@inproceedings{marton-toutanova-2016-e,
    title = "{E}-{TIPSY}: Search Query Corpus Annotated with Entities, Term Importance, {POS} Tags, and Syntactic Parses",
    author = "Marton, Yuval  and
      Toutanova, Kristina",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Grobelnik, Marko  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, Helene  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
    month = may,
    year = "2016",
    address = "Portoro{\v{z}}, Slovenia",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/landing_page/L16-1106/",
    pages = "672--676",
    abstract = "We present E-TIPSY, a search query corpus annotated with named Entities, Term Importance, POS tags, and SYntactic parses. This corpus contains crowdsourced (gold) annotations of the three most important terms in each query. In addition, it contains automatically produced annotations of named entities, part-of-speech tags, and syntactic parses for the same queries. This corpus comes in two formats: (1) Sober Subset: annotations that two or more crowd workers agreed upon, and (2) Full Glass: all annotations. We analyze the strikingly low correlation between term importance and syntactic headedness, which invites research into effective ways of combining these different signals. Our corpus can serve as a benchmark for term importance methods aimed at improving search engine quality and as an initial step toward developing a dataset of gold linguistic analysis of web search queries. In addition, it can be used as a basis for linguistic inquiries into the kind of expressions used in search."
}