conftrace_

reward augmented maximum likelihood

5 papers

Explore in graph

Also known as

RAML

Co-occurring keywords · papers mentioning both

token-level loss (1) sequence-level loss (1) response diversity (1) neural language model (1) semantic entailment (1) dialog response generation (1) boosting ensemble (1) ranked list truncation (1) patent search (1) legal search (1)

Papers

Learning to Truncate Ranked Lists for Information Retrieval AAAI 2021 Boosting Dialog Response Generation ACL 2019 Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization COLING 2018 From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction ACL 2018 Token-level and sequence-level loss smoothing for RNN language models ACL 2018