Reconstruction Loss

AbstractAutoregressive language models are powerful and relatively easy to train. However, these models are usually trained without explicit conditioning labels and do not offer easy ways to control global aspects …...

AbstractUnconscious biases continue to be prevalent in modern text and media, calling for algorithms that can assist writers with bias correction. For example, a female character in a story is …...

AbstractKB-to-text task aims at generating texts based on the given KB triples. Traditional methods usually map KB triples to sentences via a supervised seq-to-seq model. However, existing annotated datasets are …...

AbstractDense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output …...

AbstractMost event extraction methods have traditionally relied on an annotated set of event types. However, creating event ontologies and annotating supervised training data are expensive and time-consuming. Previous work has …...