We present the Extended Paraphrase typology (EPT) and the Extended Typology Paraphrase Corpus (ETPC). The EPT typology addresses several practical limitations of existing paraphrase typologies: it is the first typology that copes with the non-paraphrase pairs in the paraphrase identification corpora and distinguishes between contextual and habitual paraphrase types. ETPC is the largest corpus to date annotated with atomic paraphrase types. It is the first corpus with detailed annotation of both the paraphrase and the non-paraphrase pairs and the first corpus annotated with paraphrase and negation. Both new resources contribute to better understanding the paraphrase phenomenon, and allow for studying the relationship between paraphrasing and negation. To the developers of Paraphrase Identification systems ETPC corpus offers better means for evaluation and error analysis. Furthermore, the EPT typology and ETPC corpus emphasize the relationship with other areas of NLP such as Semantic Similarity, Textual Entailment, Summarization and Simplification.
@InProceedings{KOVATCHEV18.661, author = {Venelin Kovatchev and Toni Marti and Maria Salamo}, title = "{ETPC - A Paraphrase Identification Corpus Annotated with Extended Paraphrase Typology and Negation}", booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {May 7-12, 2018}, address = {Miyazaki, Japan}, editor = {Nicoletta Calzolari (Conference chair) and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Koiti Hasida and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Hélène Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis and Takenobu Tokunaga}, publisher = {European Language Resources Association (ELRA)}, isbn = {979-10-95546-00-9}, language = {english} }