Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911769811746816 |
|---|---|
| author | Yu, Mo Wang, Qiujing Zhang, Shunchi Sang, Yisi Pu, Kangsheng Wei, Zekai Wang, Han Xu, Liyan Li, Jing Yu, Yue Zhou, Jie |
| author_facet | Yu, Mo Wang, Qiujing Zhang, Shunchi Sang, Yisi Pu, Kangsheng Wei, Zekai Wang, Han Xu, Liyan Li, Jing Yu, Yue Zhou, Jie |
| contents | When reading a story, humans can quickly understand new fictional characters with a few observations, mainly by drawing analogies to fictional and real people they already know. This reflects the few-shot and meta-learning essence of humans' inference of characters' mental states, i.e., theory-of-mind (ToM), which is largely ignored in existing research. We fill this gap with a novel NLP dataset, ToM-in-AMC, the first assessment of machines' meta-learning of ToM in a realistic narrative understanding scenario. Our dataset consists of ~1,000 parsed movie scripts, each corresponding to a few-shot character understanding task that requires models to mimic humans' ability of fast digesting characters with a few starting scenes in a new movie.
We propose a novel ToM prompting approach designed to explicitly assess the influence of multiple ToM dimensions. It surpasses existing baseline models, underscoring the significance of modeling multiple ToM dimensions for our task. Our extensive human study verifies that humans are capable of solving our problem by inferring characters' mental states based on their previously seen movies. In comparison, our systems based on either state-of-the-art large language models (GPT-4) or meta-learning algorithms lags >20% behind, highlighting a notable limitation in existing approaches' ToM capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_04684 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind Yu, Mo Wang, Qiujing Zhang, Shunchi Sang, Yisi Pu, Kangsheng Wei, Zekai Wang, Han Xu, Liyan Li, Jing Yu, Yue Zhou, Jie Computation and Language Artificial Intelligence When reading a story, humans can quickly understand new fictional characters with a few observations, mainly by drawing analogies to fictional and real people they already know. This reflects the few-shot and meta-learning essence of humans' inference of characters' mental states, i.e., theory-of-mind (ToM), which is largely ignored in existing research. We fill this gap with a novel NLP dataset, ToM-in-AMC, the first assessment of machines' meta-learning of ToM in a realistic narrative understanding scenario. Our dataset consists of ~1,000 parsed movie scripts, each corresponding to a few-shot character understanding task that requires models to mimic humans' ability of fast digesting characters with a few starting scenes in a new movie. We propose a novel ToM prompting approach designed to explicitly assess the influence of multiple ToM dimensions. It surpasses existing baseline models, underscoring the significance of modeling multiple ToM dimensions for our task. Our extensive human study verifies that humans are capable of solving our problem by inferring characters' mental states based on their previously seen movies. In comparison, our systems based on either state-of-the-art large language models (GPT-4) or meta-learning algorithms lags >20% behind, highlighting a notable limitation in existing approaches' ToM capabilities. |
| title | Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2211.04684 |