Explicating the Implicit: Argument Detection Beyond Sentence Boundaries
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914905708298240 |
|---|---|
| author | Roit, Paul Slobodkin, Aviv Hirsch, Eran Cattan, Arie Klein, Ayal Pyatkin, Valentina Dagan, Ido |
| author_facet | Roit, Paul Slobodkin, Aviv Hirsch, Eran Cattan, Arie Klein, Ayal Pyatkin, Valentina Dagan, Ido |
| contents | Detecting semantic arguments of a predicate word has been conventionally modeled as a sentence-level task. The typical reader, however, perfectly interprets predicate-argument relations in a much wider context than just the sentence where the predicate was evoked. In this work, we reformulate the problem of argument detection through textual entailment to capture semantic relations across sentence boundaries. We propose a method that tests whether some semantic relation can be inferred from a full passage by first encoding it into a simple and standalone proposition and then testing for entailment against the passage. Our method does not require direct supervision, which is generally absent due to dataset scarcity, but instead builds on existing NLI and sentence-level SRL resources. Such a method can potentially explicate pragmatically understood relations into a set of explicit sentences. We demonstrate it on a recent document-level benchmark, outperforming some supervised methods and contemporary language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04246 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explicating the Implicit: Argument Detection Beyond Sentence Boundaries Roit, Paul Slobodkin, Aviv Hirsch, Eran Cattan, Arie Klein, Ayal Pyatkin, Valentina Dagan, Ido Computation and Language Detecting semantic arguments of a predicate word has been conventionally modeled as a sentence-level task. The typical reader, however, perfectly interprets predicate-argument relations in a much wider context than just the sentence where the predicate was evoked. In this work, we reformulate the problem of argument detection through textual entailment to capture semantic relations across sentence boundaries. We propose a method that tests whether some semantic relation can be inferred from a full passage by first encoding it into a simple and standalone proposition and then testing for entailment against the passage. Our method does not require direct supervision, which is generally absent due to dataset scarcity, but instead builds on existing NLI and sentence-level SRL resources. Such a method can potentially explicate pragmatically understood relations into a set of explicit sentences. We demonstrate it on a recent document-level benchmark, outperforming some supervised methods and contemporary language models. |
| title | Explicating the Implicit: Argument Detection Beyond Sentence Boundaries |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.04246 |