Abstract
A quantitative representation of discourse structure can be computed by measuring lexical cohesion relations among adjacent blocks of text. These representations have been proposed to deal with sub-topic text segmentation. In a parallel corpus, similar representations can be derived for versions of a text in various languages. These can be used for parallel segmentation and as an alternative measure of text-translation similarity.- Anthology ID:
- 1994.vlc-1.12
- Volume:
- Second Workshop on Very Large Corpora
- Month:
- Year:
- 1994
- Address:
- Venue:
- VLC
- SIG:
- Publisher:
- Note:
- Pages:
- 143–160
- Language:
- URL:
- https://aclanthology.org/1994.vlc-1.12
- DOI:
- Cite (ACL):
- Pim van der Eijk. 1994. Comparative Discourse Analysis of Parallel Texts. In Second Workshop on Very Large Corpora, pages 143–160.
- Cite (Informal):
- Comparative Discourse Analysis of Parallel Texts (van der Eijk, VLC 1994)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/1994.vlc-1.12.pdf