- Keywords: Span-Relation Representation, Task-Independent Framework, Natural Language Analysis, Benchmark
- TL;DR: We use a single model to solve a great variety of natural language analysis tasks by formulating them in a unified span-relation format.
- Abstract: A large number of natural language processing tasks exist to analyze syntax, semantics, and information content of human language. These seemingly very different tasks are usually solved by 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. We perform extensive experiments to test this insight on 10 disparate tasks as broad as dependency parsing (syntax), semantic role labeling (semantics), relation extraction (information content), aspect based sentiment analysis (sentiment), and many others, achieving comparable performance as state-of-the-art specialized models. We further demonstrate benefits in multi-task learning. We convert these datasets into a unified format to build a benchmark, which provides a holistic testbed for evaluating future models for generalized natural language analysis.