NAtural LOgic Meets MAchine Learning (NALOMA) is the first workshop of its kind, aiming to bridge the gap between Machine Learning and Natural Logic. It will take place from July 12-July 17, 2020, during the   Web Summer School in Logic, Language, and Information, WeSSLLI (WeSSLLI) organized by Brandeis University in Waltham, Massachusetts. WeSSLLI is the fully virtual school established as a replacement for this year’s NASSLLLI school

Recent models of Natural Language Inference (NLI) have made considerable progress in the last couple of years and have achieved performance comparable to human-level. Even though this last statement might still be an exaggeration, it is indeed true that NLI models are capable of doing more things than we thought they would some years ago. On the other hand, research on symbolic methods for NLI has not been fully abandoned. One such area that is still flourishing is research on Natural Logic. There is actually renewed interest in monotonicity inference, and connections with theorem provers and tableau systems from standard areas of logic.

Within this context, the aim of this workshop is to bring together researchers working in both Natural Logic and Machine Learning approaches to NLI, initiating a discussion with the two sets of researchers that have been largely unconnected up to now.

Call for papers

We invite submissions on topics included but not limited to:

  • reasoning systems that integrate logic-based methods with neural networks;
  • creation, evaluation, and criticism of NLI datasets;
  • training data augmentation using logic;
  • explainable models of NLI;
  • opening the “black box” of machine learning in NLI;
  • probabilistic semantics in connection with NLI;
  • downstream applications of NLI;
  • comparison and contrast between human-level and machine-level work in NLI;
  • linguistics semantics and contemporary NLI.
  • dialogue systems, QA and information retrieval systems that use (natural) logic and machine learning.

We invite two types of submission:

  • Archival (long or short) papers should report on complete, original and unpublished research. Accepted papers will be published in the workshop proceedings and appear in the ACL anthology.
  • Extended abstracts may report on work in progress or work that was recently published/accepted at a different venue. Extended abstracts will not be included in the workshop proceedings. Thus, the unpublished work will retain the status and can be submitted to another venue. Extended abstracts will be linked at the workshop webpage.

Both accepted papers and extended abstracts are expected to be presented at the workshop. Extended abstracts will be presented as talks or posters if selected by the program committee.

Authors must submit non-anonymized extended abstracts or papers before April 22. Both extended abstracts and papers must be formatted according to the ACL style. The extended abstracts should not contain an abstract section and may consist of up to 2 pages of content, plus unlimited references. Short and long papers may consist of up to 4 and 8 pages of content, respectively, plus unlimited references. Camera-ready versions of papers will be given one additional page of content so that reviewers’ comments can be taken into account.

Both extended abstracts and follow-up papers should be submitted via EasyChair at https://easychair.org/conferences/?conf=nlmml20 

Important dates

Submission of papers & extended abstracts: April 15 April 22
Notification: May 1
Final versions due: June 1
Workshop: July 12-17


For questions on this workshop: naloma20@easychair.org