Living Machines: A study of atypical animacy

TL;DR

This paper introduces a novel dataset and an unsupervised method using BERT embeddings for detecting atypical animacy, specifically when inanimate objects like machines are described as animate, improving accuracy in complex language contexts.

Contribution

The work presents the first dataset for atypical animacy detection and a BERT-based unsupervised pipeline that enhances detection accuracy in complex language scenarios.

Findings

The method outperforms previous approaches on established datasets.

It effectively captures nuanced contextual cues of atypical animacy.

The approach is adaptable to different linguistic contexts.

Abstract

This paper proposes a new approach to animacy detection, the task of determining whether an entity is represented as animate in a text. In particular, this work is focused on atypical animacy and examines the scenario in which typically inanimate objects, specifically machines, are given animate attributes. To address it, we have created the first dataset for atypical animacy detection, based on nineteenth-century sentences in English, with machines represented as either animate or inanimate. Our method builds on recent innovations in language modeling, specifically BERT contextualized word embeddings, to better capture fine-grained contextual properties of words. We present a fully unsupervised pipeline, which can be easily adapted to different contexts, and report its performance on an established animacy dataset and our newly introduced resource. We show that our method provides a substantially more accurate characterization of atypical animacy, especially when applied to highly complex forms of language use.