# Living Machines: A study of atypical animacy

arXiv: https://arxiv.org/abs/2005.11140 · HTML: https://mlsanity.com/paper/2005.11140/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2020.

## Built on by (most cited first, 14 of 14)

- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4](https://mlsanity.com/paper/2305.00118/) (2023)
- [Mirages: On Anthropomorphism in Dialogue Systems](https://mlsanity.com/paper/2305.09800/) (2023)
- [Alexa, Google, Siri: What are Your Pronouns? Gender and Anthropomorphism in the Design and Perception of Conversational Assistants](https://mlsanity.com/paper/2106.02578/) (2021)
- [Discovering Differences in the Representation of People using Contextualized Semantic Axes](https://mlsanity.com/paper/2210.12170/) (2022)
- [When Language Models Fall in Love: Animacy Processing in Transformer Language Models](https://mlsanity.com/paper/2310.15004/) (2023)
- [On Classification with Large Language Models in Cultural Analytics](https://mlsanity.com/paper/2410.12029/) (2024)
- [Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems](https://mlsanity.com/paper/2210.12429/) (2022)
- [Neural Language Models for Nineteenth-Century English](https://mlsanity.com/paper/2105.11321/) (2021)
- [An Assessment of the Impact of OCR Noise on Language Models](https://mlsanity.com/paper/2202.00470/) (2022)
- [Metadata Might Make Language Models Better](https://mlsanity.com/paper/2211.10086/) (2022)
- [Estranged Predictions: Measuring Semantic Category Disruption with Masked Language Modelling](https://mlsanity.com/paper/2511.08109/) (2025)
- [Where Animacy Lives in Large Language Models: Tracing the Circuits of the Animacy Concept](https://mlsanity.com/paper/2607.20995/) (2026)
- [Crossing the Gender Binary: Modelling Gendered Reference in Science Fiction and General Fiction](https://mlsanity.com/paper/2610.19028/) (2026)

## Abstract (arXiv)

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.