This work presents a neural, modular entity linking system that learns a unified dense representation for each entity using multiple sources of information, such as its description, contexts around its mentions, and its fine-grained types.
This work extends Neural module networks by introducing modules that reason over a paragraph of text, performing symbolic reasoning over numbers and dates in a probabilistic and differentiable manner, and proposing an unsupervised auxiliary loss to help extract arguments associated with the events in text.
A more rigorous annotation paradigm for NLP that helps to close systematic gaps in the test data, and recommends that the dataset authors manually perturb the test instances in small but meaningful ways that (typically) change the gold label, creating contrast sets.
This work develops the first XEL approach that combines supervision from multiple languages jointly, and trains a single entity linking model for multiple languages, improving upon individually trained models for each language.
A new annotation paradigm for NLP is proposed that helps to close systematic gaps in the test data, and it is recommended that after a dataset is constructed, the dataset authors manually perturb the test instances in small but meaningful ways that change the gold label, creating contrast sets.
This work addresses the problem of robustness of NER systems in data with noisy or uncertain casing, using a pretraining objective that predicts casing in text, or a truecaser, leveraging unlabeled data.
This work analyzes a wide variety of models and proposes multiple extensions to the attention module of the semantic parser, aiming to improve compositional generalization in semantic parsing, as output programs are constructed from sub-components.
A new evaluation methodology is suggested which overcomes limitations of past works, and allows for an accurate assessment of CDEC systems, and better reflects the corpus-wide information aggregation ability ofCDEC systems.
This paper presents a generic approach to factorization of relational data that collectively models all the relations in the database, and demonstrates effective utilization of additional information for held-out preference prediction on multiple Amazon and Yelp datasets.
It is found that the intermediate outputs of NMNs differ from the expected output, illustrating that the network structure does not provide a faithful explanation of model behaviour, and particular choices for module architecture are proposed that yield much better faithfulness, at a minimal cost to accuracy.