emnlp4

emnlp 1999 论文列表

Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, EMNLP 1999, College Park, MD, USA, June 21-22, 1999.

Corpus-Based Approach for Nominal Compound Analysis for Korean Based on Linguistic and Statistical Information.
Corpus-Based Learning for Noun Phrase Coreference Resolution.
Improving Brill's Pos Tagger for an Agglutinative Language.
Using Subcategorization to Resolve Verb Class Ambiguity.
An Iterative Approach to Estimating Frequencies over a Semantic Hierarchy.
Automatically Merging Lexicons that have Incompatible Part-of-Speech Categories.
Cascaded Grammatical Relation Assignment.
PP-Attachment: A Committee Machine Approach.
Taking the load off the conference chairs-towards a digital paper-routing assistant.
Automatic Construction of Weighted String Similarity Measures.
Detecting Text Similarity over Short Passages: Exploring Linguistic Feature Combinations via Machine Learning.
Lexical ambiguity and Information Retrieval revisited.
Exploiting Diversity in Natural Language Processing: Combining Parsers.
Guiding a Well-Founded Parser with Corpus Statistics.
A Learning Approach to Shallow Parsing.
Learning Discourse Relations with Active Data Selection.
Word Informativeness and Automatic Pitch Accent Modeling.
An Information-Theoretic Empirical Analysis of Dependency-Based Feature Types for Word Prediction Models.
POS Tags and Decision Trees for Language Modeling.
Why Doesn't Natural Language Come Naturally?
HMM Specialization with Selective Lexicalization.
Hybrid Disambiguation of Prepositional Phrase Attachment and Interpretation.
Unsupervised Models for Named Entity Classification.
Language Independent Named Entity Recognition Combining Morphological and Contextual Evidence.
Noun Phrase Coreference as Clustering.
Retrieving Collocations From Korean Text.
Determining the specificity of nouns from text.
Improving POS Tagging Using Machine-Learning Techniques.
Applying Extrasentential Context To Maximum Entropy Based Tagging With A Large Semantic And Syntactic Tagset.
Boosting Applied to Tagging and PP Attachment.
Cross-Language Information Retrieval for Technical Documents.
Improved Alignment Models for Statistical Machine Translation.
Mapping Multilingual Hierarchies Using Relaxation Labeling.
Text-Translation Alignment: Three Languages Are Better Than Two.
What's Happened Since the First SIGDAT Meeting?