Supported by |
|
|
|
Additional cooperation from |
|
|
Seventh International Workshop on Symbolic-Neural Learning (SNL2023)
June 28-29, 2023
Venue: RIKEN, AIP, Tokyo, Japan
SNL2023 will be held at RIKEN, AIP, Tokyo, Japan.
Workshop on Symbolic-Neural Learning (SNL) offers opportunities for researchers to discuss advancement on neural networks that relate to symbols in a broad sense. The workshop covers a wide range of research topics associated with various data types, including language, knowledge graph, database, logical operation, semantic representations, etc. Symbolic-neural learning has an innovative feature of allowing interactions in a unified representation space from different input modalities, such as speech, vision, language, or sensors observing physical phenomena.
Topics of interests include, but are not limited to, neural networks on the following areas:
- Deep learning theory, method, or application associated with symbols
- Multimodal training (e.g., speech, vision, and natural language) and grounding
- Question answering
- Machine translation
- Dialogue systems
- Language as a mechanism to structure and reason about visual perception
- Image captioning
- image generation from text
- Visual question answering
- Multimodal information processing in robotics
- Reading comprehension
- Textual entailment
Deep learning models in these areas can share various architectural modules or techniques. These may include word and phrase embeddings, attention mechanism, recurrent structures (LSTMs and GRUs), memory units, diffusion/denoising networks, implicit representations, and others. Certain linguistic and semantic resources may also be relevant across these applications. For example, dictionaries, thesauri, WordNet, FrameNet, FreeBase, DBPedia, parsers, named entity recognizers, coreference systems, knowledge graphs and encyclopedias.
The workshop consists of keynote talks, invited talks, and poster session(s).
Organizing Committee:
Satoshi Sekine (Chair) |
RIKEN Center for AIP, Tokyo, Japan |
David McAllester |
Toyota Technological Institute at Chicago, Chicago, USA |
Tomoko Matsui |
The Institute of Statistical Mathematics, Tokyo, Japan |
Yutaka Sasaki |
Toyota Technological Institute, Nagoya, Japan |
Koichi Shinoda |
Tokyo Institute of Technology, Tokyo, Japan |
Jun'ichi Tsujii |
AIST AI Research Center, Tokyo, Japan and
the University of Manchester, Manchester, UK |
Yasushi Yagi |
Osaka University, Osaka, Japan |
Program Committee:
Daichi Mochihashi (Chair) |
The Institute of Statistical Mathematics, Tokyo, Japan |
Ikuro Sato (Chair) |
Tokyo Institute of Technology, Tokyo, Japan and
Denso IT Laboratory, Tokyo, Japan |
Yukiyasu Domae |
iCPS center, AIST Tokyo, Japan |
Asako Kanezaki |
Tokyo Institute of Technology, Tokyo, Japan |
Shuhei Kurita |
RIKEN Center for AIP, Japan |
Masanori Suganuma |
Tohoku University, Sendai, Japan |
Makoto Miwa |
Toyota Technological Institute, Nagoya, Japan |
Fumio Okura |
Osaka University, Osaka, Japan |
Koichiro Yoshino |
RIKEN, Guardian Robot Project, Japan |
Local Arrangements Committee
Past Workshops:
|