WhatToSee

Index of COLING 2004

• A Deterministic Word Dependency Analyzer Enhanced With Preference Learning
• A Formal Model for Information Selection in Multi-Sentence Text Extraction
• A High-Performance Coreference Resolution System using a Constraint-based Multi-Agent Strategy
• A Language Indep endent Metho d for Question Classification
• A Lemma-Based Approach to a Maximum Entropy Word Sense Disambiguation System for Dutch
• A Multiple-Do cument Summarization System with User Interaction
• A Natural Language Processing Infrastructure for Turkish
• A Path-based Transfer Model for Machine Translation
• A Relational Syntax-Semantics Interface Based on Dependency Grammar
• A Support System for Revising Titles to Stimulate the Lay Reader’s Interest in Technical Achievements
• A System for Generating Descriptions of Sets of Objects in a Rich Variety
• A Trigger Language Model-based IR System
• A Unified Approach in Sp eech-to-Sp eech Translation: Integrating Features of Sp eech Recognition and Machine Translation
• A grammar formalism and parser for linearization-based HPSG
• Acquiring an Ontology for a Fundamental Vo cabulary
• Acquisition of Semantic Classes for Adjectives from Distributional Evidence
• An Algorithmic Framework for the Deco ding Problem in Statistical Machine Translation
• An NP-Cluster Based Approach to Coreference Resolution
• Analysis and Detection of Reading Miscues for Interactive Literacy Tutors
• Annotating and measuring temporal relations in texts
• Automated Alignment and Extraction of Bilingual Ontology for Cross-Language Domain-Specific Applications
• Automated Induction of Sense in Context
• Automatic Construction of Japanese KATAKANA Variant List from Large Corpus
• Automatic Construction of Nominal Case Frames and its Application to Indirect Anaphora Resolution
• Automatic Identification of Infrequent Word Senses
• Automatic Learning of Language Mo del Structure
• Automatic extraction of paraphrastic phrases from medium size corpora
• Back Transliteration from Japanese to English Using Target English Context
• BiFrameNet: Bilingual Frame Semantics Resource Construction by Cross-lingual Induction
• Bilingual-Dictionary Adaptation to Domains
• Browsing Help for Faster Document Retrieval
• Cascading Use of Soft and Hard Matching Pattern Rules for Weakly Supervised Information Extraction
• Characterising Measures of Lexical Distributional Similarity
• Chinese Segmentation and New Word Detection using Conditional Random Fields
• Chinese and Japanese Word Segmentation Using Word-Level and Character-Level Information
• Classifying Ellipsis in Dialogue: A Machine Learning Approach
• Cognate Mapping — A Heuristic Strategy for the Semi-Supervised Acquisition of a Spanish Lexicon from a Portuguese Seed Lexicon
• Collocation Extraction Based on Modifiability Statistics
• Combining Hierarchical Clustering and Machine Learning to Predict High-Level Discourse Structure
• Combining Linguistic Features with Weighted Bayesian Classifier for Temporal Reference Processing
• Combining Prediction by Partial Matching and Logistic Regression for Thai Word Segmentation
• Computational Cognitive Linguistics
• Constraint-based RMRS Construction from Shallow Grammars
• Construction of an Objective Hierarchy of Abstract Concepts via Directional Similarity
• Contextual pro cessing of lo cative prep ositional phrases
• Controlling Gender Equality with Shallow NLP Techniques
• Corpus and Evaluation Measures for Multiple Document Summarization with Multiple Sources
• Creative Discovery in Lexical Ontologies
• Cross-lingual Information Extraction System Evaluation
• Deep Linguistic Analysis for the Accurate Identification of Predicate-Argument Relations
• Deeper Sentiment Analysis Using Machine Translation Technology
• Dependency Structure Analysis and Sentence Boundary Detection in Sp ontaneous Japanese
• Dependency-based Sentence Alignment for Multiple Document Summarization
• Detecting Multiword Verbs in the English Sublanguage of MEDLINE Abstracts
• Detecting Transliterated Orthographic Variants via Two Similarity Metrics
• Detection of Question-Answer Pairs in Email Conversations
• Determining the Sentiment of Opinions
• Deterministic Dependency Parsing of English Text
• Direct Orthographical Mapping for Machine Transliteration
• Discovering word senses from a network of lexical cooccurrences
• Discriminative Hidden Markov Modeling with Long State Dependence using a kNN Ensemble
• Discriminative Slot Detection Using Kernel Methods
• Document Re-ranking Based on Automatically Acquired Key Terms in Chinese Information Retrieval
• Efficient Parsing of Highly Ambiguous Context-Free Grammars with Bit Vectors
• Emdros – a text database engine for analyzed or annotated text
• Enhancing automatic term recognition through recognition of variation
• Evaluating Cross-Language Annotation Transfer in the MultiSemCor Corpus
• Example-based Machine Translation Based on Syntactic Transfer with Statistical Models
• Extending MT evaluation tools with translation complexity metrics
• Extracting Hyponyms of Prespecified Hypernyms from Itemizations and Headings in Web Documents
• Efficient Confirmation Strategy for Large-scale Text Retrieval Systems with Sp oken Dialogue Interface
• FASIL Email Summarisation System
• Fast Computation of Lexical Affinity Models
• Feature Vector Quality and Distributional Similarity
• Feature Weighting for Co-occurrence-based Classification of Words
• Filtering Speaker-Specific Words from Electronic Discussions
• Fine-Grained Word Sense Disambiguation Based on Parallel Corpora, Word Alignment, Word Clustering and Aligned Wordnets
• FrameNet-based Semantic Parsing using Maximum Entropy Models
• From Controlled Do cument Authoring to Interactive Do cument Normalization
• Generalizing Dimensionality in Combinatory Categorial Grammar
• Generating Discourse Structures for Written Texts
• Generating Overview Summaries of Ongoing Email Thread Discussions
• Generation of Relative Referring Expressions based on Perceptual Grouping
• HITIQA: Towards Analytical Question Answering
• High-Performance Tagging on Medical Texts
• Identification of Confusable Drug Names: A New Approach and Evaluation Methodology
• Improved Word Alignment Using a Symmetric Lexicon Mo del
• Improving Chronological Sentence Ordering by Precedence Relation
• Improving Japanese Zero Pronoun Resolution by Global Word Sense Disambiguation
• Improving Statistical Machine Translation in the Medical Domain using the Unified Medical Language System
• Improving Statistical Word Alignment with a Rule-Based Machine Translation System
• Improving Word Alignment Quality using Morpho-syntactic Information
• Information Extraction for Question Answering: Improving Recall Through Syntactic Patterns
• Integrating Cross-Lingually Relevant News Articles and Monolingual Web Do cuments in Bilingual Lexicon Acquisition
• Interpreting Vague Utterances in Context
• Japanese Unknown Word Identification by Character-based Chunking
• Knowledge Intensive Word Alignment with KNOWA
• Kullback-Leibler Distance b etween Probabilistic Context-Free Grammars and Probabilistic Finite Automata
• Language Model Adaptation for Statistical Machine Translation with Structured Query Models
• Learning Greek Verb Complements: Addressing the Class Imbalance
• Learning a Robust Word Sense Disambiguation Mo del using Hyp ernyms in Definition Sentences
• Learning theories from text
• Learning to Identify Single-Snippet Answers to Definition Questions
• Lexicalisation Strategies in Cooperative Question-Answering Systems
• Linguistic correlates of style: authorship classification with deep linguistic analysis features
• Linguistic profiling of texts for the purpose of language verification
• Linguistically Informed Statistical Models of Constituent Structure for Ordering in Sentence Realization
• Lower and higher estimates of the number of “true analogies” between sentences contained in a large multilingual corpus
• Machine-Assisted Rhetorical Structure Annotation
• Medical WordNet: A New Methodology for the Construction and Validation of Information Resources for Consumer Health
• Modern Natural Language Interfaces to Databases: Composing Statistical Parsing with Semantic Tractability
• Morpheme-based Derivation of Bipolar Semantic Orientation of Chinese Words
• Multi-Human Dialogue Understanding for Assisting Artifact-Pro ducing Meetings
• Multi-level Bootstrapping for Extracting Parallel Sentences from a Quasi-Comparable Corpus
• Multilingual and cross-lingual news topic tracking
• Named Entity Discovery Using Comparable News Articles
• ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation
• Online Generic Editing of Heterogeneous Dictionary Entries in Papillon Pro ject
• Optimizing Algorithms for Pronoun Resolution
• Optimizing disambiguation in Swahili
• PageRank on Semantic Networks, with Application to Word Sense Disambiguation
• Part of Speech Tagging in Context
• Partially Distribution-Free Learning of Regular Languages from Positive Samples
• Playing the Telephone Game: Determining the Hierarchical Structure of Perspective and Speech Expressions
• Polarization and abstraction of grammatical formalisms as metho ds for lexical disambiguation
• Probabilistic Sentence Reduction Using Supp ort Vector Machines
• Quantitative and Qualitative Evaluation of the OntoLearn Ontology Learning System
• Query Translation by Text Categorization
• Reordering Constraints for Phrase-Based Statistical Machine Translation
• Representing Verbal Semantics with Diagrams
• Representing discourse coherence: A corpus-based analysis
• Resolving Individual and Abstract Anaphora in Texts and Dialogues
• Restrictions on Monadic Context-Free Tree Grammars
• Robust Sub-Sentential Alignment of Phrase-Structure Trees
• Semantic Role Labeling via Integer Linear Programming Inference
• Semantic Similarity Applied to Spoken Dialogue Summarization
• Semi-Supervised Training of a Kernel PCA-Based Model for Word Sense Disambiguation
• Sentiment classification on customer feedback data: noisy data, large feature vectors, and the role of linguistic analysis
• Significance tests for the evaluation of ranking methods
• Skeletons in the parser: Using a shallow parser to improve deep parsing
• Splitting Input Sentence for Machine Translation Using Language Model with Sentence Similarity
• Statistical Language Mo deling with Performance Benchmarks using Various Levels of Syntactic-Semantic Information
• Summarizing Encyclop edic Term Descriptions on the Web
• Symmetric Word Alignments for Statistical Machine Translation
• Syntactic Simplification for Improving Content Selection in Multi-Document Summarization
• Syntax-Based Alignment: Supervised or Unsupervised?
• Tagging with Hidden Markov Mo dels Using Ambiguous Tags
• Talking Robots With LEGO MindStorms
• Term Aggregation: Mining Synonymous Expressions using Personal Stylistic Variations
• Thai Spelling Recognition Using a Continuous Speech Corpus
• The Importance of Supertagging for Wide-Coverage CCG Parsing
• The Queen’s Agents: Using Collaborating Object-Based Dialogue Agents in the Queen’s Communicator
• Towards Terascale Knowledge Acquisition
• Trajectory Based Word Sense Disambiguation
• Type-inheritance Combinatory Categorial Grammar
• Understanding Students’ Explanations in Geometry Tutoring
• Unificational Combinatory Categorial Grammar:
• Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources
• Using Bag-of-Concepts to Improve the Performance of Supp ort Vector Machines in Text Categorization
• Using Gene Expression Programming to Construct Sentence Ranking Functions for Text Summarization
• Using Syntactic Information to Extract Relevant Terms for Multi-Document Summarization
• Using a Mixture of N-Best Lists from Multiple MT Systems in Rank-Sum-Based Confidence Measure for MT Outputs ∗
• Verb Phrase Ellipsis detection using Automatically Parsed Text
• Why Nitpicking Works: Evidence for Occam’s Razor in Error Correctors
• Wide-Coverage Semantic Representations from a C C G Parser
• Word Sense Disambiguation using a dictionary for sense similarity measure
• Word sense disambiguation criteria: a systematic study
• Word to word alignment strategies