A Danish FrameNet Lexicon and an Annotated Corpus Used for Training and Evaluating a Semantic Frame Classifier

被引：0

作者：

Pedersen, Bolette S. ^{[1
]}

Nimb, Sanni ^{[2
]}

Sogaard, Anders ^{[3
]}

Hartmann, Mareike ^{[3
]}

Olsen, Sussi ^{[1
]}

机构：

[1] Univ Copenhagen, Njalsgade 136, DK-2300 Copenhagen, Denmark

[2] Danish Soc Language & Literature, Christians Brygge 1, DK-1219 Copenhagen, Denmark

[3] Univ Copenhagen, Univ Parken 1, DK-2200 Copenhagen, Denmark

来源：

PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2018) | 2018年

关键词：

Danish FrameNet; concept dictionary; frame-annotated corpus; low-resourced languages; semantic frame classifier;

D O I：

暂无

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this paper, we present an approach to efficiently compile a Danish FrameNet based on the Danish Thesaurus, focusing in particular on cognition and communication frames. The Danish FrameNet uses the frame and role inventory of the English FrameNet. We present the corresponding corpus annotations of frames and roles and show how our corpus can be used for training and evaluating a semantic frame classifier for cognition and communication frames. We also present results of cross-language transfer of a model trained on the English FrameNet. Our approach is significantly faster than building a lexicon from scratch, and we show that it is feasible to annotate Danish with frames developed for English, and finally, that frame annotations - even if limited in size at the current stage - are useful for automatic frame classification.

引用

页码：2382 / 2386

页数：5