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 embeddings. We explore various choices for what can serve as a visual context and present an end-to-end method to integrate visual context elements in a multimodal skip-gram model. We provide experiments and extensive analysis of the obtained results.
We propose a model to learn visually grounded word embeddings (vis-w2v) to capture visual notions of semantic relatedness. While word embeddings trained using text have been extremely successful, they cannot uncover notions of semantic relatedness implicit in our visual world. For instance, although "eats" and "stares at" seem unrelated in text, they share semantics visually. When people are eating something, they also tend to stare at the food. Grounding diverse relations like "eats" and "stares at" into vision remains challenging, despite recent progress in vision. We note that the visual gr…
Word embedding is designed to represent the semantic meaning of a word with low dimensional vectors. The state-of-the-art methods of learning word embeddings (word2vec and GloVe) only use the word co-occurrence information. The learned embeddings are real number vectors, which are obscure to human. In this paper, we propose an Image-Enhanced Skip-Gram Model to learn grounded word embeddings by representing the word vectors in the same hyper-plane with image vectors. Experiments show that the image vectors and word embeddings learned by our model are highly correlated, which indicates that our …
CNRS, IRIT（法国国家科学研究中心，图卢兹计算机科学研究所）；Univ. of Toulouse（图卢兹大学）；California Institute of Technology（加州理工学院）
This paper introduces a novel approach to learn visually grounded meaning representations of words as low-dimensional node embeddings on an underlying graph hierarchy. The lower level of the hierarchy models modality-specific word representations through dedicated but communicating graphs, while the higher level puts these representations together on a single graph to learn a representation jointly from both modalities. The topology of each graph models similarity relations among words, and is estimated jointly with the graph embedding. The assumption underlying this model is that words sharin…
Delft University of Technology（代尔夫特理工大学）；Radboud University（拉德堡德大学）
We investigated word recognition in a Visually Grounded Speech model. The model has been trained on pairs of images and spoken captions to create visually grounded embeddings which can be used for speech to image retrieval and vice versa. We investigate whether such a model can be used to recognise words by embedding isolated words and using them to retrieve images of their visual referents. We investigate the time-course of word recognition using a gating paradigm and perform a statistical analysis to see whether well known word competition effects in human speech processing influence word re…
Zhejiang University（浙江大学）；University of California, Santa Cruz（加利福尼亚大学圣克鲁兹分校）；University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）
Grounded video description (GVD) encourages captioning models to attend to appropriate video regions (e.g., objects) dynamically and generate a description. Such a setting can help explain the decisions of captioning models and prevents the model from hallucinating object words in its description. However, such design mainly focuses on object word generation and thus may ignore fine-grained information and suffer from missing visual concepts. Moreover, relational words (e.g., "jump left or right") are usual spatio-temporal inference results, i.e., these words cannot be grounded on certain spat…
Georgia Tech（佐治亚理工学院）；Virgina Tech（弗吉尼亚理工大学）；Facebook AI Research（Facebook人工智能研究院）
To be able to interact better with humans, it is crucial for machines to understand sound - a primary modality of human perception. Previous works have used sound to learn embeddings for improved generic textual similarity assessment. In this work, we treat sound as a first-class citizen, studying downstream textual tasks which require aural grounding. To this end, we propose sound-word2vec - a new embedding scheme that learns specialized word embeddings grounded in sounds. For example, we learn that two seemingly (semantically) unrelated concepts, like leaves and paper are similar due to the …
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…
TTI-Chicago（芝加哥丰田技术研究院）；IBM Research AI（IBM研究院人工智能部门）
Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are simpler to train, and more efficient to decode with, than sub-word systems. However, A2W systems can have difficulties at training time when data is limited, and at decoding time when recognizing words outside the training vocabulary. To address these shortcomings, we investigate the use of recently proposed acoustic and acoustically grounded word embedding techniques in A2W systems. The idea is based on treating the final pre-softmax weight matrix of an AWE recognizer as a matrix of word embedding vectors, …
VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models
School of Data Science, Fudan University（复旦大学数据科学学院）；ByteDance（字节跳动）；School of Computer Science, Fudan University（复旦大学计算机科学学院）；Research Institute of Intelligent and Complex Systems, Fudan University（复旦大学智能与复杂系统研究院）；Shanghai Innovation Institute（上海创新研究院）
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…
The words-as-classifiers model of grounded lexical semantics learns a semantic fitness score between physical entities and the words that are used to denote those entities. In this paper, we explore how such a model can incrementally perform composition and how the model can be unified with a distributional representation. For the latter, we leverage the classifier coefficients as an embedding. For composition, we leverage the underlying mechanics of three different classifier types (i.e., logistic regression, decision trees, and multi-layer perceptrons) to arrive at a several systematic appro…
Microsoft Research（微软研究院）；University of Waterloo（滑铁卢大学）；Meta Research（Meta研究院）；Moscow Institute of Physics Technology（莫斯科物理技术学院）；Artificial Intelligence Research Institute（人工智能研究院）
Human intelligence can remarkably adapt quickly to new tasks and environments. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions. To facilitate research which can enable similar capabilities in machines, we made the following contributions (1) formalized the collaborative embodied agent using natural language task; (2) developed a tool for extensive and scalable data collection; and (3) collected the first dataset for interactive grounded language understan…
Radboud University（拉德堡德大学）；Delft University of Technology（代尔夫特理工大学）
Background: Computational models of speech recognition often assume that the set of target words is already given. This implies that these models do not learn to recognise speech from scratch without prior knowledge and explicit supervision. Visually grounded speech models learn to recognise speech without prior knowledge by exploiting statistical dependencies between spoken and visual input. While it has previously been shown that visually grounded speech models learn to recognise the presence of words in the input, we explicitly investigate such a model as a model of human speech recognition…
M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks
School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室）；Yuanpei College, Peking University（北京大学元培学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；School of Psychological and Cognitive Sciences, Peking University（北京大学心理学与认知科学学院）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）
In this paper, we investigate the manner in which interpretable sub-word speech units emerge within a convolutional neural network model trained to associate raw speech waveforms with semantically related natural image scenes. We show how diphone boundaries can be superficially extracted from the activation patterns of intermediate layers of the model, suggesting that the model may be leveraging these events for the purpose of word recognition. We present a series of experiments investigating the information encoded by these events.
Distributional semantic models capture word-level meaning that is useful in many natural language processing tasks and have even been shown to capture cognitive aspects of word meaning. The majority of these models are purely text based, even though the human sensory experience is much richer. In this paper we create visually grounded word embeddings by combining English text and images and compare them to popular text-based methods, to see if visual information allows our model to better capture cognitive aspects of word meaning. Our analysis shows that visually grounded embedding similaritie…
In this paper, we study how word-like units are represented and activated in a recurrent neural model of visually grounded speech. The model used in our experiments is trained to project an image and its spoken description in a common representation space. We show that a recurrent model trained on spoken sentences implicitly segments its input into word-like units and reliably maps them to their correct visual referents. We introduce a methodology originating from linguistics to analyse the representation learned by neural networks -- the gating paradigm -- and show that the correct representa…
Interaction Lab（交互实验室）；Heriot-Watt University（赫瑞瓦特大学）；University of Groningen（格罗宁根大学）
We motivate and describe a new freely available human-human dialogue dataset for interactive learning of visually grounded word meanings through ostensive definition by a tutor to a learner. The data has been collected using a novel, character-by-character variant of the DiET chat tool (Healey et al., 2003; Mills and Healey, submitted) with a novel task, where a Learner needs to learn invented visual attribute words (such as " burchak " for square) from a tutor. As such, the text-based interactions closely resemble face-to-face conversation and thus contain many of the linguistic phenomena enc…
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…
Vision-Language Pre-training (VLP) has achieved impressive performance on various cross-modal downstream tasks. However, most existing methods can only learn from aligned image-caption data and rely heavily on expensive regional features, which greatly limits their scalability and performance. In this paper, we propose an end-to-end unified-modal pre-training framework, namely UNIMO-2, for joint learning on both aligned image-caption data and unaligned image-only and text-only corpus. We build a unified Transformer model to jointly learn visual representations, textual representations and sema…
Charles University（查理大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN AIP（理化学研究所先进智能项目中心）
We present our work in progress exploring the possibilities of a shared embedding space between textual and visual modality. Leveraging the textual nature of object detection labels and the hypothetical expressiveness of extracted visual object representations, we propose an approach opposite to the current trend, grounding of the representations in the word embedding space of the captioning system instead of grounding words or sentences in their associated images. Based on the previous work, we apply additional grounding losses to the image captioning training objective aiming to force visual…
We present a multi-modal dialogue system for interactive learning of perceptually grounded word meanings from a human tutor. The system integrates an incremental, semantic parsing/generation framework - Dynamic Syntax and Type Theory with Records (DS-TTR) - with a set of visual classifiers that are learned throughout the interaction and which ground the meaning representations that it produces. We use this system in interaction with a simulated human tutor to study the effects of different dialogue policies and capabilities on the accuracy of learned meanings, learning rates, and efforts/costs…
We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within a life-long interactive learning period, the agent, trained using Reinforcement Learning (RL), must be able to handle natural conversations with human users and achieve good learning performance (accuracy) while minimising human effort in the learning process. We train and evaluate this system in interaction with a simulated human tutor, which is built on the BURCHAK corpus -- a Human-Human Dialogue dataset for the …
Baidu Research（百度研究院）；National Engineering Laboratory for Deep Learning Technology and Applications（深度学习技术及应用国家工程实验室）
We build a virtual agent for learning language in a 2D maze-like world. The agent sees images of the surrounding environment, listens to a virtual teacher, and takes actions to receive rewards. It interactively learns the teacher's language from scratch based on two language use cases: sentence-directed navigation and question answering. It learns simultaneously the visual representations of the world, the language, and the action control. By disentangling language grounding from other computational routines and sharing a concept detection function between language grounding and prediction, th…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）；Center for Data Science, AAIS, Peking University（北京大学人工智能研究院数据科学中心）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）
We study video-grounded dialogue generation, where a response is generated based on the dialogue context and the associated video. The primary challenges of this task lie in (1) the difficulty of integrating video data into pre-trained language models (PLMs) which presents obstacles to exploiting the power of large-scale pre-training; and (2) the necessity of taking into account the complementarity of various modalities throughout the reasoning process. Although having made remarkable progress in video-grounded dialogue generation, existing methods still fall short when it comes to integrating…
In Multimodal Neural Machine Translation (MNMT), a neural model generates a translated sentence that describes an image, given the image itself and one source descriptions in English. This is considered as the multimodal image caption translation task. The images are processed with Convolutional Neural Network (CNN) to extract visual features exploitable by the translation model. So far, the CNNs used are pre-trained on object detection and localization task. We hypothesize that richer architecture, such as dense captioning models, may be more suitable for MNMT and could lead to improved trans…
Hefei University of Technology（合肥工业大学）；University of Science and Technology of China（中国科学技术大学）；Nanyang Technological University（南洋理工大学）
Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transparency. Specifically, we expect that a captioner can fix its attentive gaze on the correct objects while generating the corresponding words. This ability is also known as grounded image captioning. However, the grounding accuracy of existing captioners is far from satisfactory. To improve the grounding accuracy while retaining the captioning quality, it is expensive to collect the word-region alignment as strong supe…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究院）
During language acquisition, infants have the benefit of visual cues to ground spoken language. Robots similarly have access to audio and visual sensors. Recent work has shown that images and spoken captions can be mapped into a meaningful common space, allowing images to be retrieved using speech and vice versa. In this setting of images paired with untranscribed spoken captions, we consider whether computer vision systems can be used to obtain textual labels for the speech. Concretely, we use an image-to-words multi-label visual classifier to tag images with soft textual labels, and then tra…
We revisit Levin's theory about the correspondence of verb meaning and syntax and infer semantic classes from a large syntactic classification of more than 600 German verbs taking clausal and non-finite arguments. Grasping the meaning components of Levin-classes is known to be hard. We address this challenge by setting up a multi-perspective semantic characterization of the inferred classes. To this end, we link the inferred classes and their English translation to independently constructed semantic classes in three different lexicons - the German wordnet GermaNet, VerbNet and FrameNet - and p…
When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the model is hallucinating based on priors in the dataset and/or the language model. The most common way of relating image regions with words in caption models is through an attention mechanism over the regions that are used as input to predict the next word. The model must therefore learn to predict the attentional weights without knowing the word it should loc…
The Technion - Israel Institute of Technology（以色列理工学院）；Walmart Labs（沃尔玛实验室）
Classifying products into categories precisely and efficiently is a major challenge in modern e-commerce. The high traffic of new products uploaded daily and the dynamic nature of the categories raise the need for machine learning models that can reduce the cost and time of human editors. In this paper, we propose a decision level fusion approach for multi-modal product classification using text and image inputs. We train input specific state-of-the-art deep neural networks for each input source, show the potential of forging them together into a multi-modal architecture and train a novel poli…
VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；University of Science and Technology of China（中国科学技术大学）
University College London（伦敦大学学院）；William Harvey Research Institute（威廉·哈维研究所）；Queen Mary University of London（伦敦玛丽女王大学）
Assisted text input techniques can save time and effort and improve text quality. In this paper, we investigate how grounded and conditional extensions to standard neural language models can bring improvements in the tasks of word prediction and completion. These extensions incorporate a structured knowledge base and numerical values from the text into the context used to predict the next word. Our automated evaluation on a clinical dataset shows extended models significantly outperform standard models. Our best system uses both conditioning and grounding, because of their orthogonal benefits.…
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Language models have emerged as a central component across NLP, and a great deal of progress depends on the ability to cheaply adapt them (e.g., through finetuning) to new domains and tasks. A language model's vocabulary$-$typically selected before training and permanently fixed later$-$affects its size and is part of what makes it resistant to such adaptation. Prior work has used compositional input embeddings based on surface forms to ameliorate this issue. In this work, we go one step beyond and propose a fully compositional output embedding layer for language models, which is further groun…
University of Edinburgh（爱丁堡大学）；Samsung AI Centre（三星人工智能中心）
Word2Vec (W2V) and GloVe are popular, fast and efficient word embedding algorithms. Their embeddings are widely used and perform well on a variety of natural language processing tasks. Moreover, W2V has recently been adopted in the field of graph embedding, where it underpins several leading algorithms. However, despite their ubiquity and relatively simple model architecture, a theoretical understanding of what the embedding parameters of W2V and GloVe learn and why that is useful in downstream tasks has been lacking. We show that different interactions between PMI vectors reflect semantic wor…
Computer Science and Artificial Intelligence Lab（计算机科学与人工智能实验室）；Massachusetts Institute of Technology（麻省理工学院）
In this paper, we present a method for learning discrete linguistic units by incorporating vector quantization layers into neural models of visually grounded speech. We show that our method is capable of capturing both word-level and sub-word units, depending on how it is configured. What differentiates this paper from prior work on speech unit learning is the choice of training objective. Rather than using a reconstruction-based loss, we use a discriminative, multimodal grounding objective which forces the learned units to be useful for semantic image retrieval. We evaluate the sub-word units…
