Kenny Q. Zhu

ST$^2$: Small-data Text Style Transfer via Multi-task Meta-Learning

2020 · arXiv (Cornell University)

Text style transfer aims to paraphrase a sentence in one style into another style while preserving content. Due to lack of parallel training data, state-of-art methods are unsupervised and rely on large datasets that share …

Enhanced Story Representation by ConceptNet for Predicting Story Endings

2020

Predicting endings for narrative stories is a grand challenge for machine commonsense reasoning. The task requires ac- curate representation of the story semantics and structured logic knowledge. Pre-trained language models, such as BERT, made progress …

Context Compression for Auto-regressive Transformers with Sentinel Tokens

2023

The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation. Moreover, the excessive key-value cache that arises when dealing with long inputs also brings severe …

Multi-channel BiLSTM-CRF Model for Emerging Named Entity Recognition in Social Media

2017

In this paper, we present our multichannel neural architecture for recognizing emerging named entity in social media messages, which we applied in the Novel and Emerging Named Entity Recognition shared task at the EMNLP 2017 …

Knowledge Base Question Answering via Encoding of Complex Query Graphs

2018

Answering complex questions that involve multiple entities and multiple relations using a standard knowledge base is an open and challenging task. Most existing KBQA approaches focus on simpler questions and do not work very well …