Sciweavers

NAACL
2007
13 years 6 months ago
A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation
We compare two pivot strategies for phrase-based statistical machine translation (SMT), namely phrase translation and sentence translation. The phrase translation strategy means t...
Masao Utiyama, Hitoshi Isahara
NAACL
2007
13 years 6 months ago
Near-Synonym Choice in an Intelligent Thesaurus
An intelligent thesaurus assists a writer with alternative choices of words and orders them by their suitability in the writing context. In this paper we focus on methods for auto...
Diana Zaiu Inkpen
NAACL
2007
13 years 6 months ago
Combining Lexical and Grammatical Features to Improve Readability Measures for First and Second Language Texts
This work evaluates a system that uses interpolated predictions of reading difficulty that are based on both vocabulary and grammatical features. The combined approach is compared...
Michael Heilman, Kevyn Collins-Thompson, Jamie Cal...
NAACL
2007
13 years 6 months ago
Lexicalized Markov Grammars for Sentence Compression
We present a sentence compression system based on synchronous context-free grammars (SCFG), following the successful noisy-channel approach of (Knight and Marcu, 2000). We define...
Michel Galley, Kathleen McKeown
NAACL
2007
13 years 6 months ago
A Unified Local and Global Model for Discourse Coherence
Micha Elsner, Joseph Austerweil, Eugene Charniak
NAACL
2007
13 years 6 months ago
Statistical Phrase-Based Post-Editing
This article describes a machine translation system based on an automatic post-editing strategy: initially translate the input text into the target-language using a rule-based MT ...
Michel Simard, Cyril Goutte, Pierre Isabelle
NAACL
2007
13 years 6 months ago
Using "Annotator Rationales" to Improve Machine Learning for Text Categorization
We propose a new framework for supervised machine learning. Our goal is to learn from smaller amounts of supervised training data, by collecting a richer kind of training data: an...
Omar Zaidan, Jason Eisner, Christine D. Piatko
NAACL
2007
13 years 6 months ago
Applying Many-to-Many Alignments and Hidden Markov Models to Letter-to-Phoneme Conversion
Letter-to-phoneme conversion generally requires aligned training data of letters and phonemes. Typically, the alignments are limited to one-to-one alignments. We present a novel t...
Sittichai Jiampojamarn, Grzegorz Kondrak, Tarek Sh...
NAACL
2007
13 years 6 months ago
Worst-Case Synchronous Grammar Rules
We relate the problem of finding the best application of a Synchronous ContextFree Grammar (SCFG) rule during parsing to a Markov Random Field. This representation allows us to u...
Daniel Gildea, Daniel Stefankovic
NAACL
2007
13 years 6 months ago
Improved Inference for Unlexicalized Parsing
We present several improvements to unlexicalized parsing with hierarchically state-split PCFGs. First, we present a novel coarse-to-fine method in which a grammar’s own hierarc...
Slav Petrov, Dan Klein