Product reviews may have complex discourse including coreference and bridging relations to a main product, competing products, and interacting products.
We develop a system for the FEVEROUS fact extraction and verification task that ranks an initial set of potential evidence and then pursues missing evidence in subsequent hops by trying to generate it, with a “next hop prediction module” whose output is matched against page elements in a predicted article.
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training.
Finally, we show that preprocessing source reviews by simplification can raise the opinion prevalence achieved by existing abstractive opinion summarization systems to the level of human performance.
Knowledge Graphs (KGs) store information in the form of (head, predicate, tail)-triples.
We study few-shot debugging of transformer based natural language understanding models, using recently popularized test suites to not just diagnose but correct a problem.
Modern natural language understanding models depend on pretrained subword embeddings, but applications may need to reason about words that were never or rarely seen during pretraining.
Finally, we empirically show that our designed network architecture is more robust against state-of-art gradient descent based attacks, such as a PGD attack on the benchmark datasets MNIST and CIFAR10.
Learning disentangled representations of natural language is essential for many NLP tasks, e. g., conditional text generation, style transfer, personalized dialogue systems, etc.
As a first instantiation of this framework, we train a pointer-generator network to predict followup questions based on the question and partial information.
We develop a system for the FEVER fact extraction and verification challenge that uses a high precision entailment classifier based on transformer networks pretrained with language modeling, to classify a broad set of potential evidence.