Browse > Natural Language Processing > Semantic Role Labeling > Semantic Role Labeling (predicted predicates)

Semantic Role Labeling (predicted predicates)

1 papers with code · Natural Language Processing

PropBank semantic role labeling with predicted predicates.

State-of-the-art leaderboards

Greatest papers with code

Linguistically-Informed Self-Attention for Semantic Role Labeling

EMNLP 2018 strubell/LISA

Unlike previous models which require significant pre-processing to prepare linguistic features, LISA can incorporate syntax using merely raw tokens as input, encoding the sequence only once to simultaneously perform parsing, predicate detection and role labeling for all predicates. In experiments on CoNLL-2005 SRL, LISA achieves new state-of-the-art performance for a model using predicted predicates and standard word embeddings, attaining 2.5 F1 absolute higher than the previous state-of-the-art on newswire and more than 3.5 F1 on out-of-domain data, nearly 10% reduction in error.

DEPENDENCY PARSING MULTI-TASK LEARNING PART-OF-SPEECH TAGGING PREDICATE DETECTION SEMANTIC ROLE LABELING (PREDICTED PREDICATES) WORD EMBEDDINGS