Probabilistic Frame Induction

TL;DR

This paper introduces a probabilistic method for automatically inducing semantic frames from text, improving upon previous ad hoc techniques by providing a more robust, extendable, and state-of-the-art approach that models frames, events, and participants as latent topics.

Contribution

It presents the first probabilistic framework for frame induction, incorporating frames, events, and participants as latent topics, and uses a novel split-merge method to infer the number of frames.

Findings

Achieved state-of-the-art results in frame induction tasks.

Reduced engineering effort compared to previous methods.

Effectively models frames, events, and participants as latent topics.

Abstract

In natural-language discourse, related events tend to appear near each other to describe a larger scenario. Such structures can be formalized by the notion of a frame (a.k.a. template), which comprises a set of related events and prototypical participants and event transitions. Identifying frames is a prerequisite for information extraction and natural language generation, and is usually done manually. Methods for inducing frames have been proposed recently, but they typically use ad hoc procedures and are difficult to diagnose or extend. In this paper, we propose the first probabilistic approach to frame induction, which incorporates frames, events, participants as latent topics and learns those frame and event transitions that best explain the text. The number of frames is inferred by a novel application of a split-merge method from syntactic parsing. In end-to-end evaluations from text to induced frames and extracted facts, our method produced state-of-the-art results while substantially reducing engineering effort.