natural language understanding

Join Us at the CALCULUS Symposium 2024 – Advancing Natural Language Understanding

We are excited to invite you to the CALCULUS Symposium, part of the ERC Horizon 2020 Advanced Grant CALCULUS, scheduled for January 29-30, 2024, at KU Leuven, Belgium. The symposium highlights novel approaches to natural language understanding. The symposium aims to encourage discussion among researchers on implementations and challenges, and will explore topics related but not limited to brain-inspired machine learning, representation learning, reasoning, continual learning and multimodal learning.

The GEM (Generation, Evaluation, Metrics) workshop at ACL, 2021 is inviting transformation submissions to NL-Augmenter.

Hosted at EMNLP 2017, SCNLP encourages novel contributions that revisit the conventional NLP problems with a focus on incorporating the richness of spoken language, as well as contributions that promote cross-fertilization between statistical methods for automatic speech recognition (ASR) and NLP.

The DSTC shared task has now been running since 2013. This year’s challenge has been renamed to Dialog System Technology Challenge, which reflects the wider scope we aim for.

The DSTC6 challenge will include 3-4 tracks, which should reflect the interests of the community. We would like to encourage you to submit a track proposal for dialog related technologies including but not limited to:

We are happy to announce the release of the test portion of the LAMBADA dataset (LAnguage Modeling Broadened to Account for Discourse Aspects). LAMBADA aims at testing computational models of natural language on their ability to integrate information from a larger context than a single sentence or an n-gram window. Current models have a very hard time with discourse context in general, and with the LAMBADA task specifically (as shown in Paperno et al. 2016).

Call for Shared Task Participation
SemEval 2016 Task 1: Semantic Textual Similarity (STS)

Semantic Textual Similarity (STS) measures the degree of equivalence in the underlying semantics of paired snippets of text. While making such an assessment is trivial for humans, constructing algorithms and computational models that mimic human level performance represents a difficult and deep natural language understanding (NLU) problem.

LiLT is inviting submissions for a special issue on Modality in Natural Language Understanding.

Our main interest is in contributions that show how modal expressions contribute to inferences about, among other things, what is actual, likely or unlikely, what an agent believes or prefers, or what the obligations in a given situation are.

We envision three major parts for the volume, corresponding to the broad categories below:

• modality annotation