Special Session on Negation

Besides long papers presenting novel research on the topics indicated in the Call for Papers, the workshop includes an annotation exercise focused on negation, as a follow-up of work initiated in the 2016 ExProM workshop. Our goal is twofold:

The goals of the special session are the following:

  1. to work towards a standard for annotating and processing negation, and
  2. to foster an international collaboration network.
The Special Session will be a hands-on and discussion session. We solicit position papers from researchers working on negation per se, as well as on NLP applications that need to be sensitive to this level of information, such as machine translation, textual entailment, opinion mining, biomedical information extraction, summarization and language generation.
  1. Position papers from researchers working on negation per se, as well as on NLP applications that need to be sensitive to this level of information, such as machine translation, textual entailment, opinion mining, biomedical information extraction, summarization or language generation. Ideally, these short papers should be written from the perspective of a specific NLP application. As for the content, they should describe the negation phenomena that hinder the application performance, with examples that can be used in a discussion session aimed at finding solutions.
  2. Position papers where an annotation task related to negation is defined. The paper should describe an (original) annotation task and motivate why it is useful. Ideally, authors should report on a pilot annotation experiment where the task has been tested. The pilot experiment can be done on a few samples of text. Crowd-source annotation tasks are encouraged.

The papers will not be presented in a traditional session, but their content will be discussed. In order to guarantee a productive working session, participants will be provided one month before the workshop with all papers accepted for the Special Session, as well as the annotation samples reported in these papers and a list of discussion items. The organisers will lead a discussion based on this content.

For the annotation task, participants can use their own datasets or the samples of text provided by the organisers. Samples from different genres and domains will be provided: news reports, opinionated texts, image captions, and biomedical abstracts. Participants who do not use the samples provided by the organisers will be asked to release the annotation sample so that other participants can prepare for the discussion session.

As a result of the Special Session, the organisers will invite interested participants to participate in a collaboration network enabling further development of the concepts and conclusions resulting from the discussion. Some annotation tasks that can be addressed are the following:

  • Focus of negation
  • Implicit positive meanings of negated statements
  • Negation in modelling perspectives
  • Categories of negated statements that are meaningful for NLP applications
  • Affixal negation
  • Indirect negation
  • Lexical negation
  • Quantifiers and negation
  • Paraphrasing negated propositions

Corpora

The organization is releasing a sample of negations from OntoNotes, FactBank and Flickr to facilitate discussion. To obtain the corpora, please follow these steps:
  1. If you don't have an LDC account, create one for free.
  2. Fill this form (TBA) and follow the instructions to send it to the LDC.
  3. The LDC will send the corpora to participants directly.

Participants are also welcome to use their own corpora for the special session on negation.


Questions? Contact the organizers.