Trends and Opportunities -- Has Computational Linguistics Become More Applied? -- Opportunities for Natural Language Processing Research in Education -- Linguistic Knowledge Representation Formalisms -- Information Structure in a Formal Framework -- A Karaka Based Annotation Scheme for English -- Corpus Analysis and Lexical Resources -- Substring Statistics -- Evaluation of the Syntactic Annotation in EPEC, the Reference Corpus for the Processing of Basque -- Reducing Noise in Labels and Features for a Real World Dataset: Application of NLP Corpus Annotation Methods -- Unsupervised Classification of Verb Noun Multi-Word Expression Tokens -- Extraction of Lexical Knowledge -- Semantic Mapping for Related Term Identification -- An Improved Automatic Term Recognition Method for Spanish -- Bootstrapping a Verb Lexicon for Biomedical Information Extraction -- TermeX: A Tool for Collocation Extraction -- Morphology and Parsing -- Guessers for Finite-State Transducer Lexicons -- Combining Language Modeling and Discriminative Classification for Word Segmentation -- Formal Grammar for Hispanic Named Entities Analysis -- Automatic Extraction of Clause Relationships from a Treebank -- A General Method for Transforming Standard Parsers into Error-Repair Parsers -- Semantics -- Topic-Focus Articulation from the Semantic Point of View -- The Value of Weights in Automatically Generated Text Structures -- AORTE for Recognizing Textual Entailment -- Word Sense Disambiguation -- Semi-supervised Word Sense Disambiguation Using the Web as Corpus -- Semi-supervised Clustering for Word Instances and Its Effect on Word Sense Disambiguation -- Alleviating the Problem of Wrong Coreferences in Web Person Search -- Improved Unsupervised Name Discrimination with Very Wide Bigrams and Automatic Cluster Stopping -- Machine Translation and Multilinguism -- Enriching Statistical Translation Models Using a Domain-Independent Multilingual Lexical Knowledge Base -- Exploiting Parallel Treebanks to Improve Phrase-Based Statistical Machine Translation -- Cross-Language Frame Semantics Transfer in Bilingual Corpora -- A Parallel Corpus Labeled Using Open and Restricted Domain Ontologies -- Language Identification on the Web: Extending the Dictionary Method -- Information Extraction and Text Mining -- Business Specific Online Information Extraction from German Websites -- Low-Cost Supervision for Multiple-Source Attribute Extraction -- An Integrated Architecture for Processing Business Documents in Turkish -- Detecting Protein-Protein Interactions in Biomedical Texts Using a Parser and Linguistic Resources -- Learning to Learn Biological Relations from a Small Training Set -- Using a Bigram Event Model to Predict Causal Potential -- Semantic-Based Temporal Text-Rule Mining -- Generating Executable Scenarios from Natural Language -- Determining the Polarity and Source of Opinions Expressed in Political Debates -- Information Retrieval and Text Comparison -- Query Translation and Expansion for Searching Normal and OCR-Degraded Arabic Text -- NLP for Shallow Question Answering of Legal Documents Using Graphs -- Semantic Clustering for a Functional Text Classification Task -- Reducing the Plagiarism Detection Search Space on the Basis of the Kullback-Leibler Distance -- Empirical Paraphrasing of Modern Greek Text in Two Phases: An Application to Steganography -- BorderFlow: A Local Graph Clustering Algorithm for Natural Language Processing -- Generalized Mongue-Elkan Method for Approximate Text String Comparison -- Text Summarization -- Estimating Risk of Picking a Sentence for Document Summarization -- The Decomposition of Human-Written Book Summaries -- Applications to the Humanities -- Linguistic Ethnography: Identifying Dominant Word Classes in Text.