Invited Speakers -- WordsEye: A Text-to-Scene Conversion System -- Automatic Anaphora Resolution: Limits, Impediments, and Ways Forward -- Pragmatics, Discourse, Semantics, Syntax, and the Lexicon -- Feature-Based WSD: Why We Are at a Dead-End -- Improving Feature Selection for Maximum Entropy-Based Word Sense Disambiguation -- Heuristics-Based Replenishment of Collocation Databases -- On the Analysis of Locative Phrases with Graphs and Lexicon-Grammar: The Classifier/Proper Noun Pairing -- The Role of Pause Occurrence and Pause Duration in the Signaling of Narrative Structure -- A Grammar-Based System to Solve Temporal Expressions in Spanish Texts -- Semantic Information in Anaphora Resolution -- A Type of Transitive Inalienable Possession Construction in Korean -- The Treatment of Numbers in Polish by Graphs -- From Syntax to Semantics: Taking Advantages of 5P -- Processing Discontinuity -- Resolution of Demonstrative Anaphoric References in Portuguese Written Texts -- Interpreting and Generating Spoken and Written Language -- Large Vocabulary Continuous Speech Recognition Using Weighted Finite-State Transducers -- Building Language Models for Continuous Speech Recognition Systems -- Language-Oriented Information Retrieval, Question Answering, Summarization, and Information Extraction -- Relevant Information Extraction Driven with Rhetorical Schemas to Summarize Scientific Papers -- Language-Oriented Machine Learning -- Mapping an Automated Survey Coding Task into a Probabilistic Text Categorization Framework -- Combining Multiclass Maximum Entropy Text Classifiers with Neural Network Voting -- Multi-lingual Processing, Machine Translation, and Translation Aids -- Compound Temporal Adverbs in Portuguese and in Spanish -- Description of a Multilingual Database of Proper Names -- Natural Language Interfaces and Dialogue Systems -- A Project of Speech Input and Output in an E-commerce Application -- Ambiguity Reports for Flexible Dialog Management -- A Natural Language Dialogue Manager for Accessing Databases -- Helping the Composition of Help Contents -- Meteo: A Telephone-Based Portuguese Conversation System in Weather Domain -- Tools and Resources -- Concluding Remarks on Multi-band and Multi-stream Research for Noise-Robust ASR -- Groundwork for the Development of the Brazilian Portuguese Wordnet -- Linguistic Processing of Biomedical Texts -- DISPARA, a System for Distributing Parallel Corpora on the Web -- Using Morphological, Syntactical, and Statistical Information for Automatic Term Acquisition -- Complex Lexical Units and Automata -- Constructing Empirical Formulas for Testing Word Similarity by the Inductive Method of Model Self-Organization -- Multilingual Corpora Annotation for Processing Definite Descriptions -- Relational Data Model in Document Hierarchical Indexing -- Evaluation of Systems -- DMSumm: Review and Assessment.