Related papers: Enhancing BERT-Based Visual Question Answering thr…
This paper focuses on enhancing the captions generated by image-caption generation systems. We propose an approach for improving caption generation systems by choosing the most closely related output to the image rather than the most likely…
Abstract: In this paper we present an approach to develop a text-classification model which would be able to identify populist content in text. The developed BERT-based model is largely successful in identifying populist content in text and…
We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or…
Most organizational data in this world are stored as documents, and visual retrieval plays a crucial role in unlocking the collective intelligence from all these documents. However, existing benchmarks focus on English-only document…
A considerable number of texts encountered daily are somehow connected with each other. For example, Wikipedia articles refer to other articles via hyperlinks, scientific papers relate to others via citations or (co)authors, while tweets…
Visual question answering (VQA) and image captioning require a shared body of general knowledge connecting language and vision. We present a novel approach to improve VQA performance that exploits this connection by jointly generating…
In this paper, we report our method for the Information Extraction task in 2019 Language and Intelligence Challenge. We incorporate BERT into the multi-head selection framework for joint entity-relation extraction. This model extends…
Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…
Recently, the automatic prediction of personality traits has received increasing attention and has emerged as a hot topic within the field of affective computing. In this work, we present a novel deep learning-based approach for automated…
Using attention weights to identify information that is important for models' decision-making is a popular approach to interpret attention-based neural networks. This is commonly realized in practice through the generation of a heat-map for…
We present a method for exploring regions around individual points in a contextualized vector space (particularly, BERT space), as a way to investigate how these regions correspond to word senses. By inducing a contextualized "pseudoword"…
Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, directly…
Search engines rely heavily on term-based approaches that represent queries and documents as bags of words. Text---a document or a query---is represented by a bag of its words that ignores grammar and word order, but retains word frequency…
Classification is a common AI problem, and vector search is a typical solution. This transforms a given body of text into a numerical representation, known as an embedding, and modern improvements to vector search focus on optimising speed…
Pre-training a language model and then fine-tuning it for downstream tasks has demonstrated state-of-the-art results for various NLP tasks. Pre-training is usually independent of the downstream task, and previous works have shown that this…
In this paper, we consider the problem of machine reading task when the questions are in the form of keywords, rather than natural language. In recent years, researchers have achieved significant success on machine reading comprehension…
One of the most remarkable properties of word embeddings is the fact that they capture certain types of semantic and syntactic relationships. Recently, pre-trained language models such as BERT have achieved groundbreaking results across a…
For tasks involving language and vision, the current state-of-the-art methods tend not to leverage any additional information that might be present to gather relevant (commonsense) knowledge. A representative task is Visual Question…
Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a…
This paper describes a novel study on using `Attention Mask' input in transformers and using this approach for detecting offensive content in both English and Persian languages. The paper's principal focus is to suggest a methodology to…