EMNLP
2004
15 years 14 days ago
2004
This paper presents Domain Relevance Estimation (DRE), a fully unsupervised text categorization technique based on the statistical estimation of the relevance of a text with respe...
105
click to vote
EMNLP
2004
15 years 14 days ago
2004
We describe how simple, commonly understood statistical models, such as statistical dependency parsers, probabilistic context-free grammars, and word-to-word translation models, c...
EMNLP
2004
15 years 14 days ago
2004
This paper provides evidence for Genzel and Charniak's (2002) entropy rate principle, which predicts that the entropy of a sentence increases with its position in the text. W...
EMNLP
2004
15 years 14 days ago
2004
EMNLP
2004
15 years 14 days ago
2004
The morphology of Semitic languages is unique in the sense that the major word-formation mechanism is an inherently non-concatenative process of interdigitation, whereby two morph...
93
Voted
EMNLP
2004
15 years 14 days ago
2004
Accurate dependency recovery has recently been reported for a number of wide-coverage statistical parsers using Combinatory Categorial Grammar (CCG). However, overall figures give...
109
Voted
EMNLP
2004
15 years 14 days ago
2004
We present a new approach to intrinsic summary evaluation, based on initial experiments in van Halteren and Teufel (2003), which combines two novel aspects: comparison of informat...
EMNLP
2004
15 years 14 days ago
2004
The focus of research in text classification has expanded from simple topic identification to more challenging tasks such as opinion/modality identification. Unfortunately, the la...
78
Voted
EMNLP
2004
15 years 14 days ago
2004
Paraphrase recognition is a critical step for natural language interpretation. Accordingly, many NLP applications would benefit from high coverage knowledge bases of paraphrases. ...
EMNLP
2004
15 years 14 days ago
2004
We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to ...