Sciweavers

87 search results - page 10 / 18
» Cross-Corpus Evaluation of Word Alignment
Sort
View
EMNLP
2008
13 years 10 months ago
Indirect-HMM-based Hypothesis Alignment for Combining Outputs from Machine Translation Systems
This paper presents a new hypothesis alignment method for combining outputs of multiple machine translation (MT) systems. An indirect hidden Markov model (IHMM) is proposed to add...
Xiaodong He, Mei Yang, Jianfeng Gao, Patrick Nguye...
COLING
2008
13 years 10 months ago
ParaMetric: An Automatic Evaluation Metric for Paraphrasing
We present ParaMetric, an automatic evaluation metric for data-driven approaches to paraphrasing. ParaMetric provides an objective measure of quality using a collection of multipl...
Chris Callison-Burch, Trevor Cohn, Mirella Lapata
IICAI
2007
13 years 10 months ago
Exploring Translation Similarities for Building a Better Sentence Aligner
Abstract. The approaches previously used for sentence alignment (sentence length, word correspondence and cognate matching) take into account different aspects of similarity betwe...
Anil Kumar Singh, Samar Husain
EMNLP
2004
13 years 9 months ago
Dependencies vs. Constituents for Tree-Based Alignment
Given a parallel parsed corpus, statistical treeto-tree alignment attempts to match nodes in the syntactic trees for a given sentence in two languages. We train a probabilistic tr...
Daniel Gildea
ICASSP
2010
IEEE
13 years 8 months ago
Evaluation of semantic role labeling and dependency parsing of automatic speech recognition output
Semantic role labeling (SRL) is an important module of spoken language understanding systems. This work extends the standard evaluation metrics for joint dependency parsing and SR...
Benoît Favre, Bernd Bohnet, Dilek Hakkani-T&...