Generalizing Natural Language Analysis through Span-relation Representations

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple insight that a great variety of tasks can be represented in a single unified format consisting of labeling spans and relations between spans, thus a single task-independent model can be used across different tasks... (read more)

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Named Entity Recognition CoNLL 2003 (English) SpanRel F1 92.2 # 27
Semantic Role Labeling (predicted predicates) CoNLL 2012 SpanRel F1 82.4 # 3
Part-Of-Speech Tagging Penn Treebank SpanRel Accuracy 97.7 # 5
Dependency Parsing Penn Treebank SpanRel LAS 94.7 # 8
Constituency Parsing Penn Treebank SpanRel F1 score 95.5 # 8
Relation Extraction SemEval-2010 Task 8 SpanRel F1 87.4 # 11
Relation Extraction WLPC SpanRel F1 65.5 # 1
Named Entity Recognition WLPC SpanRel F1 79.2 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet