Co-Trained Retriever-Generator Framework for Question Generation in Earnings Calls
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_ | 1866909327843917824 |
|---|---|
| author | Juan, Yining Chen, Chung-Chi Huang, Hen-Hsen Chen, Hsin-Hsi |
| author_facet | Juan, Yining Chen, Chung-Chi Huang, Hen-Hsen Chen, Hsin-Hsi |
| contents | In diverse professional environments, ranging from academic conferences to corporate earnings calls, the ability to anticipate audience questions stands paramount. Traditional methods, which rely on manual assessment of an audience's background, interests, and subject knowledge, often fall short - particularly when facing large or heterogeneous groups, leading to imprecision and inefficiency. While NLP has made strides in text-based question generation, its primary focus remains on academic settings, leaving the intricate challenges of professional domains, especially earnings call conferences, underserved. Addressing this gap, our paper pioneers the multi-question generation (MQG) task specifically designed for earnings call contexts. Our methodology involves an exhaustive collection of earnings call transcripts and a novel annotation technique to classify potential questions. Furthermore, we introduce a retriever-enhanced strategy to extract relevant information. With a core aim of generating a spectrum of potential questions that analysts might pose, we derive these directly from earnings call content. Empirical evaluations underscore our approach's edge, revealing notable excellence in the accuracy, consistency, and perplexity of the questions generated. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18677 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Co-Trained Retriever-Generator Framework for Question Generation in Earnings Calls Juan, Yining Chen, Chung-Chi Huang, Hen-Hsen Chen, Hsin-Hsi Computation and Language In diverse professional environments, ranging from academic conferences to corporate earnings calls, the ability to anticipate audience questions stands paramount. Traditional methods, which rely on manual assessment of an audience's background, interests, and subject knowledge, often fall short - particularly when facing large or heterogeneous groups, leading to imprecision and inefficiency. While NLP has made strides in text-based question generation, its primary focus remains on academic settings, leaving the intricate challenges of professional domains, especially earnings call conferences, underserved. Addressing this gap, our paper pioneers the multi-question generation (MQG) task specifically designed for earnings call contexts. Our methodology involves an exhaustive collection of earnings call transcripts and a novel annotation technique to classify potential questions. Furthermore, we introduce a retriever-enhanced strategy to extract relevant information. With a core aim of generating a spectrum of potential questions that analysts might pose, we derive these directly from earnings call content. Empirical evaluations underscore our approach's edge, revealing notable excellence in the accuracy, consistency, and perplexity of the questions generated. |
| title | Co-Trained Retriever-Generator Framework for Question Generation in Earnings Calls |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.18677 |