Other formats:
BibTeX
LaTeX
RIS
@inproceedings{746172, author = {Němčík, Václav}, address = {Brno}, booktitle = {RASLAN 2007}, edition = {1}, keywords = {anaphora resolution; linguistic resources; verb valency; semantic plausibility; WordNet; Czech}, howpublished = {tištěná verze "print"}, language = {eng}, location = {Brno}, isbn = {978-80-210-4471-5}, pages = {57-62}, publisher = {Masarykova Univerzita}, title = {Enhancing Anaphora Resolution for Czech}, url = {https://nlp.fi.muni.cz/raslan/2007/papers/4.pdf}, year = {2007} }
TY - JOUR ID - 746172 AU - Němčík, Václav PY - 2007 TI - Enhancing Anaphora Resolution for Czech PB - Masarykova Univerzita CY - Brno SN - 9788021044715 KW - anaphora resolution KW - linguistic resources KW - verb valency KW - semantic plausibility KW - WordNet KW - Czech UR - https://nlp.fi.muni.cz/raslan/2007/papers/4.pdf N2 - Resolution of anaphoric reference is one of the most important challenges in natural language processing (NLP). Functionality of most NLP systems crucially relies on an accurate mechanism for determining which expressions in the input refer to the same entity in the real world. The immense complexity of this issue has led the research community to adopt predominantly knowledge-poor methods, despite the fact that these are known to be incapable of solving this task reliably. This paper suggests several ways of extending such methods by further resources and mechanisms in order to arrive at a more adequate anaphora resolution procedure. First, the paper sketches how to exploit information about verb valencies or co-occurrence statistics to account for semantic plausibility of individual antecedent candidates. Further, several ways of adapting ML-based AR methods are suggested, so that they account for the structure of the AR task more closely. ER -
NĚMČÍK, Václav. Enhancing Anaphora Resolution for Czech. In \textit{RASLAN 2007}. 1st ed. Brno: Masarykova Univerzita, 2007, p.~57-62. ISBN~978-80-210-4471-5.
|