acts analysis by using shrinkage and discourse stack | p. 731 |
| Anaphora resolution for biomedical literature by exploiting multiple resources | p. 742 |
| Automatic slide generation based on discourse structure analysis | p. 754 |
| Using the structure of a conceptual network in computing semantic relatedness | p. 767 |
| Semantic role labelling of prepositional phrases | p. 779 |
| Global path-based refinement of noisy graphs applied to verb semantics | p. 792 |
| Semantic role tagging for Chinese at the lexical level | p. 804 |
| Detecting article errors based on the mass count distinction | p. 815 |
| Principles of non-stationary hidden Markov model and its applications to sequence labeling task | p. 827 |
| Integrating punctuation rules and Naive bayesian model for Chinese creation title recognition | p. 838 |
| A connectionist model of anticipation in visual worlds | p. 849 |
| Automatically inducing a part-of-speech tagger by projecting from multiple source languages across aligned corpora | p. 862 |
| The verbal entries and their description in a grammatical information-dictionary of contemporary Tibetan | p. 874 |
| Tense tagging for verbs in cross-lingual context : a case study | p. 885 |
| Regularisation techniques for conditional random fields : parameterised versus parameter-free | p. 896 |
| Exploiting lexical conceptual structure for paraphrase generation | p. 908 |
| Word sense disambiguation by relative selection | p. 920 |
| Towards robust high performance word sense disambiguation of English verbs using rich linguistic features | p. 933 |
| Automatic interpretation of noun compounds using WordNet similarity | p. 945 |
| An empirical study on language model adaptation using a metric of domain similarity | p. 957 |
| A comparative study of language models for book and author recognition | p. 969 |
| Lexical choice via topic adaptation for paraphrasing written language to spoken language | p. 981 |
| A case-based reasoning approach for speech corpus generation | p. 993 |
| Web-based terminology translation mining | p. 1004 |
| Extracting terminologically relevant collocations in the translation of Chinese monograph | p. 1017 |
| Table of Contents provided by Blackwell. All Rights Reserved. |
