Pretrained masked language models (MLMs) require finetuning for most NLP tasks. Instead,
we evaluate MLMs out of the box via their pseudo-log-likelihood scores (PLLs), which are …

Recently, sequence-to-sequence (seq2seq) models with the Transformer architecture have
achieved remarkable performance on various conditional text generation tasks, such as …

Radiology report generation aims at generating descriptive text from radiology images
automatically, which may present an opportunity to improve radiology reporting and …

Existing explanation models generate only text for recommendations but still struggle to
produce diverse contents. In this paper, to further enrich explanations, we propose a new …

Complementary product recommendation aims at providing product suggestions that are
often bought together to serve a joint demand. Existing work mainly focuses on modeling …

While neural machine translation (NMT) has achieved remarkable success, NMT systems
are prone to make word omission errors. In this work, we propose a contrastive learning …

In automatic speech recognition (ASR) rescoring, the hypothesis with the fewest errors
should be selected from the n-best list using a language model (LM). However, LMs are …

Multimodal machine translation (MMT) aims to improve translation quality by equipping the
source sentence with its corresponding image. Despite the promising performance, MMT …

Few-shot learning aims to train models that can be generalized to novel classes with only a
few samples. Recently, a line of works are proposed to enhance few-shot learning with …

Existing models for data-to-text tasks generate fluent but sometimes incorrect sentences
eg,“Nikkei gains” is generated when “Nikkei drops” is expected. We investigate models …