Dingcheng Li


2021

pdf bib
Contextual Rephrase Detection for Reducing Friction in Dialogue Systems
Zhuoyi Wang | Saurabh Gupta | Jie Hao | Xing Fan | Dingcheng Li | Alexander Hanbo Li | Chenlei Guo
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

For voice assistants like Alexa, Google Assistant, and Siri, correctly interpreting users’ intentions is of utmost importance. However, users sometimes experience friction with these assistants, caused by errors from different system components or user errors such as slips of the tongue. Users tend to rephrase their queries until they get a satisfactory response. Rephrase detection is used to identify the rephrases and has long been treated as a task with pairwise input, which does not fully utilize the contextual information (e.g. users’ implicit feedback). To this end, we propose a contextual rephrase detection model ContReph to automatically identify rephrases from multi-turn dialogues. We showcase how to leverage the dialogue context and user-agent interaction signals, including the user’s implicit feedback and the time gap between different turns, which can help significantly outperform the pairwise rephrase detection models.

pdf bib
Learning to Selectively Learn for Weakly-supervised Paraphrase Generation
Kaize Ding | Dingcheng Li | Alexander Hanbo Li | Xing Fan | Chenlei Guo | Yang Liu | Huan Liu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Paraphrase generation is a longstanding NLP task that has diverse applications on downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised endeavors have been proposed to alleviate this issue, they may fail to generate meaningful paraphrases due to the lack of supervision signals. In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with data of weak supervision. Specifically, we tackle the weakly-supervised paraphrase generation problem by: (1) obtaining abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion; and (2) developing a meta-learning framework to progressively select valuable samples for fine-tuning a pre-trained language model BART on the sentential paraphrasing task. We demonstrate that our approach achieves significant improvements over existing unsupervised approaches, and is even comparable in performance with supervised state-of-the-arts.

pdf bib
A Deep Decomposable Model for Disentangling Syntax and Semantics in Sentence Representation
Dingcheng Li | Hongliang Fei | Shaogang Ren | Ping Li
Findings of the Association for Computational Linguistics: EMNLP 2021

Recently, disentanglement based on a generative adversarial network or a variational autoencoder has significantly advanced the performance of diverse applications in CV and NLP domains. Nevertheless, those models still work on coarse levels in the disentanglement of closely related properties, such as syntax and semantics in human languages. This paper introduces a deep decomposable model based on VAE to disentangle syntax and semantics by using total correlation penalties on KL divergences. Notably, we decompose the KL divergence term of the original VAE so that the generated latent variables can be separated in a more clear-cut and interpretable way. Experiments on benchmark datasets show that our proposed model can significantly improve the disentanglement quality between syntactic and semantic representations for semantic similarity tasks and syntactic similarity tasks.

2020

pdf bib
Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
Kaize Ding | Jianling Wang | Jundong Li | Dingcheng Li | Huan Liu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Text classification is a critical research topic with broad applications in natural language processing. Recently, graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising results on this canonical task. Despite the success, their performance could be largely jeopardized in practice since they are: (1) unable to capture high-order interaction between words; (2) inefficient to handle large datasets and new documents. To address those issues, in this paper, we propose a principled model – hypergraph attention networks (HyperGAT), which can obtain more expressive power with less computational consumption for text representation learning. Extensive experiments on various benchmark datasets demonstrate the efficacy of the proposed approach on the text classification task.

2019

pdf bib
End-to-end Deep Reinforcement Learning Based Coreference Resolution
Hongliang Fei | Xu Li | Dingcheng Li | Ping Li
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Recent neural network models have significantly advanced the task of coreference resolution. However, current neural coreference models are usually trained with heuristic loss functions that are computed over a sequence of local decisions. In this paper, we introduce an end-to-end reinforcement learning based coreference resolution model to directly optimize coreference evaluation metrics. Specifically, we modify the state-of-the-art higher-order mention ranking approach in Lee et al. (2018) to a reinforced policy gradient model by incorporating the reward associated with a sequence of coreference linking actions. Furthermore, we introduce maximum entropy regularization for adequate exploration to prevent the model from prematurely converging to a bad local optimum. Our proposed model achieves new state-of-the-art performance on the English OntoNotes v5.0 benchmark.

pdf bib
Integration of Knowledge Graph Embedding Into Topic Modeling with Hierarchical Dirichlet Process
Dingcheng Li | Siamak Zamani | Jingyuan Zhang | Ping Li
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Leveraging domain knowledge is an effective strategy for enhancing the quality of inferred low-dimensional representations of documents by topic models. In this paper, we develop topic modeling with knowledge graph embedding (TMKGE), a Bayesian nonparametric model to employ knowledge graph (KG) embedding in the context of topic modeling, for extracting more coherent topics. Specifically, we build a hierarchical Dirichlet process (HDP) based model to flexibly borrow information from KG to improve the interpretability of topics. An efficient online variational inference method based on a stick-breaking construction of HDP is developed for TMKGE, making TMKGE suitable for large document corpora and KGs. Experiments on three public datasets illustrate the superior performance of TMKGE in terms of topic coherence and document classification accuracy, compared to state-of-the-art topic modeling methods.

2015

pdf bib
Representing Clinical Diagnostic Criteria in Quality Data Model Using Natural Language Processing
Na Hong | Dingcheng Li | Yue Yu | Hongfang Liu | Christopher G. Chute | Guoqian Jiang
Proceedings of BioNLP 15

2011

pdf bib
A Combination of Topic Models with Max-margin Learning for Relation Detection
Dingcheng Li | Swapna Somasundaran | Amit Chakraborty
Proceedings of TextGraphs-6: Graph-based Methods for Natural Language Processing

pdf bib
A Pronoun Anaphora Resolution System based on Factorial Hidden Markov Models
Dingcheng Li | Tim Miller | William Schuler
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

2008

pdf bib
Conditional Random Fields and Support Vector Machines for Disorder Named Entity Recognition in Clinical Texts
Dingcheng Li | Guergana Savova | Karin Kipper-Schuler
Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing