Cohere: A Toolkit for Local Coherence
By Karin Sim Smith, Wilker Aziz, Lucia Specia. 2016
12 citations recorded by the source corpus.
We describe COHERE, our coherence toolkit which incorporates various complementary models for capturing and measuring different aspects of text coherence. In addition to the traditional entity grid model (Lapata, 2005) and graph-based metric (Guinaudeau and Strube, 2013), we provide an implementation of a state-of-the-art syntax-based model (Louis and Nenkova, 2012), as well as an adaptation of this model which shows significant performance improvements in our experiments. We benchmark these models using the standard setting for text coherence: original documents and versions of the document with sentences in shuffled order.
Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Lucia Specia
- Carolina Scarton
- Kashif Shah
- Daniel Beck
- Karin Sim Smith
- Varvara Logacheva
- Mohit Bansal
- Frédéric Blain
In Natural Language Processing
- Lucia Specia
- Carolina Scarton
- Daniel Beck
- Kashif Shah
- Karin Sim Smith
- David Langlois
- Varvara Logacheva
- Philipp Koehn
Citations in the corpus
- Word embeddings and discourse information for Quality Estimation (2016, methodology): “We use an Entity Graph Model (Sim Smith et al., 2016), which is based on the bipartite graph of Guin-audeau and Strube (2013) and tracks the occurrence of entities throughout the document, including between non-adjacent sentences.”