Describe me an Aucklet: Generating Grounded Perceptual Category Descriptions
Centre for Linguistic Theory and Studies in Probability (CLASP)（语言理论与概率研究中心）；Department of Philosophy, Linguistics, and Theory of Science (FLoV)（哲学、语言学与理论科学系）；University of Gothenburg（哥德堡大学）
Bill Noble, Nikolai Ilinykh
备注：
To appear in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP, Main)
Human speakers can generate descriptions of perceptual concepts, abstracted from the instance-level. Moreover, such descriptions can be used by other speakers to learn provisional representations of those concepts. Learning and using abstract perceptual concepts is under-investigated in the language-and-vision field. The problem is also highly relevant to the field of representation learning in multi-modal NLP. In this paper, we introduce a framework for testing category-level perceptual grounding in multi-modal language models. In particular, we train separate neural networks to generate and interpret descriptions of visual categories. We measure the communicative success of the two models with the zero-shot classification performance of the interpretation model, which we argue is an indicator of perceptual grounding. Using this framework, we compare the performance of prototype- and exemplar-based representations. Finally, we show that communicative success exposes performance issues in the generation model, not captured by traditional intrinsic NLG evaluation metrics, and argue that these issues stem from a failure to properly ground language in vision at the category level.
Distributional word representation methods exploit word co-occurrences to build compact vector encodings of words. While these representations enjoy widespread use in modern natural language processing, it is unclear whether they accurately encode all necessary facets of conceptual meaning. In this paper, we evaluate how well these representations can predict perceptual and conceptual features of concrete concepts, drawing on two semantic norm datasets sourced from human participants. We find that several standard word representations fail to encode many salient perceptual features of concepts…
Language grounding aims at linking the symbolic representation of language (e.g., words) into the rich perceptual knowledge of the outside world. The general approach is to embed both textual and visual information into a common space -the grounded space-confined by an explicit relationship between both modalities. We argue that this approach sacrifices the abstract knowledge obtained from linguistic co-occurrence statistics in the process of acquiring perceptual information. The focus of this paper is to solve this issue by implicitly grounding the word embeddings. Rather than learning two ma…
University of Chicago（芝加哥大学）；Psiphon Inc, Toronto（Psiphon公司（多伦多））；Stanford University（斯坦福大学）；University of California, Berkeley（加州大学伯克利分校）；Haas Business School（哈斯商学院）；Columbia University（哥伦比亚大学）；Sony CSL Paris（索尼CSL巴黎）
Popular approaches to natural language processing create word embeddings based on textual co-occurrence patterns, but often ignore embodied, sensory aspects of language. Here, we introduce the Python package comp-syn, which provides grounded word embeddings based on the perceptually uniform color distributions of Google Image search results. We demonstrate that comp-syn significantly enriches models of distributional semantics. In particular, we show that (1) comp-syn predicts human judgments of word concreteness with greater accuracy and in a more interpretable fashion than word2vec using low…
Heriot-Watt University（赫瑞-瓦特大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Carnegie Mellon University（卡内基梅隆大学）
In visual guessing games, a Guesser has to identify a target object in a scene by asking questions to an Oracle. An effective strategy for the players is to learn conceptual representations of objects that are both discriminative and expressive enough to ask questions and guess correctly. However, as shown by Suglia et al. (2020), existing models fail to learn truly multi-modal representations, relying instead on gold category labels for objects in the scene both at training and inference time. This provides an unnatural performance advantage when categories at inference time match those at tr…
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；University of Pennsylvania（宾夕法尼亚大学）
We introduce and implement a cognitively plausible model for learning from generic language, statements that express generalizations about members of a category and are an important aspect of concept development in language acquisition (Carlson & Pelletier, 1995; Gelman, 2009). We extend a computational framework designed to model grounded language acquisition by introducing the concept network. This new layer of abstraction enables the system to encode knowledge learned from generic statements and represent the associations between concepts learned by the system. Through three tasks that util…
University of Copenhagen（哥本哈根大学）；Uppsala University（乌普萨拉大学）；University of Trento（特伦托大学）；Brown University（布朗大学）
Pretrained language models have been shown to encode relational information, such as the relations between entities or concepts in knowledge-bases -- (Paris, Capital, France). However, simple relations of this type can often be recovered heuristically and the extent to which models implicitly reflect topological structure that is grounded in world, such as perceptual structure, is unknown. To explore this question, we conduct a thorough case study on color. Namely, we employ a dataset of monolexemic color terms and color chips represented in CIELAB, a color space with a perceptually meaningful…
Sorbonne Universités, UPMC Univ Paris 06, UMR 7606, CNRS, LIP6（索邦大学，巴黎第六大学，UMR 7606，法国国家科学研究中心，LIP6实验室）
Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to integrate perceptual and visual features. Most of these works consider the visual appearance of objects to enhance word representations but they ignore the visual environment and context in which objects appear. We propose to unify text-based techniques with vision-based techniques by simultaneously leveraging textual and visual context to learn multimodal word embe…
University of Washington（华盛顿大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Tufts University（塔夫茨大学）
Natural language understanding for robotics can require substantial domain- and platform-specific engineering. For example, for mobile robots to pick-and-place objects in an environment to satisfy human commands, we can specify the language humans use to issue such commands, and connect concept words like red can to physical object properties. One way to alleviate this engineering for a new domain is to enable robots in human environments to adapt dynamically---continually learning new language constructions and perceptual concepts. In this work, we present an end-to-end pipeline for translati…
Heriot-Watt University（赫瑞-瓦特大学）；University of Copenhagen（哥本哈根大学）；University of Edinburgh（爱丁堡大学）
Approaches to Grounded Language Learning typically focus on a single task-based final performance measure that may not depend on desirable properties of the learned hidden representations, such as their ability to predict salient attributes or to generalise to unseen situations. To remedy this, we present GROLLA, an evaluation framework for Grounded Language Learning with Attributes with three sub-tasks: 1) Goal-oriented evaluation; 2) Object attribute prediction evaluation; and 3) Zero-shot evaluation. We also propose a new dataset CompGuessWhat?! as an instance of this framework for evaluati…
We argue that an explainable artificial intelligence must possess a rationale for its decisions, be able to infer the purpose of observed behaviour, and be able to explain its decisions in the context of what its audience understands and intends. To address these issues we present four novel contributions. Firstly, we define an arbitrary task in terms of perceptual states, and discuss two extremes of a domain of possible solutions. Secondly, we define the intensional solution. Optimal by some definitions of intelligence, it describes the purpose of a task. An agent possessed of it has a ration…
We are increasingly surrounded by artificially intelligent technology that takes decisions and executes actions on our behalf. This creates a pressing need for general means to communicate with, instruct and guide artificial agents, with human language the most compelling means for such communication. To achieve this in a scalable fashion, agents must be able to relate language to the world and to actions; that is, their understanding of language must be grounded and embodied. However, learning grounded language is a notoriously challenging problem in artificial intelligence research. Here we …
Many task domains require robots to interpret and act upon natural language commands which are given by people and which refer to the robot's physical surroundings. Such interpretation is known variously as the symbol grounding problem, grounded semantics and grounded language acquisition. This problem is challenging because people employ diverse vocabulary and grammar, and because robots have substantial uncertainty about the nature and contents of their surroundings, making it difficult to associate the constitutive language elements (principally noun phrases and spatial relations) of the co…
University of Rochester（罗切斯特大学）；Toyota Technological Institute at Chicago（芝加哥丰田技术学院）
The speed and accuracy with which robots are able to interpret natural language is fundamental to realizing effective human-robot interaction. A great deal of attention has been paid to developing models and approximate inference algorithms that improve the efficiency of language understanding. However, existing methods still attempt to reason over a representation of the environment that is flat and unnecessarily detailed, which limits scalability. An open problem is then to develop methods capable of producing the most compact environment model sufficient for accurate and efficient natural l…
