SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Cross-lingual Focused Evaluation

Daniel Cer (1) , Mona Diab (2) , Eneko E. Agirre (3) , Iñigo Lopez-Gazpio (3) , Lucia Specia (4)

1 Google Inc [Mountain View]
2 GW - The George Washington University
3 UPV / EHU - University of the Basque Country = Euskal Herriko Unibertsitatea
4 University of Sheffield [Sheffield]

Semantic Textual Similarity (STS) measures the meaning similarity of sentences. Applications include machine translation (MT), summarization, generation, question answering (QA), short answer grading, semantic search, dialog and conversational systems. The STS shared task is a venue for assessing the current state-of-the-art. The 2017 task focuses on multilingual and cross-lingual pairs with one sub-track exploring MT quality estimation (MTQE) data. The task obtained strong participation from 31 teams, with 17 participating in all language tracks. We summarize performance and review a selection of well performing methods. Analysis highlights common errors, providing insight into the limitations of existing models. To support ongoing work on semantic representations, the STS Benchmark is introduced as a new shared training and evaluation set carefully selected from the corpus of English STS shared task data (2012-2017).

Mots clés: Textual similarity; Semantics; Meaning computation; Dataset; Shared task; Natural Language Processing NLP; Natural Language Understanding; Machine Translation

Domaines: Informatique et langage [cs.CL]; Apprentissage [cs.LG]

Daniel Cer, Mona Diab, Eneko E. Agirre, Iñigo Lopez-Gazpio, Lucia Specia. SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Cross-lingual Focused Evaluation. The 11th International Workshop on Semantic Evaluation (SemEval-2017), Steven Bethard; Marine Carpuat; Marianna Apidianaki; Saif M. Mohammad; Daniel Cer; David Jurgens, Aug 2017, Vancouver, Canada. pp.1 - 14. ⟨hal-01560674⟩