TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Noh, Tae-Gil
A1  - Padó, Sebastian
T1  - A Language Model Sensitive to Discourse Context
T2  - Proceedings of the 12th edition of the KONVENS conference
N2  - The paper proposes a meta language model that can dynamically incorporate the influence of wider discourse context. The model provides a conditional probability in forms of P (text|context), where the context can be arbitrary length of text, and is used to influence the probability distribution over documents. A preliminary evaluation using a 3-gram model as the base language model shows significant reductions in perplexity by incorporating discourse context.
KW  - Maschinelles Lernen
KW  - Statistische Methoden
KW  - Statistical Methods
KW  - Machine Learning
Y1  - 2014
U6  - https://nbn-resolving.org/urn:nbn:de:gbv:hil2-opus-2822
UN  - https://nbn-resolving.org/urn:nbn:de:gbv:hil2-opus-2822
SP  - 201
EP  - 206
ER  -