Matching a target text to a source text based on their meaning.
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 co-occurrence in the same article.
In order to better capture sentence level semantic relations within a document, we pre-train the model with a novel masked sentence block language modeling task in addition to the masked word language modeling task used by BERT.
In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation.
Ranked #3 on Text-to-Image Generation on COCO (SOA-C metric)
Different from previous work that applies joint random masking to both modalities, we use conditional masking on pre-training tasks (i. e., masked language/region modeling is conditioned on full observation of image/text).
Ranked #1 on Visual Reasoning on NLVR2 Test
Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to capture limited number of semantic alignments which is less interpretable.
Ranked #5 on Cross-Modal Retrieval on Flickr30k
This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems.
Ranked #1 on Extractive Text Summarization on CNN / Daily Mail
In this paper, we present a fast and strong neural approach for general purpose text matching applications.
Ranked #3 on Question Answering on WikiQA
Deep Semantic Matching is a crucial component in various natural language processing applications such as question and answering (QA), where an input query is compared to each candidate question in a QA corpus in terms of relevance.
That is because there are usually many noises in the setting of long-form text matching, and it is difficult for existing semantic text matching to capture the key matching signals from this noisy information.