@inproceedings{JosiWartenaHeid2019, author = {Frieda Josi and Christian Wartena and Ulrich Heid}, title = {Detecting Paraphrases of Standard Clause Titles in Insurance Contracts}, series = {RELATIONS - Workshop on meaning relations between phrases and sentences (May 23, 2019, Gothenburg, Sweden)}, isbn = {978-1-950737-22-2}, doi = {10.25968/opus-1337}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:960-opus4-13375}, pages = {23 -- 33}, year = {2019}, abstract = {For the analysis of contract texts, validated model texts, such as model clauses, can be used to identify used contract clauses. This paper investigates how the similarity between titles of model clauses and headings extracted from contracts can be computed, and which similarity measure is most suitable for this. For the calculation of the similarities between title pairs we tested various variants of string similarity and token based similarity. We also compare two additional semantic similarity measures based on word embeddings using pre-trained embeddings and word embeddings trained on contract texts. The identification of the model clause title can be used as a starting point for the mapping of clauses found in contracts to verified clauses.}, language = {en} }