SemEval-2017 Task

A SemEval-2017 Task is a SemEval task associated with the SemEval-2017 workshop.

• Context:
  • It is divided in 12 NLP benchmark tasks including:
    • SemEval-2017 Semantic Textual Similarity Benchmark Task,
    • SemEval-2017 Question Answering Benchmark Task,
    • SemEval-2017 Sentiment Analysis Benchmark Task,
    • SemEval-2017 Parsing Semantic Text Benchmark Task.
• Example(s):
  • SemEval-2017 Task 1,
  • SemEval-2017 Task 2,
  • …
  • SemEval-2017 Task-10 ScienceIE.
  • SemEval-2017 Task-11.
  • SemEval-2017 Task-12.
  • …
• Counter-Example(s):
  • a SemEval-2018 Task.
  • a SemEval-2016 Task.
• See: Multilingual All-Words Sense Disambiguation and Entity Linking, Semantic Similarity Task.

---

---

References

2017

• (Bethard et al., 2017) ⇒ Steven Bethard, Marine Carpuat, Marianna Apidianaki, Saif M. Mohammad, Daniel M. Cer, and David Jurgens. (2017). “Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval ACL 2017)".
  • QUOTE: SemEval-2017 was co-located with the 55th annual meeting of the Association for Computational Linguistics (ACL’2017) in Vancouver, Canada. It included the following 12 shared tasks organized in three tracks:
    • Semantic comparison for words and texts.
      • Task 1: Semantic Textual Similarity.
      • Task 2: Multi-lingual and Cross-lingual Semantic Word Similarity.
      • Task 3: Community Question Answering.
    • Detecting sentiment, humor, and truth
      • Task 4: Sentiment Analysis in Twitter.
      • Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News.
      • Task 6: #HashtagWars: Learning a Sense of Humor
      • Task 7: Detection and Interpretation of English Puns
      • Task 8: RumourEval: Determining rumour veracity and support for rumours
    • Parsing semantic structures.
      • Task 9: Abstract Meaning Representation Parsing and Generation.
      • Task 10: Extracting Keyphrases and Relations from Scientific Publications.
      • Task 11: End-User Development using Natural Language.
      • Task 12: Clinical TempEval

2017b

• http://alt.qcri.org/semeval2017/index.php?id=tasks
  • Semantic comparison for words and texts.
    • Task 1: Semantic Textual Similarity.
    • Task 2: Multi­lingual and Cross­-lingual Semantic Word Similarity.
    • Task 3: Community Question Answering.
  • Detecting sentiment, humor, and truth.
    • Task 4: Sentiment Analysis in Twitter.
    • Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News.
    • Task 6: #HashtagWars: Learning a Sense of Humor.
    • Task 7: Detection and Interpretation of English Puns.
    • Task 8: RumourEval: Determining rumour veracity and support for rumours.
  • Parsing semantic structures.
    • Task 9: Abstract Meaning Representation Parsing and Generation[1]
    • Task 10: Extracting Keyphrases and Relations from Scientific Publications[2]
    • Task 11: End-User Development using Natural Language[3]
    • Task 12: Clinical TempEval[4]

---