arXiv subjects

Shuyang Cao

Publications and source records attributed to Shuyang Cao.

24 records · Page 2Linked to original sources

arXiv2021

Controllable Open-ended Question Generation with A New Question Type Ontology

We investigate the less-explored task of generating open-ended questions that are typically answered by multiple sentences. We first define a new question type ontology which differentiates the nuanced nature of questions better than widely used question words. A new dataset with 4,959 questions is labeled based on the new ontology. We then propose a novel question type-aware question generation framework, augmented by a semantic graph representation, to jointly predict question focuses and produce the question. Based on this framework, we further use both exemplars and automatically generated templates to improve controllability and diversity. Experiments on two newly collected large-scale datasets show that our model improves question quality over competitive comparisons based on automatic metrics. Human judges also rate our model outputs highly in answerability, coverage of scope, and overall quality. Finally, our model variants with templates can produce questions with enhanced controllability and diversity.

cs.CL↗

arXiv2021

Efficient Attentions for Long Document Summarization

The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional strides to effectively pinpoint salient information from the source. We further conduct a systematic study of existing efficient self-attentions. Combined with Hepos, we are able to process ten times more tokens than existing models that use full attentions. For evaluation, we present a new dataset, GovReport, with significantly longer documents and summaries. Results show that our models produce significantly higher ROUGE scores than competitive comparisons, including new state-of-the-art results on PubMed. Human evaluation also shows that our models generate more informative summaries with fewer unfaithful errors.

cs.CL↗

arXiv2021

Attention Head Masking for Inference Time Content Selection in Abstractive Summarization

How can we effectively inform content selection in Transformer-based abstractive summarization models? In this work, we present a simple-yet-effective attention head masking technique, which is applied on encoder-decoder attentions to pinpoint salient content at inference time. Using attention head masking, we are able to reveal the relation between encoder-decoder attentions and content selection behaviors of summarization models. We then demonstrate its effectiveness on three document summarization datasets based on both in-domain and cross-domain settings. Importantly, our models outperform prior state-of-the-art models on CNN/Daily Mail and New York Times datasets. Moreover, our inference-time masking technique is also data-efficient, requiring only 20% of the training samples to outperform BART fine-tuned on the full CNN/DailyMail dataset.

cs.CL↗

arXiv2021

Inference Time Style Control for Summarization

How to generate summaries of different styles without requiring corpora in the target styles, or training separate models? We present two novel methods that can be deployed during summary decoding on any pre-trained Transformer-based summarization model. (1) Decoder state adjustment instantly modifies decoder final states with externally trained style scorers, to iteratively refine the output against a target style. (2) Word unit prediction constrains the word usage to impose strong lexical control during generation. In experiments of summarizing with simplicity control, automatic evaluation and human judges both find our models producing outputs in simpler languages while still informative. We also generate news headlines with various ideological leanings, which can be distinguished by humans with a reasonable probability.

cs.CL↗

arXiv2018

Extraction and identification of noise patterns for ultracold atoms in an optical lattice

To extract useful information about quantum effects in cold atom experiments, one central task is to identify the intrinsic quantum fluctuation from extrinsic system noises of various kinds. As a data processing method, principal component analysis can decompose fluctuations in experimental data into eigen modes, and give a chance to separate noises originated from different physical sources. In this paper, we demonstrate for Bose-Einstein condensates in one-dimensional optical lattices that the principal component analysis can be applied to time-of-flight images to successfully separate and identify noises from different origins of leading contribution, and can help to reduce or even eliminate noises via corresponding data processing procedures. The attribution of noise modes to their physical origins is also confirmed by numerical analysis within a mean-field theory.

cond-mat.quant-gas↗

arXiv2018

Deformable Stacked Structure for Named Entity Recognition

Neural architecture for named entity recognition has achieved great success in the field of natural language processing. Currently, the dominating architecture consists of a bi-directional recurrent neural network (RNN) as the encoder and a conditional random field (CRF) as the decoder. In this paper, we propose a deformable stacked structure for named entity recognition, in which the connections between two adjacent layers are dynamically established. We evaluate the deformable stacked structure by adapting it to different layers. Our model achieves the state-of-the-art performances on the OntoNotes dataset.

cs.CL↗