Building scalable models to learn from diverse, multimodal data remains an open challenge.
For vision-language data, the dominant approaches are based on contrastive learning …

Cross-lingual transfer, where a high-resource transfer language is used to improve the
accuracy of a low-resource task language, is now an invaluable tool for improving …

Heterologous expression is the main approach for recombinant protein production ingenetic
synthesis, for which codon optimization is necessary. The existing optimization methods are …

A recently proposed lattice model has demonstrated that words in character sequence can
provide rich word boundary information for character-based Chinese NER model. In this …

Named entity recognition (NER) models are typically based on the architecture of Bi-
directional LSTM (BiLSTM). The constraints of sequential nature and the modeling of single …

Gazetteers were shown to be useful resources for named entity recognition (NER). Many
existing approaches to incorporating gazetteers into machine learning based NER systems …

Visual contexts often help to recognize named entities more precisely in short texts such as
tweets or snapchat. For example, one can identify" Charlie''as a name of a dog according to …

Document-level relation extraction (DocRE) is the task of identifying all relations between
each entity pair in a document. Evidence, defined as sentences containing clues for the …

Existing works, including ELMO and BERT, have revealed the importance of pre-training for
NLP tasks. While there does not exist a single pre-training model that works best in all …

In an increasingly connected global market, news sentiment towards one company may not
only indicate its own market performance, but can also be associated with a broader …