AMTEXT: Extractionbased MT for Arabic

1
AMTEXTExtraction-based MT for Arabic

• Faculty
• Alon Lavie, Jaime Carbonell
• Students and Staff
• Laura Kieras, Peter Jansen
• Informant
• Loubna El Abadi

2
Goals and Approach

• Analysts often are looking for limited concrete
  information within the text ? full MT may not be
  necessary
• Alternative rather than full MT followed by
  extraction, first extract and then translate only
  extracted information
• AMTEXT approach
• learn extraction patterns and their translations
  from small amounts of human translated and
  aligned data
• Combine with broad coverage Named-Entity
  translation lexicons
• System output translation of extracted
  information a structured representation

3
AMTEXT Extraction-based MT
Word-aligned elicited data
Source Text
Learning Module
Run Time Extract Transfer System
Transfer Rules
Filled Template
Partial Parser Transfer Engine
SS NE-P pagash et NE-P TE -gt NE-P met with
NE-P TE((X1Y1) (X4Y4) (X5Y5))
Extracted Target Text
Post-processor Extractor
NE Translation Lexicon
Word Translation Lexicon
4
Elicitation Example
5
Partial Parsing

• Input Full text in the foreign language
• Output Translation of extracted/matched text
• Goal Extract by effectively matching transfer
  rules with the full text
• Identify/parse NEs and words in restricted
  vocabulary
• Identify transfer-rule (source-side) patterns
• Handle expected high-levels of ambiguity

Sharon, meluve b-sar ha-xuc shalom, yipagesh im
bush hayom
NE-P
NE-P
NE-P
TE
Sharon will meet with Bush today
6
Proof-of-Concept System

• funded by small year-0 ITIC/REFLEX
• Arabic-to-English
• Newswire text (available from TIDES)
• Limited set of actions (X meet Y)
• Limited translation patterns
• ltPerson-NEgt ltmeet-verbgt ltPerson-NEgt ltLOCgt ltTEgt
• Limited vocabulary and NE lexicon

7
Demonstration

• http//www-2.cs.cmu.edu/afs/cs/user/alavie/Avenue/
  tmp/demo20sep/met.dev.htm

8
Integration Technical Issues

• Components
• Converter of Arabic to Darwish representation
  and pre-processor (scripts)
• Transfer Engine (C/C)
• Post-processor extractor (perl scripts)
• Input Arabic text in UTF8
• Output formatted html page