Understanding the semantic structure of unstructured data -- text, dialogs, images -- is a critical challenge given their central role in many applications, including question answering, dialog systems, information retrieval...  In recent years, there has been much interest in designing models and algorithms to automatically extract and manipulate these semantic representations from raw data.

Semantics is a diverse field. It encompasses extracting structured data from text and dialog data (knowledge base extraction, logical form extraction, information extraction), linguistic approaches to extract and compose representation of meaning, inference and reasoning over meaning representation based on logic or algebra. It also includes approaches that aims at grounding language by learning relations between language and visual observations, linking language to the physical world (e.g. through robotics, machine commands). Despite spanning different disciplines with seemingly incompatible views, these approaches to semantics all aims at enabling computers to evolve and interact with humans and the physical world in general.

The goal of the workshop is dual. First, we aim at gathering experts from the different fields of semantics to favor cross-fertilization, discussions and constructive debates. Second, we encourage invited speakers and participants to expose their future research directions, take position and highlight the key challenges the community need to face. The workshop devotes most of the program to panel sessions about future directions.

We welcome contributions (up to 4 pages abstract) in the following areas and related topics:

- Word similarities and sense disambiguation

- Information and relation extraction

- Lexical and compositional semantics

- Learning semantic frames and semantic role labelling

- Grounded language learning

- Semantic representation for dialog understanding

- Visual scene understanding

- Multi-modal semantic representation and reasoning

Submit your abstract through CMT:

https://cmt.research.microsoft.com/LS2014/

Morning

---

Machine Reasoning & Artificial Intelligence

• 08:30a Pedro Domingos, University of Washington, Symmetry-Based Semantic Parsing
• 08:50a Tomas Mikolov, Facebook, Challenges in Development of Machine Intelligence
• 09:10a Luke Zettlemoyer, University of Washington, Semantic Parsing for Knowledge Extraction
• 09:30a Panel Discussion

Contributed Posters

• 10:00a Contributed Posters, Coffee Break

Natural Language Processing & Semantics from Text Corpora 

• 10:30a Stephen Clark, University of Cambridge, Composition in Distributed Semantics
• 10:50a Sebastian Riedel, University College London, Embedding Probabilistic Logic for Machine Reading
• 11:10a Ivan Titov, University of Amsterdam, Inducing Semantics Frames and Roles from Text in a Reconstruction-Error Minimization Framework
• 11:30a Panel Discussion

Afternoon

---

Personal Assistants, Dialog Systems, and Question Answering

• 03:00p Susan Hendrich, Microsoft Cortana
• 03:20p Ashutosh Saxena, Cornell, Tell Me Dave: Context-Sensitive Grounding of Natural Language into Robotic Tasks
• 03:40p Jason Weston, Facebook, Memory Networks
• 04:00p Panel Discussion

Contributed Posters

• 04:30p Contributed Posters, Coffee Break

Reasoning from Visual Scenes

• 05:00p Alyosha Efros, UC Berkeley, Towards The Visual Memex
• 05:20p Jeffrey Siskind, Purdue University, Learning to Ground Sentences in Video
• 05:40p Larry Zitnick, Microsoft Research, Forget Reality: Learning from Visual Abstraction
• 06:00p Panel Discussion

    Morning Session (10:00p-10:30p)

    Afternoon Session (4:10p-5:00p)

This workshop directly follows the previous workshop:

NIPS 2011 Workshop on Learning Semantics (A. Bordes and L. Bottou were already organizers of this event).

It is related to the workshops on  automated knowledge base construction:

NIPS 2013: Knowledge Extraction from Text
NIPS 2009: Grammar Induction, Representation of Language and Language Learning
NIPS 2008: Speech and Language: Learning-based Methods and Systems
NIPS 2007: The grammar of vision: probabilistic grammar-based models for visual scene understanding and object categorization