Improving MT Word Alignment Using Aligned Multi-Stage Parses

Nianwen Xue; Adam Meyers; Michiko Kosaka; Shasha Liao

Back

Improving MT Word Alignment Using Aligned Multi-Stage Parses

Conference paper

Open access

Improving MT Word Alignment Using Aligned Multi-Stage Parses

Nianwen Xue, Adam Meyers, Michiko Kosaka and Shasha Liao

SSST-5: Fifth Workshop on Syntax, Semantics and Structure in Statistical Translation (at ACL HLT 2011), 5 (Portland, OR, 06/23/2011)

06/23/2011

Abstract

Chinese Language or Literature

Computational Linguistics

English Language or Literature

Machine Translation

We use hand-coded rules and graph-aligned logical dependencies to reorder English text towards Chinese word order. We obtain a 1.5% higher F-score for Giza++ compared to running with unprocessed text. We describe this research and its implications for SMT.

Files and links (1)

url

Improving MT Word Alignment Using Aligned Multi-Stage ParsesView

paper bib and textCC BY-NC V3.0, Open

Metrics

5 Record Views

Details

Title: Improving MT Word Alignment Using Aligned Multi-Stage Parses
Creators: Nianwen Xue (Author) - Brandeis University, Michtom School of Computer Science
Adam Meyers (Author)
Michiko Kosaka (Author) - Monmouth University
Shasha Liao (Author) - New York University
Conference: SSST-5: Fifth Workshop on Syntax, Semantics and Structure in Statistical Translation (at ACL HLT 2011), 5 (Portland, OR, 06/23/2011)
Number of pages: 10
Identifiers: 9924148844701921
Academic Unit: Benjamin and Mae Volen National Center for Complex Systems; Interdepartmental Program in Linguistics and Computational Linguistics; Michtom School of Computer Science
Language: Chinese; English
Resource Type: Conference paper

Improving MT Word Alignment Using Aligned Multi-Stage Parses

Abstract

Files and links (1)

Metrics

Details

Brandeis University Social media