S
Siva Reddy
Researcher at University of Cambridge
Publications - 82
Citations - 4168
Siva Reddy is an academic researcher from University of Cambridge. The author has contributed to research in topics: Parsing & Natural language. The author has an hindex of 25, co-authored 82 publications receiving 3321 citations. Previous affiliations of Siva Reddy include McGill University & International Institute of Information Technology, Hyderabad.
Papers
More filters
Journal ArticleDOI
Learning an Executable Neural Semantic Parser
TL;DR: The authors describe a neural semantic parser that maps natural language utterances onto logical forms that can be executed against a task-specific environment, such as a knowledge base or a data set.
Proceedings ArticleDOI
Understanding by Understanding Not: Modeling Negation in Language Models.
TL;DR: By training BERT with the resulting combined objective of an unlikelihood objective that is based on negated generic sentences from a raw text corpus, this work reduces the mean top 1 error rate to 4% on the negated LAMA dataset.
Proceedings ArticleDOI
StereoSet: Measuring stereotypical bias in pretrained language models
TL;DR: This article presented StereoSet, a large-scale natural English dataset to measure stereotypical biases in four domains: gender, profession, race, and religion, and compared both stereotypical bias and language modeling ability of popular models like BERT, GPT-2, RoBERTa and XLnet.
Proceedings ArticleDOI
Assessing Relative Sentence Complexity using an Incremental CCG Parser
TL;DR: The authors' evaluation on Simple and Standard Wikipedia sentence pairs suggests that incremental CCG features are indeed more useful than phrase structure features achieving 0.44 points gain in performance.
Journal ArticleDOI
Learning Typed Entailment Graphs with Global Soft Constraints
Mohammad Javad Hosseini,Nathanael Chambers,Siva Reddy,Xavier Holt,Shay B. Cohen,Mark Johnson,Mark Steedman +6 more
TL;DR: This paper presents a scalable method that learns globally consistent similarity scores based on new soft constraints that consider both the structures across typed entailment graphs and inside each graph, and shows large improvements over local similarity scores on two entailment data sets.