There will be four workshops colocated with IWCS 2021:
- ISA-17: The Seventeenth Joint ACL - ISO Workshop on Interoperable Semantic Annotation (proceedings: online, archive)
- MMSR I: Beyond Language: Multimodal Semantic Representations (proceedings: online, archive)
- NALOMA'21: Natural Logic meets Machine Learning 2021 (proceedings: online, archive)
- SemSpace 2021: Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science (proceedings: online, archive)
Note that all workshops have their own submission deadlines, style-files, organising committee, etc. Please check their websites for detailed information.
ISA-17 is the seventeenth edition of a series of joint workshops of SIGSEM and ISO. These workshops bring together researchers and users interested in the annotation of semantic information in text, speech, gestures, graphics, video, images, and multimodal communication, including the markup of events, time, space, dialogue acts, discourse relations, semantic roles, coreference, and quantification, and other aspects of meaning for which the ISO organisation pursues the establishment of annotation methods and representation schemes, in support of the creation of interoperable semantic resources. This workshop will feature two specialised tracks, focused on (1) the annotation of quantification and modification phenomena in natural language; (2) the design and representation of data structures for generating visualisations of linguistically represented objects, properties, and events.
This is the first edition of the workshop Beyond Language: Multimodal Semantic Representations. The demand for more sophisticated natural human-computer and human-robot interactions is rapidly increasing, as users become more accustomed to conversation-like interactions with their devices. This requires not only the robust recognition and generation of expressions through multiple modalities (language, gesture, vision, action), but also the encoding of situated meaning. This workshop is geared toward the exploration and modeling of the semantics of multimodal communication to generate representations for common ground between human and computer. A formal representation of multimodal semantics including (but not limited to) language, gesture, gaze, and facial expression, will aid the goal of building intelligent systems that are collaborative partners with humans and able to perform a variety of tasks. As such, this workshop provides a space for both theoretical and practical discussion of how linguistic co-modalities support, inform, and align with "meaning" found in the linguistic signal alone.
After the successful completion of NALOMA'20 (NAtural LOgic Meets MAchine Learning), NALOMA'21 seeks to continue the series and attract exciting contributions. The NALOMA workshop addresses two issues of the NLI community: the one-dimensionality of the existing approaches and the dataset weaknesses. It aims to bridge the gap between ML/DL and symbolic/logic-based approaches to NLI and contribute to current efforts to provide data which is more reliable, more representative-of-human-inference and more linguistically diverse. NALOMA seeks to raise awareness on the data-related issues to NLI and discuss appropriate solutions. It is especially suitable for researchers interested in any aspect of NLI, e.g., in hybrid solutions to NLI and reasoning and in evaluating existing corpora and proposing new ones.
Semantic Spaces at the Intersection of NLP, Physics, and Cognitive Science (SemSpace2021) is the latest edition of a series of workshops that brings together research at the intersection of NLP, Physics, and Cognitive Science. Using the common ground of vector spaces, the workshop offers researchers in these areas an appropriate forum for presenting their uniquely motivated work and ideas. The interplay between the three disciplines will foster theoretically motivated approaches to understanding how meanings of words interact with each other in sentences and discourse via grammatical types, how they are determined by input from the world, and how word and sentence meanings interact logically.