A Game-Theoretic Approach to Generating Spatial Descriptions

By Dave Golland, Percy Liang, Daniel Klein. 2010

158 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

A simple neural network module for relational reasoning (2017, background): “gh grounding language in spatial percepts has a long-standing tradition, the majority of previous research has focused on either rule-based spatial representations or hand-engineered spatial features [8, 10, 20, 21, 24, 29, 38, 39]. Although there are some attempts to learn spatial relations using s”
Generation and Comprehension of Unambiguous Object Descriptions (2015, background): “However a strategy that directly generates an expression based only on the target object (which [19] calls the reflex speaker strategy) has the drawback that it may fail to generate discriminative sentences.”
Emergence of Grounded Compositional Language in Multi-Agent Populations (2017, neutral): “Prag-matic language use has been proposed in the context of two-player reference games (Golland, Liang, and Klein 2010; Vogel et al. 2014; Andreas and Klein 2016) focusing on the task of identifying object references through a learned language.”
Cooperative Inverse Reinforcement Learning (2016, background): “Examples include ﬁnding a motion that best communicates an agent’s intention (Dragan & Srinivasa, 2013), or ﬁnding a natural language utterance that best communicates a particular grounding (Golland et al., 2010).”
Learning Language Games through Interaction (2016, methodology): “To speed up learning, we leverage computational models of pragmatics (Jäger, 2008; Golland et al., 2010; Frank and Goodman, 2012; Smith et al., 2013; Vogel et al., 2013).”
Towards a Visual Turing Challenge (2014, background): “Others [39] have modeled the pragmatic effects in the question answering task, but such approaches have never been shown to work in less constrained environments.”
A Comprehensive Survey of Deep Learning for Image Captioning (2018, methodology): “edding space. Mao et al. [92] proposed a special type of text generation method for images. This method can generate a description for an specific object or region that is called referring expression [37, 46, 68, 102, 103, 136, 141]. Using this expression it can then infer the object or region which”
Reasoning about Pragmatics with Neural Listeners and Speakers (2016, methodology): “It is trained by maximizing the conditional likelihood of captions in the training data: These base models are intended to be the minimal learned equivalents of the hand-engineered speakers and hand-written grammars employed in previous derived approaches (Golland et al., 2010).”
Asking for Help Using Inverse Semantics (2014, background): “HRI ’14 Germany Copyright 20XX ACM X-XXXXX-XX-X/XX/XX ...$15.00. a robot recover.”
A Joint Speaker-Listener-Reinforcer Model for Referring Expressions (2016, background): “Golland et al [7] proposed that an optimal speaker should act based on listener’s response.”
Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods (2019, background): “Given these tasks, different approaches are proposed for referring expression generation (Golland et al., 2010; Mitchell et al., 2013), comprehension (Kazemzadeh et al.”
Semantic Parsing for Text to 3D Scene Generation (2014, background): “…has dealt with grounding text to physical attributes and relations (Matuszek et al., 2012; Krishnamurthy and Kollar, 2013), generating text for referring to objects (FitzGerald et al., 2013) and with connecting language to spatial relationships (Golland et al., 2010; Artzi and Zettlemoyer, 2013).”
Interactive Learning from Activity Description (2021, background): “Another related line of research is work on the rational speech act (RSA) or pragmatic reasoning (Grice, 1975; Golland et al., 2010; Monroe & Potts, 2015; Goodman & Frank, 2016; Andreas & Klein, 2016; Fried et al., 2018a), which is also concerned with transferring information via language.”
The red one!: On learning to refer to things based on discriminative properties (2016, background): “We are currently working towards adding communication (thus simulating a speaker-listener scenario (Golland et al., 2010)) and natural language to the picture.”
Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding (2017, background): “Golland et al. (2010) develop a pragmatic speaker model, S ( L 0 ) , that reasons about log-linear listeners trained on human utterances containing spatial references in virtual-world environments.”
Grounding spatial relations for human-robot interaction (2013, methodology): “Following the idea of [18], we introduced jittering effects to the objects to make the classifier robust against view and perspective changes.”
Evaluating Machines by their Real-World Language Use (2020, methodology): “Our evaluation relates to pragmatics in NLP, where communication is modeled also through listeners and speakers (Golland et al., 2010; Frank and Goodman, 2012).”