Large Language Models (LLMs) handle physical commonsense information inadequately. As a result of being trained in a disembodied setting, LLMs often fail to predict an action’s outcome in a given environment. However, predicting the effects of an action before it is executed is crucial in planning, where coherent sequences of actions are often needed to achieve a goal. Therefore, we introduce the multi-modal task of predicting the outcomes of actions solely from realistic sensory inputs (images and text). Next, we extend an LLM to model latent representations of objects to better predict action outcomes in an environment. We show that multi-modal models can capture physical commonsense when augmented with visual information. Finally, we evaluate our model’s performance on novel actions and objects and find that combining modalities help models to generalize and learn physical commonsense reasoning better.

Interactive Task Learning (ITL) concerns learning about unforeseen domain concepts via natural interactions with human users. The learner faces a number of significant constraints: learning should be online, incremental and few-shot, as it is expected to perform tangible belief updates right after novel words denoting unforeseen concepts are introduced. In this work, we explore a challenging symbol grounding task—discriminating among object classes that look very similar—within the constraints imposed by ITL. We demonstrate empirically that more data-efficient grounding results from exploiting the truth-conditions of the teacher’s generic statements (e.g., “Xs have attribute Z.”) and their implicatures in context (e.g., as an answer to “How are Xs and Ys different?”, one infers Y lacks attribute Z).

Simulation is an invaluable tool for developing and evaluating controllers for self-driving cars. Current simulation frameworks are driven by highly-specialist domain specific languages, and so a natural language interface would greatly enhance usability. But there is often a gap, consisting of tacit assumptions the user is making, between a concise English utterance and the executable code that captures the user’s intent. In this paper we describe a system that addresses this issue by supporting an extended multimodal interaction: the user can follow up prior instructions with refinements or revisions, in reaction to the simulations that have been generated from their utterances so far. We use Large Language Models (LLMs) to map the user’s English utterances in this interaction into domain-specific code, and so we explore the extent to which LLMs capture the context sensitivity that’s necessary for computing the speaker’s intended message in discourse.

We present a procedure for learning to ground symbols from a sequence of stimuli consisting of an arbitrarily complex noun phrase (e.g. “all but one green square above both red circles.”) and its designation in the visual scene. Our distinctive approach combines: a) lazy few-shot learning to relate open-class words like green and above to their visual percepts; and b) symbolic reasoning with closed-class word categories like quantifiers and negation. We use this combination to estimate new training examples for grounding symbols that occur within a noun phrase but aren’t designated by that noun phase (e.g, red in the above example), thereby potentially gaining data efficiency. We evaluate the approach in a visual reference resolution task, in which the learner starts out unaware of concepts that are part of the domain model and how they relate to visual percepts.

This paper describes a method for learning from a teacher’s potentially unreliable corrective feedback in an interactive task learning setting. The graphical model uses discourse coherence to jointly learn symbol grounding, domain concepts and valid plans. Our experiments show that the agent learns its domain-level task in spite of the teacher’s mistakes.

In this paper we present a comparative evaluation of various negotiation strategies within an online version of the game “Settlers of Catan”. The comparison is based on human subjects playing games against artificial game-playing agents (‘bots’) which implement different negotiation dialogue strategies, using a chat dialogue interface to negotiate trades. Our results suggest that a negotiation strategy that uses persuasion, as well as a strategy that is trained from data using Deep Reinforcement Learning, both lead to an improved win rate against humans, compared to previous rule-based and supervised learning baseline dialogue negotiators.

As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability—for instance, learning to ground symbols in the physical world. Realistically, this task must cope with small datasets consisting of a particular users’ contextual assignment of meaning to terms. We present a method for processing a raw stream of cross-modal input—i.e., linguistic instructions, visual perception of a scene and a concurrent trace of 3D eye tracking fixations—to produce the segmentation of objects with a correspondent association to high-level concepts. To test our framework we present experiments in a table-top object manipulation scenario. Our results show our model learns the user’s notion of colour and shape from a small number of physical demonstrations, generalising to identifying physical referents for novel combinations of the words.

Dans cet article, nous présentons une analyse à base de contraintes de la relation forme-sens des gestes déictiques et de leur signal de parole synchrone. En nous basant sur une étude empirique de corpus multimodaux, nous définissons quels énoncés multimodaux sont bien formés, et lesquels ne pourraient jamais produire le sens voulu dans la situation communicative. Plus précisément, nous formulons une grammaire multimodale dont les règles de construction utilisent la prosodie, la syntaxe et la sémantique de la parole, la forme et le sens du signal déictique, ainsi que la performance temporelle de la parole et la deixis afin de contraindre la production d’un arbre de syntaxe combinant parole et gesture déictique ainsi que la représentation unifiée du sens pour l’action multimodale correspondant à cet arbre. La contribution de notre projet est double : nous ajoutons aux ressources existantes pour le TAL un corpus annoté de parole et de gestes, et nous créons un cadre théorique pour la grammaire au sein duquel la composition sémantique d’un énoncé découle de la synchronie entre geste et parole.