Sentence Embeddings as an intermediate target in end-to-end summarisation
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908351891243008 |
|---|---|
| author | Zembrzuski, Maciej Mahamood, Saad |
| author_facet | Zembrzuski, Maciej Mahamood, Saad |
| contents | Current neural network-based methods to the problem of document summarisation struggle when applied to datasets containing large inputs. In this paper we propose a new approach to the challenge of content-selection when dealing with end-to-end summarisation of user reviews of accommodations. We show that by combining an extractive approach with externally pre-trained sentence level embeddings in an addition to an abstractive summarisation model we can outperform existing methods when this is applied to the task of summarising a large input dataset. We also prove that predicting sentence level embedding of a summary increases the quality of an end-to-end system for loosely aligned source to target corpora, than compared to commonly predicting probability distributions of sentence selection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03481 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sentence Embeddings as an intermediate target in end-to-end summarisation Zembrzuski, Maciej Mahamood, Saad Computation and Language Current neural network-based methods to the problem of document summarisation struggle when applied to datasets containing large inputs. In this paper we propose a new approach to the challenge of content-selection when dealing with end-to-end summarisation of user reviews of accommodations. We show that by combining an extractive approach with externally pre-trained sentence level embeddings in an addition to an abstractive summarisation model we can outperform existing methods when this is applied to the task of summarising a large input dataset. We also prove that predicting sentence level embedding of a summary increases the quality of an end-to-end system for loosely aligned source to target corpora, than compared to commonly predicting probability distributions of sentence selection. |
| title | Sentence Embeddings as an intermediate target in end-to-end summarisation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.03481 |