We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data. Our alignment model is based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks over sentences, and a structured objective that aligns the two modalities through a multimodal embedding. We then describe a Multimodal Recurrent Neural Network architecture that uses the inferred alignments to learn to generate novel descriptions of image regions. We demonstrate that our alignment model produces state of the art results in retrieval experiments on Flickr8K, Flickr30K and MSCOCO datasets. We then show that the generated descriptions significantly outperform retrieval baselines on both full images and on a new dataset of region-level annotations.

/pdf/deep-visual-semantic-alignments-for-generating-image-511hd6wg22.pdf

Deep visual-semantic alignments for generating image descriptions

We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data. Our alignment model is based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks (RNN) over sentences, and a structured objective that aligns the two modalities through a multimodal embedding. We then describe a Multimodal Recurrent Neural Network architecture that uses the inferred alignments to learn to generate novel descriptions of image regions. We demonstrate that our alignment model produces state of the art results in retrieval experiments on Flickr8K, Flickr30K and MSCOCO datasets. We then show that the generated descriptions outperform retrieval baselines on both full images and on a new dataset of region-level annotations. Finally, we conduct large-scale analysis of our RNN language model on the Visual Genome dataset of 4.1 million captions and highlight the differences between image and region-level caption statistics.

Deep Visual-Semantic Alignments for Generating Image Descriptions

Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network

In this paper, we train a semantic parser that scales up to Freebase. Instead of relying on annotated logical forms, which is especially expensive to obtain at large scale, we learn from question-answer pairs. The main challenge in this setting is narrowing down the huge number of possible logical predicates for a given question. We tackle this problem in two ways: First, we build a coarse mapping from phrases to predicates using a knowledge base and a large text corpus. Second, we use a bridging operation to generate additional predicates based on neighboring predicates. On the dataset of Cai and Yates (2013), despite not having annotated logical forms, our system outperforms their state-of-the-art parser. Additionally, we collected a more realistic and challenging dataset of question-answer pairs and improves over a natural baseline.

/pdf/semantic-parsing-on-freebase-from-question-answer-pairs-y7fve0pp42.pdf

Semantic Parsing on Freebase from Question-Answer Pairs

Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction toward cognition and human-level intelligence. In this survey, we provide a comprehensive review of the knowledge graph covering overall research topics about: 1) knowledge graph representation learning; 2) knowledge acquisition and completion; 3) temporal knowledge graph; and 4) knowledge-aware applications and summarize recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models, and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference, and logical rule reasoning are reviewed. We further explore several emerging topics, including metarelational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of data sets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.

A Survey on Knowledge Graphs: Representation, Acquisition and Applications

General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris' distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task's training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED.

Matching the Blanks: Distributional Similarity for Relation Learning

General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris’ distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task’s training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED

/pdf/matching-the-blanks-distributional-similarity-for-relation-44twxuksvy.pdf

As robots become more ubiquitous and capable, it becomes ever more important to enable untrained users to easily interact with them. Recently, this has led to study of the language grounding problem, where the goal is to extract representations of the meanings of natural language tied to perception and actuation in the physical world. In this paper, we present an approach for joint learning of language and perception models for grounded attribute induction. Our perception model includes attribute classifiers, for example to detect object color and shape, and the language model is based on a probabilistic categorial grammar that enables the construction of rich, compositional meaning representations. The approach is evaluated on the task of interpreting sentences that describe sets of objects in a physical workspace. We demonstrate accurate task performance and effective latent-variable concept induction in physical grounded scenes.

A Joint Model of Language and Perception for Grounded Attribute Learning

As robots become more ubiquitous and capable, it becomes ever more important for untrained users to easily interact with them. Recently, this has led to study of the language grounding problem, where the goal is to extract representations of the meanings of natural language tied to the physical world. We present an approach for joint learning of language and perception models for grounded attribute induction. The perception model includes classifiers for physical characteristics and a language model based on a probabilistic categorial grammar that enables the construction of compositional meaning representations. We evaluate on the task of interpreting sentences that describe sets of objects in a physical workspace, and demonstrate accurate task performance and effective latent-variable concept induction in physical grounded scenes.

/pdf/a-joint-model-of-language-and-perception-for-grounded-2stzruzr6a.pdf

We present a new method for semantic role labeling in which arguments and semantic roles are jointly embedded in a shared vector space for a given predicate. These embeddings belong to a neural network, whose output represents the potential functions of a graphical model designed for the SRL task. We consider both local and structured learning methods and obtain strong results on standard PropBank and FrameNet corpora with a straightforward product-of-experts model. We further show how the model can learn jointly from PropBank and FrameNet annotations to obtain additional improvements on the smaller FrameNet dataset.

/pdf/semantic-role-labeling-with-neural-network-factors-2sk9p1htbp.pdf

Nicholas FitzGerald

Papers

Matching the Blanks: Distributional Similarity for Relation Learning

Matching the Blanks: Distributional Similarity for Relation Learning

A Joint Model of Language and Perception for Grounded Attribute Learning

A Joint Model of Language and Perception for Grounded Attribute Learning

Semantic Role Labeling with Neural Network Factors