Improving sentence compression by learning to predict gaze
| Autor: | Yoav Goldberg, Anders Søgaard, Sigrid Klerke |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
FOS: Computer and information sciences
Sentence compression Computer Science - Computation and Language Computer science Speech recognition 05 social sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 0501 psychology and cognitive sciences 02 engineering and technology Gaze Computation and Language (cs.CL) 050105 experimental psychology |
| Zdroj: | HLT-NAACL |
| DOI: | 10.48550/arxiv.1604.03357 |
| Popis: | We show how eye-tracking corpora can be used to improve sentence compression models, presenting a novel multi-task learning algorithm based on multi-layer LSTMs. We obtain performance competitive with or better than state-of-the-art approaches. Comment: NAACL 2016. Received Best Short Paper Award |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|