Spain

Standard image caption generation systems produce generic descriptions of images and do not utilize any contextual information or world knowledge. In particular, they are unable to generate captions that contain references to the geographic context of an image, for example, the location where a photograph is taken or relevant geographic objects around an image location. In this talk, we will present a geo-aware image caption generation system, which incorporates geographic contextual information into a standard image captioning pipeline. We describe a way to build an image-specific representation of the geographic context and to adapt the caption generation network to produce appropriate geographic names in the image descriptions. We show the results of evaluating our system on a novel captioning dataset that contains contextualized captions and geographic metadata. The system achieves substantial improvements in BLEU, ROUGE, METEOR and CIDEr scores. We also present a new metric that assesses generated geographic references directly and empirically demonstrate our system&#39;s ability to produce captions with relevant and factually accurate geographic referencing.

COLING 2020

Geo-Aware Image Caption Generation

geographic context

contextualized language generation

geographic information

knowledge integration

caption generation

image captioning

contextualization

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

Standard image caption generation systems produce generic descriptions of images and do not utilize any contextual information or world knowledge. In particular, they are unable to generate captions that contain references to the geographic context of an image, for example, the location where a photograph is taken or relevant geographic objects around an image location. In this talk, we will present a geo-aware image caption generation system, which incorporates geographic contextual information into a standard image captioning pipeline. We describe a way to build an image-specific representation of the geographic context and to adapt the caption generation network to produce appropriate geographic names in the image descriptions. We show the results of evaluating our system on a novel captioning dataset that contains contextualized captions and geographic metadata. The system achieves substantial improvements in BLEU, ROUGE, METEOR and CIDEr scores. We also present a new metric that assesses generated geographic references directly and empirically demonstrate our system's ability to produce captions with relevant and factually accurate geographic referencing.

technical paper

This paper extends existing work on terminology integration into Neural Machine Translation, a common industrial practice to dynamically adapt translation to a specific domain. Our method, based on the use of placeholders complemented with morphosyntactic annotation, efficiently taps into the ability of the neural network to deal with symbolic knowledge to surpass the surface generalization shown by alternative techniques. We compare our approach to state-of-the-art systems and benchmark them through a well-defined evaluation framework, focusing on actual application of terminology and not just on the overall performance. Results indicate the suitability of our method in the use-case where terminology is used in a system trained on generic data only.

Integrating Domain Terminology into Neural Machine Translation

Recently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research has explored the suitability of this approach in low resource settings with less than 1,000 training data points. In this work, we explore fine-tuning methods of BERT - a pre-trained Transformer based language model - by utilizing pool-based active learning to speed up training while keeping the cost of labeling new data constant. Our experimental results on the GLUE data set show an advantage in model performance by maximizing the approximate knowledge gain of the model when querying from the pool of unlabeled data. Finally, we demonstrate and analyze the benefits of freezing layers of the language model during fine-tuning to reduce the number of trainable parameters, making it more suitable for low-resource settings.

Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning

Question generation over knowledge bases (KBQG) aims at generating natural-language questions about a subgraph, i.e. a set of (connected) triples. Two main challenges still face the current crop of encoder-decoder-based methods, especially on small subgraphs: (1) low diversity and poor fluency due to the limited information contained in the subgraphs, and (2) semantic drift due to the decoder’s oblivion of the semantics of the answer entity. We propose an innovative knowledge-enriched, type-constrained and grammar-guided KBQG model, named KTG, to addresses the above challenges.

Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases

In this paper, we approach the multilingual text classification task in the context of the epidemiological field. Multilingual text classification models tend to perform differently across different languages (low- or high-resource), more particularly when the dataset is highly imbalanced, which is the case for epidemiological datasets. We conduct a comparative study of different machine and deep learning text classification models using a dataset comprising news articles related to epidemic outbreaks from six languages, four low-resourced and two high-resourced, in order to analyze the influence of the nature of the language, the structure of the document, and the size of the data. Our findings indicate that the performance of the models based on fine-tuned language models exceeds by more than 50% the chosen baseline models that include a specialized epidemiological news surveillance system and several machine learning models. Also, low-resource languages are highly influenced not only by the typology of the languages on which the models have been pre-trained or/and fine-tuned but also by their size. Furthermore, we discover that the beginning and the end of documents provide the most salient features for this task and, as expected, the performance of the models was proportionate to the training data size.

Multilingual Epidemiological Text Classification: A Comparative Study

Recent image captioning models have made much progress for exploring the multi-modal interaction, such as attention mechanisms. Though these mechanisms can boost the interaction, there are still two gaps between the visual and language domains: (1) the gap between the visual features and textual semantics, (2) the gap between the disordering of visual features and the ordering of texts. To bridge the gaps we propose a high-level semantic planning (HSP) mechanism that incorporates both a semantic reconstruction and an explicit order planning. We integrate the planning mechanism to the attention based caption model and propose the High-level Semantic PLanning based Attention Network (HS-PLAN). First, an attention based reconstruction module is designed to reconstruct the visual features with high-level semantic information. Then we apply a pointer network to serialize the features and obtain the explicit order plan to guide the generation. Experiments conducted on MS COCO show that our model outperforms previous methods and achieves the state-of-the-art performance of 133.4% CIDEr-D score.

Bridge the Gap: High-level Semantic Planning for Image Captioning

We focus on a recently deployed system built for summarizing academic articles by concept tagging. The system has shown great coverage and high accuracy of concept identification which could be contributed by the knowledge acquired from millions of publications. Provided with the explainable concepts and knowledge encoded in a pre-trained neural model, we investigate whether the tagged concepts can be applied to a broader class of applications. We propose transforming the tagged concepts into sparse vectors as representations of academic documents. The effectiveness of the representations is analyzed theoretically by a proposed framework. We also empirically show that the representations can have advantages on academic topic discovery and paper recommendation.

Explainable and Sparse Representations of Academic Articles for Knowledge Exploration

The automatic summarization of argumentative texts has hardly been explored. This paper takes a further step in this direction, targeting news editorials, i.e., opinionated articles with a well-defined argumentation structure. With Webis-EditorialSum-2020, we present a corpus of 1330 carefully curated summaries for 266 news editorials. We evaluate these summaries based on a tailored annotation scheme, where a high-quality summary is expected to be thesis-indicative, persuasive, reasonable, concise, and self-contained. Our corpus contains at least three high-quality summaries for about 90% of the editorials, rendering it a valuable resource for the development and evaluation of summarization technology for long argumentative texts. We further report details of both, an in-depth corpus analysis, and the evaluation of two extractive summarization models.

News Editorials: Towards Summarizing Long Argumentative Texts

Mannual annotation for dependency parsing is both labourious and time costly, resulting in the difficulty to learn practical dependency parsers for many languages due to the lack of labelled training corpora. To compensate for the scarcity of labelled data, semi-supervised dependency parsing methods are developed to utilize unlabelled data in the training procedure of dependency parsers. In previous work, the autoencoder framework is a prevalent approach for the utilization of unlabelled data. In this framework, training sentences are reconstructed from a decoder conditioned on dependency trees predicted by an encoder. The tree structure requirement brings challenges for both the encoder and the decoder. Sophisticated techniques are employed to tackle these challenges at the expense of model complexity and approximations in encoding and decoding. In this paper, we propose a model based on the variational autoencoder framework. By relaxing the tree constraint in both the encoder and the decoder during training, we make the learning of our model fully arc-factored and thus circumvent the challenges brought by the tree constraint. We evaluate our model on datasets across several languages and the results demonstrate the advantage of our model over previous approaches in both parsing accuracy and speed.

Semi-Supervised Dependency Parsing with Arc-Factored Variational Autoencoding

Press releases have an increasingly strong influence on media coverage of health research; how- ever, they have been found to contain seriously exaggerated claims that can misinform the public and undermine public trust in science. In this study we propose an NLP approach to identify ex- aggerated causal claims made in health press releases that report on observational studies, which are designed to establish correlational findings, but are often exaggerated as causal. We devel- oped a new corpus and trained models that can identify causal claims in the main statements in a press release. By comparing the claims made in a press release with the corresponding claims in the original research paper, we found that 22% of press releases made exaggerated causal claims from correlational findings in observational studies. Furthermore, universities exagger- ated more often than journal publishers by a ratio of 1.5 to 1. Encouragingly, the exaggeration rate has slightly decreased over the past 10 years, despite the increase of the total number of press releases. More research is needed to understand the cause of the decreasing pattern.

Measuring correlation-to-causation exaggeration in press releases

Automatic evaluation of language generation systems is a well-studied problem in Natural Language Processing. While novel metrics are proposed every year, a few popular metrics remain as the \I{de facto} metrics to evaluate tasks such as image captioning and machine translation, despite their known limitations. This is partly due to ease of use, and partly because researchers expect to see them and know how to interpret them. In this paper, we urge the community for more careful consideration of how they automatically evaluate their models by demonstrating important failure cases on multiple datasets, language pairs and tasks. Our experiments show that metrics (i) usually prefer system outputs to human-authored texts, (ii) can be insensitive to correct translations of rare words, (iii) can yield surprisingly high scores when given a single sentence as system output for the entire test set.

Geo-Aware Image Caption Generation

Downloads

Next from COLING 2020

Integrating Domain Terminology into Neural Machine Translation

Similar lecture

Bridge the Gap: High-level Semantic Planning for Image Captioning

Geo-Aware Image Caption Generation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Integrating Domain Terminology into Neural Machine Translation

Similar lecture

Bridge the Gap: High-level Semantic Planning for Image Captioning

Downloads