Pre-trained Language Models (PLMs) which are trained on large text corpus via self-
supervised learning method, have yielded promising performance on various tasks in …

Universally modeling all typical information extraction tasks (UIE) with one generative
language model (GLM) has revealed great potential by the latest study, where various IE …

Math Word Problem (MWP) solving needs to discover the quantitative relationships over
natural language narratives. Recent work shows that existing models memorize procedures …

Although neural models have achieved competitive results in dialogue systems, they have
shown limited ability in representing core semantics, such as ignoring important entities. To …

Transformer-based language models pre-trained on large amounts of text data have proven
remarkably successful in learning generic transferable linguistic representations. Here we …

Despite recent progress towards scaling up multimodal vision-language models, these
models are still known to struggle on compositional generalization benchmarks such as …

Social media is a widely used platform that provides a huge amount of user-generated
content that can be processed to extract information about users' emotions. This has …

Paraphrase identification involves identifying whether a pair of sentences express the same
or similar meanings. While cross-encoders have achieved high performances across …

Grammatical Error Correction (GEC) aims to automatically detect and correct grammatical
errors. In this aspect, dominant models are trained by one-iteration learning while …

Transformers are now widely used in code representation, and several recent works further
develop tree Transformers to capture the syntactic structure in source code. Specifically …