• Publications
  • Influence
Entity Linking via Joint Encoding of Types, Descriptions, and Context
TLDR
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. Expand
Neural Module Networks for Reasoning over Text
TLDR
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. Expand
Joint Multilingual Supervision for Cross-lingual Entity Linking
TLDR
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. Expand
Evaluating Models’ Local Decision Boundaries via Contrast Sets
TLDR
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. Expand
Evaluating NLP Models via Contrast Sets
TLDR
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. Expand
Obtaining Faithful Interpretations from Compositional Neural Networks
TLDR
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. Expand
Improving Compositional Generalization in Semantic Parsing
TLDR
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. Expand
Robust Named Entity Recognition with Truecasing Pretraining
TLDR
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. Expand
Revisiting the Evaluation for Cross Document Event Coreference
TLDR
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. Expand
Collectively Embedding Multi-Relational Data for Predicting User Preferences
TLDR
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. Expand
...
1
2
...