Article Structure
Abstract
This paper proposes an approach to reference resolution in situated dialogues by exploiting extra-linguistic information.
Introduction
The task of identifying reference relations including anaphora and coreferences within texts has received a great deal of attention in natural language processing, from both theoretical and empirical perspectives.
REX-J corpus: a corpus of collaborative work dialogue
For investigating dialogue from the multi-modal perspective, researchers have developed data sets including extra-linguistic information, bridging objects in the world and their referring expressions.
Reference Resolution using Extra-linguistic Information
Before explaining the treatment of extra-linguistic information, let us first describe the task definition, taking the REX-J corpus as target data.
Empirical Evaluation
In order to investigate the effect of the extra-linguistic information introduced in this paper, we conduct an empirical evaluation using the REX-J corpus.
Related Work
There have been increasing concerns about reference resolution in dialogue.
Conclusion
This paper presented the task of reference resolution bridging pieces in the real world and their referents in dialogue.
Topics
coreference
- The task of identifying reference relations including anaphora and coreferences within texts has received a great deal of attention in natural language processing, from both theoretical and empirical perspectives.Page 1, “Introduction”
- In these data sets, coreference relations are defined as a limited version of a typical coreference; this generally means that only the relations where expressions refer to the same named entities are addressed, because it makes the coreference resolution task more information extraction-oriented.Page 1, “Introduction”
- In other words, the coreference task as defined by MUC and ACE is geared toward only identifying coreference relations anchored to an entity within the text.Page 1, “Introduction”
- These features have been examined by approaches to anaphora or coreference resolution (Soon et al., 2001; Ng and Cardie, 2002, etc.)Page 4, “Reference Resolution using Extra-linguistic Information”
See all papers in Proc. ACL 2010 that mention coreference.
See all papers in Proc. ACL that mention coreference.
Back to top.
SVM
- Although the work by Denis and Baldridge (2008) uses Maximum Entropy to create their ranking-based model, we adopt the Ranking SVM algorithm (J oachims, 2002), which learns a weight vector to rank candidates for a given partial ranking of each referent.Page 3, “Reference Resolution using Extra-linguistic Information”
- SVM ) should be separately created with regards to distinct features.Page 5, “Empirical Evaluation”
- We utilised SVanl‘;8 as an implementation of the Ranking SVM algorithm, in which the parameter c was set as 1.0 and the remaining parameters were set to their defaults.Page 6, “Empirical Evaluation”
See all papers in Proc. ACL 2010 that mention SVM.
See all papers in Proc. ACL that mention SVM.
Back to top.
