no code implementations • CCL 2022 • Xuanfan Ni, Piji Li
“开放式自动故事生成通过输入故事的开头、大纲、主线等, 得到具有一致性、连贯性和逻辑性的故事。现有的方法想要提升生成故事的质量, 往往需要大量训练数据和更多参数的模型。针对以上问题, 该文利用提示学习在零样本与少样本场景下的优势, 同时使用外部常识推理知识, 提出了一种故事生成方法。该方法将故事生成分为三个阶段:输入故事的开头, 常识推理模型生成可能的事件;根据类型不同, 将事件填入问题模板中, 构建引导模型生成合理回答的问题;问答模型产生对应问题的答案, 并选择困惑度最小的作为故事下文。重复上述过程, 最终生成完整的故事。自动评测与人工评测指标表明, 与基线模型相比, 该文提出的方法能够生成更连贯、具体和合乎逻辑的故事。”
no code implementations • COLING 2022 • Qingyue Wang, Yanan Cao, Piji Li, Yanhe Fu, Zheng Lin, Li Guo
Zero-shot learning for Dialogue State Tracking (DST) focuses on generalizing to an unseen domain without the expense of collecting in domain data.
no code implementations • Findings (ACL) 2022 • Yong Dai, Linyang Li, Cong Zhou, Zhangyin Feng, Enbo Zhao, Xipeng Qiu, Piji Li, Duyu Tang
The meaning of a word in Chinese is different in that a word is a compositional unit consisting of multiple characters.
no code implementations • 8 Apr 2024 • Xuanfan Ni, Hengyi Cai, Xiaochi Wei, Shuaiqiang Wang, Dawei Yin, Piji Li
However, prior benchmarks create datasets that ostensibly cater to long-text comprehension by expanding the input of traditional tasks, which falls short to exhibit the unique characteristics of long-text understanding, including long dependency tasks and longer text length compatible with modern LLMs' context window size.
1 code implementation • 19 Mar 2024 • Xi Wang, Hongliang Dai, Shen Gao, Piji Li
In response to this research gap, we create a benchmark for the characteristic AI agents task, including dataset, techniques, and evaluation metrics.
no code implementations • 4 Mar 2024 • Chen Xu, Tian Lan, Changlong Yu, Wei Wang, Jun Gao, Yu Ji, Qunxi Dong, Kun Qian, Piji Li, Wei Bi, Bin Hu
Lexicon-based constrained decoding approaches aim to control the meaning or style of the generated text through certain target concepts.
no code implementations • 26 Jan 2024 • Xi Wang, Ruoqing Zhao, Hongliang Dai, Piji Li
Chinese Spelling Check (CSC) is a meaningful task in the area of Natural Language Processing (NLP) which aims at detecting spelling errors in Chinese texts and then correcting these errors.
no code implementations • 26 Dec 2023 • Ruoqing Zhao, Xi Wang, Hongliang Dai, Pan Gao, Piji Li
Automated radiology report generation has the potential to improve radiology reporting and alleviate the workload of radiologists.
no code implementations • 26 Dec 2023 • Xuan Sheng, Zhicheng Li, Zhaoyang Han, Xiangmao Chang, Piji Li
Meanwhile, we conduct automatic evaluation and human inspection, which indicate the proposed method possesses good performance of stealthiness without bringing grammatical issues and altering the meaning of sentences.
no code implementations • 18 Dec 2023 • Congchi Yin, Qian Yu, Zhiwei Fang, Jie He, Changping Peng, Zhangang Lin, Jingping Shao, Piji Li
Decoding non-invasive cognitive signals to natural language has long been the goal of building practical brain-computer interfaces (BCIs).
1 code implementation • 18 Oct 2023 • Renzhi Wang, Jing Li, Piji Li
Diffusion models have garnered considerable interest in the field of text generation.
1 code implementation • 24 May 2023 • Chunpu Xu, Jing Li, Piji Li, Min Yang
To allow users to better showcase themselves and network with others, we explore the auto-generation of social media self-introduction, a short sentence outlining a user's personal interests.
no code implementations • 27 Mar 2023 • Xuanfan Ni, Piji Li, Huayang Li
Text structuralization is one of the important fields of natural language processing (NLP) consists of information extraction (IE) and structure formalization.
1 code implementation • 3 Mar 2023 • Shuo Feng, Piji Li
To address this problem, we take advantage of the memorization effects of deep neural networks and a small amount of annotated data to get a model with much knowledge and a little noise, and then we use this model to relabel the ancient Chinese sentences in parallel corpus.
1 code implementation • 2 Mar 2023 • Congchi Yin, Piji Li, Zhaochun Ren
Then we perform clustering to utterance-level representations and form topic-level clusters that can be considered as vertices in dialogue structure graph.
1 code implementation • 26 Feb 2023 • Chunpu Xu, Hanzhuo Tan, Jing Li, Piji Li
To fill in the gap, we present a novel concept of cross-modality discourse, reflecting how human readers couple image and text understandings.
1 code implementation • 11 Dec 2022 • Yougang Lyu, Piji Li, Yechang Yang, Maarten de Rijke, Pengjie Ren, Yukun Zhao, Dawei Yin, Zhaochun Ren
We also propose a dynamic negative sampling strategy to capture the dynamic influence of biases by employing a bias-only model to dynamically select the most similar biased negative samples.
no code implementations • 22 Nov 2022 • Xuan Sheng, Zhaoyang Han, Piji Li, Xiangmao Chang
Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP).
no code implementations • COLING 2022 • Piji Li
The task of Chinese Spelling Check (CSC) is aiming to detect and correct spelling errors that can be found in the text.
no code implementations • 5 Sep 2022 • Yundi Shi, Piji Li, Changchun Yin, Zhaoyang Han, Lu Zhou, Zhe Liu
Therefore, in this paper, we propose a malicious prompt template construction method (\textbf{PromptAttack}) to probe the security performance of PLMs.
no code implementations • 3 Aug 2022 • Shuming Shi, Enbo Zhao, Duyu Tang, Yan Wang, Piji Li, Wei Bi, Haiyun Jiang, Guoping Huang, Leyang Cui, Xinting Huang, Cong Zhou, Yong Dai, Dongyang Ma
In Effidit, we significantly expand the capacities of a writing assistant by providing functions in five categories: text completion, error checking, text polishing, keywords to sentences (K2S), and cloud input methods (cloud IME).
1 code implementation • 2 May 2022 • Chen Xu, Piji Li, Wei Wang, Haoran Yang, Siyun Wang, Chuangbai Xiao
In this work, we propose COSPLAY(COncept Set guided PersonaLized dialogue generation Across both partY personas) that considers both parties as a "team": expressing self-persona while keeping curiosity toward the partner, leading responses around mutual personas, and finding the common ground.
1 code implementation • Findings (ACL) 2022 • Qintong Li, Piji Li, Wei Bi, Zhaochun Ren, Yuxuan Lai, Lingpeng Kong
Open-ended text generation tasks, such as dialogue generation and story completion, require models to generate a coherent continuation given limited preceding context.
no code implementations • 10 Apr 2022 • Haoran Yang, Piji Li, Wai Lam
Continuous prompt tuning which prepends a few trainable vectors to the embeddings of input is one of these methods and has drawn much attention due to its effectiveness and efficiency.
no code implementations • 1 Mar 2022 • Yong Dai, Linyang Li, Cong Zhou, Zhangyin Feng, Enbo Zhao, Xipeng Qiu, Piji Li, Duyu Tang
The meaning of a word in Chinese is different in that a word is a compositional unit consisting of multiple characters.
1 code implementation • Findings (EMNLP) 2021 • Haoran Yang, Wai Lam, Piji Li
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence.
no code implementations • 6 Aug 2021 • Wei Wang, Piji Li, Hai-Tao Zheng
In the phase of surface realization, a mixed-granularity sentence decoder is designed to generate text with better consistency by jointly incorporating the predicted sentence-level main idea as well as the preceding contextual token-level information.
1 code implementation • 3 Aug 2021 • Wang Chen, Piji Li, Hou Pong Chan, Irwin King
The supporting utterance flow modeling helps to generate a coherent summary by smoothly shifting the focus from the former utterances to the later ones.
1 code implementation • ACL 2021 • Dong Wang, Ning Ding, Piji Li, Hai-Tao Zheng
Recent works aimed to improve the robustness of pre-trained models mainly focus on adversarial training from perturbed examples with similar semantics, neglecting the utilization of different or even opposite semantics.
1 code implementation • ACL 2021 • Wang Chen, Piji Li, Irwin King
Our metric consists of a centrality-weighted relevance score and a self-referenced redundancy score.
1 code implementation • ACL 2021 • Piji Li, Shuming Shi
We investigate the problem of Chinese Grammatical Error Correction (CGEC) and present a new framework named Tail-to-Tail (\textbf{TtT}) non-autoregressive sequence prediction to address the deep issues hidden in CGEC.
1 code implementation • EACL 2021 • Yixuan Su, Deng Cai, Yan Wang, David Vandyke, Simon Baker, Piji Li, Nigel Collier
In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance.
no code implementations • 13 Feb 2021 • Wei Wang, Piji Li, Hai-Tao Zheng
Automatic comment generation is a special and challenging task to verify the model ability on news content comprehension and language generation.
1 code implementation • 18 Jan 2021 • Qintong Li, Piji Li, Xinyi Li, Zhaochun Ren, Zhumin Chen, Maarten de Rijke
In this paper, we propose the abstractive opinion tagging task, where systems have to automatically generate a ranked list of opinion tags that are based on, but need not occur in, a given set of user-generated reviews.
no code implementations • 17 Dec 2020 • Zelong Yang, Yan Wang, Piji Li, Shaobin Lin, Shuming Shi, Shao-Lun Huang, Wei Bi
The multiplayer online battle arena (MOBA) games have become increasingly popular in recent years.
no code implementations • 17 Oct 2020 • Wei Wang, Piji Li, Hai-Tao Zheng
In terms of consistency, on one hand, GPT2 cannot guarantee the consistency of the plots explicitly.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Yifan Gao, Piji Li, Wei Bi, Xiaojiang Liu, Michael R. Lyu, Irwin King
Besides a small number of high-resource sentence functions, a large portion of sentence functions is infrequent.
1 code implementation • 21 Sep 2020 • Qintong Li, Piji Li, Zhaochun Ren, Pengjie Ren, Zhumin Chen
Finally, to generate the empathetic response, we propose an emotional cross-attention mechanism to learn the emotional dependencies from the emotional context graph.
no code implementations • 19 Sep 2020 • Xin Li, Piji Li, Yan Wang, Xiaojiang Liu, Wai Lam
Most of the existing works for dialogue generation are data-driven models trained directly on corpora crawled from websites.
1 code implementation • ACL 2020 • Wang Chen, Hou Pong Chan, Piji Li, Irwin King
A new setting is recently introduced into this problem, in which, given a document, the model needs to predict a set of keyphrases and simultaneously determine the appropriate number of keyphrases to produce.
1 code implementation • ACL 2020 • Piji Li, Haisong Zhang, Xiaojiang Liu, Shuming Shi
(3) Although they are restricted to some formats, the sentence integrity must be guaranteed.
no code implementations • 7 Apr 2020 • Piji Li, Lidong Bing, Zhongyu Wei, Wai Lam
Different from neural machine translation, in the task of text summarization, salience estimation for words, phrases or sentences is a critical component, since the output summary is a distillation of the input text.
no code implementations • The Thirty-Fourth AAAI Conference on Artificial Intelligence 2020 • Ruize Wang, Zhongyu Wei, Piji Li, Qi Zhang, Xuanjing Huang
In particular, on the within-image level, we employ a Graph Convolution Network (GCN) to enrich local fine-grained region representations of objects on scene graphs.
Ranked #7 on Visual Storytelling on VIST
1 code implementation • 9 Mar 2020 • Piji Li
A weighted joint prediction paradigm for both context and response is designed to evaluate the performance of models with or without the loss term for context prediction.
2 code implementations • 6 Feb 2020 • Minghong Xu, Piji Li, Haoran Yang, Pengjie Ren, Zhaochun Ren, Zhumin Chen, Jun Ma
To address this, we propose a neural topical expansion framework, namely Persona Exploration and Exploitation (PEE), which is able to extend the predefined user persona description with semantically correlated content before utilizing them to generate dialogue responses.
no code implementations • 26 Nov 2019 • Xin Li, Piji Li, Wei Bi, Xiaojiang Liu, Wai Lam
In this paper, we propose to formulate the STC task as a language modeling problem and tailor-make a training strategy to adapt a language model for response generation.
no code implementations • COLING 2020 • Ruize Wang, Zhongyu Wei, Ying Cheng, Piji Li, Haijun Shan, Ji Zhang, Qi Zhang, Xuanjing Huang
Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically.
Ranked #9 on Visual Storytelling on VIST
no code implementations • IJCNLP 2019 • Mingyue Shang, Piji Li, Zhenxin Fu, Lidong Bing, Dongyan Zhao, Shuming Shi, Rui Yan
Text style transfer task requires the model to transfer a sentence of one style to another style while retaining its original content meaning, which is a challenging problem that has long suffered from the shortage of parallel data.
1 code implementation • IJCNLP 2019 • Zihao Wang, Kwun Ping Lai, Piji Li, Lidong Bing, Wai Lam
Therefore, we propose a meta-learning framework that aims at handling infrequent relations with few-shot learning and uncommon entities by using textual descriptions.
1 code implementation • IJCNLP 2019 • Shen Gao, Xiuying Chen, Piji Li, Zhangming Chan, Dongyan Zhao, Rui Yan
There are two main challenges in this task: (1) the model needs to incorporate learned patterns from the prototype, but (2) should avoid copying contents other than the patternized words---such as irrelevant facts---into the generated summaries.
1 code implementation • ACL 2019 • Yifan Gao, Piji Li, Irwin King, Michael R. Lyu
The coreference alignment modeling explicitly aligns coreferent mentions in conversation history with corresponding pronominal references in generated questions, which makes generated questions interconnected to conversation history.
1 code implementation • NAACL 2019 • Wang Chen, Hou Pong Chan, Piji Li, Lidong Bing, Irwin King
For further exploiting the power of extraction and retrieval, we propose a neural-based merging module to combine and re-rank the predicted keyphrases from the enhanced generative model, the extractive model, and the retrieved keyphrases.
no code implementations • 6 Mar 2019 • Piji Li, ZiHao Wang, Lidong Bing, Wai Lam
In order to exploit the persona information, we propose a framework based on adversarial variational auto-encoders (aVAE) for persona modeling from the historical tips and reviews of users and items.
no code implementations • 13 Dec 2018 • Shen Gao, Xiuying Chen, Piji Li, Zhaochun Ren, Lidong Bing, Dongyan Zhao, Rui Yan
To tackle this problem, we propose the task of reader-aware abstractive summary generation, which utilizes the reader comments to help the model produce better summary about the main aspect.
Ranked #1 on Reader-Aware Summarization on RASG
1 code implementation • 13 Nov 2018 • Xin Li, Lidong Bing, Piji Li, Wai Lam
Target-based sentiment analysis involves opinion target extraction and target sentiment classification.
Aspect-Based Sentiment Analysis (ABSA) Sentiment Classification
1 code implementation • EMNLP 2018 • Yi Liao, Lidong Bing, Piji Li, Shuming Shi, Wai Lam, Tong Zhang
For example, an input sequence could be a word sequence, such as review sentence and advertisement text.
2 code implementations • 8 Sep 2018 • Yifan Gao, Lidong Bing, Piji Li, Irwin King, Michael R. Lyu
We investigate the task of distractor generation for multiple choice reading comprehension questions from examinations.
1 code implementation • 2 May 2018 • Xin Li, Lidong Bing, Piji Li, Wai Lam, Zhimou Yang
Aspect Term Extraction (ATE), a key sub-task in Aspect-Based Sentiment Analysis, aims to extract explicit aspect expressions from online user reviews.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • EMNLP 2018 • Yi Liao, Lidong Bing, Piji Li, Shuming Shi, Wai Lam, Tong Zhang
For example, an input sequence could be a word sequence, such as review sentence and advertisement text.
no code implementations • 28 Mar 2018 • Piji Li, Lidong Bing, Wai Lam
For the critic, we combine the maximum likelihood estimator with a well designed global summary quality estimator which is a neural network based binary classifier aiming to make the generated summaries indistinguishable from the human-written ones.
no code implementations • EMNLP 2017 • Piji Li, Wai Lam, Lidong Bing, Weiwei Guo, Hang Li
The attention weights are learned automatically by an unsupervised data reconstruction framework which can capture the sentence salience.
no code implementations • WS 2017 • Piji Li, Lidong Bing, Wai Lam
We investigate the problem of reader-aware multi-document summarization (RA-MDS) and introduce a new dataset for this problem.
1 code implementation • EMNLP 2017 • Piji Li, Wai Lam, Lidong Bing, ZiHao Wang
We propose a new framework for abstractive text summarization based on a sequence-to-sequence oriented encoder-decoder model equipped with a deep recurrent generative decoder (DRGN).
Ranked #5 on Text Summarization on DUC 2004 Task 1
no code implementations • 1 Aug 2017 • Piji Li, ZiHao Wang, Zhaochun Ren, Lidong Bing, Wai Lam
In essence, writing some tips and giving a numerical rating are two facets of a user's product assessment action, expressing the user experience and feelings.
no code implementations • IJCNLP 2015 • Lidong Bing, Piji Li, Yi Liao, Wai Lam, Weiwei Guo, Rebecca J. Passonneau
We propose an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases.
no code implementations • 28 Apr 2015 • Piji Li, Lidong Bing, Wai Lam, Hang Li, Yi Liao
We propose a new MDS paradigm called reader-aware multi-document summarization (RA-MDS).