Increasing Robustness for Cross-domain Dialogue Act Classification on Social Media Data

Keyphrases

• Cross-domain 100%
• Social Media Data 100%
• Dialogue Act Classification 100%
• High Performance 25%
• Social Media 25%
• Natural Language Processing 25%
• Processing Task 25%
• Performance Improvement 25%
• Language Variation 25%
• Lexical Normalization 25%
• In-domain 25%
• Utterance 25%
• Transformer-based 25%
• Language Types 25%
• Non-standard Form 25%
• Cross-domain Data 25%
• Resampling 25%

Computer Science

• Social Medium Data 100%
• Natural Language Processing 50%
• Data Source 50%
• Processing Task 50%
• Data Domain 50%
• Performance Improvement 50%