Natural Language Decompositions of Implicit Content Enable Better Text Representations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916626297782272 |
|---|---|
| author | Hoyle, Alexander Sarkar, Rupak Goel, Pranav Resnik, Philip |
| author_facet | Hoyle, Alexander Sarkar, Rupak Goel, Pranav Resnik, Philip |
| contents | When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into account. We use a large language model to produce sets of propositions that are inferentially related to the text that has been observed, then validate the plausibility of the generated content via human judgments. Incorporating these explicit representations of implicit content proves useful in multiple problem settings that involve the human interpretation of utterances: assessing the similarity of arguments, making sense of a body of opinion data, and modeling legislative behavior. Our results suggest that modeling the meanings behind observed language, rather than the literal text alone, is a valuable direction for NLP and particularly its applications to social science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_14583 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Natural Language Decompositions of Implicit Content Enable Better Text Representations Hoyle, Alexander Sarkar, Rupak Goel, Pranav Resnik, Philip Computation and Language When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into account. We use a large language model to produce sets of propositions that are inferentially related to the text that has been observed, then validate the plausibility of the generated content via human judgments. Incorporating these explicit representations of implicit content proves useful in multiple problem settings that involve the human interpretation of utterances: assessing the similarity of arguments, making sense of a body of opinion data, and modeling legislative behavior. Our results suggest that modeling the meanings behind observed language, rather than the literal text alone, is a valuable direction for NLP and particularly its applications to social science. |
| title | Natural Language Decompositions of Implicit Content Enable Better Text Representations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2305.14583 |