Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder
This addresses a bottleneck in event argument extraction for natural language processing, offering an incremental improvement over existing methods.
The paper tackles event argument extraction by capturing interactions among event arguments, proposing a Seq2Seq-like approach with a Bi-directional Entity-level Recurrent Decoder that improves accuracy by incorporating contextual role predictions.
Capturing interactions among event arguments is an essential step towards robust event argument extraction (EAE). However, existing efforts in this direction suffer from two limitations: 1) The argument role type information of contextual entities is mainly utilized as training signals, ignoring the potential merits of directly adopting it as semantically rich input features; 2) The argument-level sequential semantics, which implies the overall distribution pattern of argument roles over an event mention, is not well characterized. To tackle the above two bottlenecks, we formalize EAE as a Seq2Seq-like learning problem for the first time, where a sentence with a specific event trigger is mapped to a sequence of event argument roles. A neural architecture with a novel Bi-directional Entity-level Recurrent Decoder (BERD) is proposed to generate argument roles by incorporating contextual entities' argument role predictions, like a word-by-word text generation process, thereby distinguishing implicit argument distribution patterns within an event more accurately.