K
Kristina Toutanova
Researcher at Google
Publications - 121
Citations - 68587
Kristina Toutanova is an academic researcher from Google. The author has contributed to research in topics: Machine translation & Parsing. The author has an hindex of 47, co-authored 113 publications receiving 40174 citations. Previous affiliations of Kristina Toutanova include Microsoft & Stanford University.
Papers
More filters
Posted Content
Improving Span-based Question Answering Systems with Coarsely Labeled Data.
TL;DR: This work studies approaches to improve fine-grained short answer Question Answering models by integrating coarse- grained data annotated for paragraph-level relevance and shows that coarsely annotated data can bring significant performance gains.
Posted Content
Joint Passage Ranking for Diverse Multi-Answer Retrieval
TL;DR: The authors propose a joint passage retrieval model focusing on re-ranking, which makes use of an autoregressive re-ranker that selects a sequence of passages, equipped with novel training and decoding algorithms.
Posted Content
Representations for Question Answering from Documents with Tables and Text
TL;DR: This paper proposed a method to combine text and table-based predictions for question answering from full documents, obtaining significant improvements on the Natural Questions dataset, using the information from an article as additional context.
Counterfactual reasoning: Do Language Models need world knowledge for causal inference?
TL;DR: It is found that pre-trained language models are consistently able to override real-world knowledge in counterfactual scenarios, and that this effect is more robust in case of stronger baseline world knowledge—however, it is also found that for most models this effect appears largely to be driven by simple lexical cues.
The MSR-NRC-SRI MT System for NIST Open Machine Translation 2008 Evaluation
Xiaodong He,Jianfeng Gao,Chris Quirk,Patrick Nguyen,Arul Menezes,Robert C. Moore,Kristina Toutanova,Mei Yang,Bill Dolan,Mu Li,Chi-Ho Li,Dongdong Zhang,Long Jiang,Ming Zhou,Henry Li +14 more
TL;DR: A new method to generate a better alignment between multiple MT hypotheses from different individual systems is developed, which is used to construct a high-quality confusion network.