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 …

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

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 …

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 …

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 …

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

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 …

When acquiring syntax, children consistently choose hierarchical rules over competing non-
hierarchical possibilities. Is this preference due to a learning bias for hierarchical structure …

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