Share This Author
Style Transfer in Text: Exploration and Evaluation
This work proposes two novel evaluation metrics that measure two aspects of style transfer: transfer strength and content preservation, and shows that the proposed content preservation metric is highly correlate to human judgments.
Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings
A new corpus of Weibo messages annotated for both name and nominal mentions is presented and a joint training objective for the embeddings that makes use of both (NER) labeled and unlabeled raw text is proposed.
Cross-Sentence N-ary Relation Extraction with Graph LSTMs
- Nanyun Peng, Hoifung Poon, Chris Quirk, Kristina Toutanova, Wen-tau Yih
- Computer ScienceTACL
- 5 April 2017
A general relation extraction framework based on graph long short-term memory networks (graph LSTMs) that can be easily extended to cross-sentence n-ary relation extraction is explored, demonstrating its effectiveness with both conventional supervised learning and distant supervision.
Plan-And-Write: Towards Better Automatic Storytelling
- Lili Yao, Nanyun Peng, R. Weischedel, Kevin Knight, Dongyan Zhao, Rui Yan
- Computer ScienceAAAI
- 14 November 2018
Experiments show that with explicit storyline planning, the generated stories are more diverse, coherent, and on topic than those generated without creating a full plan, according to both automatic and human evaluations.
Stack-Pointer Networks for Dependency Parsing
A novel architecture for dependency parsing: stack-pointer networks (StackPtr), which first reads and encodes the whole sentence, then builds the dependency tree top-down in a depth-first fashion, yielding an efficient decoding algorithm with O(n^2) time complexity.
Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings
- Sarik Ghazarian, Johnny Tian-Zheng Wei, A. Galstyan, Nanyun Peng
- Computer ScienceProceedings of the Workshop on Methods for…
- 24 April 2019
Using contextualized word embeddings to compute more accurate relatedness scores and thus better evaluation metrics is explored, and experiments show that the evaluation metrics outperform RUBER, which is trained on staticembeddings.
Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning
It is shown that new state-of-the-art word segmentation systems use neural models to learn representations for predicting word boundaries, and these same representations, jointly trained with an NER system, yield significant improvements in NER for Chinese social media.
The Woman Worked as a Babysitter: On Biases in Language Generation
The notion of the regard towards a demographic is introduced, the varying levels of regard towards different demographics are used as a defining metric for bias in NLG, and the extent to which sentiment scores are a relevant proxy metric for regard is analyzed.
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing
- Wasi Uddin Ahmad, Zhisong Zhang, Xuezhe Ma, E. Hovy, Kai-Wei Chang, Nanyun Peng
- Computer Science, LinguisticsNAACL
- 1 November 2018
Investigating crosslingual transfer and posit that an orderagnostic model will perform better when transferring to distant foreign languages shows that RNN-based architectures transfer well to languages that are close to English, while self-attentive models have better overall cross-lingualtransferability and perform especially well on distant languages.
Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering
This paper augments a general commonsense QA framework with a knowledgeable path generator by extrapolating over existing paths in a KG with a state-of-the-art language model, which learns to connect a pair of entities in text with a dynamic, and potentially novel, multi-hop relational path.