Many natural language processing (NLP) tasks appear in dual forms, which are generally
solved by dual learning technique that models the dualities between the coupled tasks. In …

Language understanding research is held back by a failure to relate language to the
physical world it describes and to the social interactions it facilitates. Despite the incredible …

Multimodal sentiment analysis aims to extract and integrate semantic information collected
from multiple modalities to recognize the expressed emotions and sentiment in multimodal …

Generative models of code, pretrained on large corpora of programs, have shown great
success in translating natural language to code (Chen et al., 2021; Austin et al., 2021; Li et …

Humans learn language by listening, speaking, writing, reading, and also, via interaction
with the multimodal real world. Existing language pre-training frameworks show the …

Machine learning has been advancing dramatically over the past decade. Most strides are
human-based applications due to the availability of large-scale datasets; however …

The rapid growth of user-generated videos on the Internet has intensified the need for text-
based video retrieval systems. Traditional methods mainly favor the concept-based …

We study a formalization of the grammar induction problem that models sentences as being
generated by a compound probabilistic context-free grammar. In contrast to traditional …

The success of large-scale contrastive vision-language pretraining (CLIP) has benefited
both visual recognition and multimodal content understanding. The concise design brings …

With the recent success and popularity of pre-trained language models (LMs) in natural
language processing, there has been a rise in efforts to understand their inner workings. In …