Sciweavers

EMNLP
2004
13 years 6 months ago
Evaluating Information Content by Factoid Analysis: Human annotation and stability
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...
Simone Teufel, Hans van Halteren
EMNLP
2004
13 years 6 months ago
A Boosting Algorithm for Classification of Semi-Structured Text
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...
Taku Kudo, Yuji Matsumoto
EMNLP
2004
13 years 6 months ago
Scaling Web-based Acquisition of Entailment Relations
Paraphrase recognition is a critical step for natural language interpretation. Accordingly, many NLP applications would benefit from high coverage knowledge bases of paraphrases. ...
Idan Szpektor, Hristo Tanev, Ido Dagan, Bonaventur...
EMNLP
2004
13 years 6 months ago
Max-Margin Parsing
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 ...
Ben Taskar, Dan Klein, Mike Collins, Daphne Koller...
EMNLP
2004
13 years 6 months ago
Multi-Document Biography Summarization
In this paper we describe a biography summarization system using sentence classification and ideas from information retrieval. Although the individual techniques are not new, asse...
Liang Zhou, Miruna Ticrea, Eduard H. Hovy
EMNLP
2004
13 years 6 months ago
A Resource-light Approach to Russian Morphology: Tagging Russian using Czech resources
In this paper, we describe a resource-light system for the automatic morphological analysis and tagging of Russian. We eschew the use of extensive resources (particularly, large a...
Jiri Hana, Anna Feldman, Chris Brew
EMNLP
2004
13 years 6 months ago
Automatic Analysis of Plot for Story Rewriting
A method for automatic plot analysis of narrative texts that uses components of both traditional symbolic analysis of natural language and statistical machine-learning is presente...
Harry Halpin, Johanna D. Moore, Judy Robertson
EMNLP
2004
13 years 6 months ago
Monolingual Machine Translation for Paraphrase Generation
We apply statistical machine translation (SMT) tools to generate novel paraphrases of input sentences in the same language. The system is trained on large volumes of sentence pair...
Chris Quirk, Chris Brockett, William B. Dolan
EMNLP
2004
13 years 6 months ago
LexPageRank: Prestige in Multi-Document Text Summarization
Multidocument extractive summarization relies on the concept of sentence centrality to identify the most important sentences in a document. Centrality is typically defined in term...
Günes Erkan, Dragomir R. Radev