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).
%0 Conference Paper
%1 cer-etal-2017-semeval
%A Cer, Daniel
%A Diab, Mona
%A Agirre, Eneko
%A Lopez-Gazpio, Iñigo
%A Specia, Lucia
%B Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
%C Vancouver, Canada
%D 2017
%I Association for Computational Linguistics
%K mapping matching measures nlp semantic
%P 1--14
%R 10.18653/v1/S17-2001
%T SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation
%U https://www.aclweb.org/anthology/S17-2001
%X 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).
@inproceedings{cer-etal-2017-semeval,
abstract = {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 \textit{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 \textit{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).},
added-at = {2019-12-14T20:59:45.000+0100},
address = {Vancouver, Canada},
author = {Cer, Daniel and Diab, Mona and Agirre, Eneko and Lopez-Gazpio, I{\~n}igo and Specia, Lucia},
biburl = {https://www.bibsonomy.org/bibtex/2e37069d3db2ce7690978deeaa93007c9/dawa},
booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation ({S}em{E}val-2017)},
doi = {10.18653/v1/S17-2001},
interhash = {c9dde1d019b77b800d6d717f3c0c9fc4},
intrahash = {e37069d3db2ce7690978deeaa93007c9},
keywords = {mapping matching measures nlp semantic},
month = aug,
pages = {1--14},
publisher = {Association for Computational Linguistics},
timestamp = {2019-12-14T20:59:45.000+0100},
title = {{S}em{E}val-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation},
url = {https://www.aclweb.org/anthology/S17-2001},
year = 2017
}