Sciweavers

EMNLP
2007
13 years 6 months ago
Semi-Supervised Structured Output Learning Based on a Hybrid Generative and Discriminative Approach
This paper proposes a framework for semi-supervised structured output learning (SOL), specifically for sequence labeling, based on a hybrid generative and discriminative approach...
Jun Suzuki, Akinori Fujino, Hideki Isozaki
EMNLP
2007
13 years 6 months ago
Part-of-Speech Tagging for Middle English through Alignment and Projection of Parallel Diachronic Texts
We demonstrate an approach for inducing a tagger for historical languages based on existing resources for their modern varieties. Tags from Present Day English source text are pro...
Taesun Moon, Jason Baldridge
EMNLP
2007
13 years 6 months ago
Using Foreign Inclusion Detection to Improve Parsing Performance
Inclusions from other languages can be a significant source of errors for monolingual parsers. We show this for English inclusions, which are sufficiently frequent to present a ...
Beatrice Alex, Amit Dubey, Frank Keller
EMNLP
2007
13 years 6 months ago
Compressing Trigram Language Models With Golomb Coding
Trigram language models are compressed using a Golomb coding method inspired by the original Unix spell program. Compression methods trade off space, time and accuracy (loss). The...
Kenneth Church, Ted Hart, Jianfeng Gao
EMNLP
2007
13 years 6 months ago
Characterizing the Errors of Data-Driven Dependency Parsing Models
We present a comparative error analysis of the two dominant approaches in datadriven dependency parsing: global, exhaustive, graph-based models, and local, greedy, transition-base...
Ryan T. McDonald, Joakim Nivre
EMNLP
2007
13 years 6 months ago
Finding Good Sequential Model Structures using Output Transformations
In Sequential Viterbi Models, such as HMMs, MEMMs, and Linear Chain CRFs, the type of patterns over output sequences that can be learned by the model depend directly on the model...
Edward Loper
EMNLP
2007
13 years 6 months ago
Experimental Evaluation of LTAG-Based Features for Semantic Role Labeling
In this technical report, we propose the use of Lexicalized Tree-Adjoining Grammar (LTAG) formalism as an important additional source of features for the Semantic Role Labeling (S...
Yudong Liu, Anoop Sarkar
EMNLP
2007
13 years 6 months ago
A Discriminative Learning Model for Coordinate Conjunctions
We propose a sequence-alignment based method for detecting and disambiguating coordinate conjunctions. In this method, averaged perceptron learning is used to adapt the substituti...
Masashi Shimbo, Kazuo Hara
EMNLP
2007
13 years 6 months ago
Modelling Compression with Discourse Constraints
Sentence compression holds promise for many applications ranging from summarisation to subtitle generation and subtitle generation. The task is typically performed on isolated sen...
James Clarke, Mirella Lapata