Xiuying Chen


2024

pdf bib
IAD: In-Context Learning Ability Decoupler of Large Language Models in Meta-Training
Yuhan Liu | Xiuying Chen | Gao Xing | Ji Zhang | Rui Yan
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Large Language Models (LLMs) exhibit remarkable In-Context Learning (ICL) ability, where the model learns tasks from prompts consisting of input-output examples. However, the pre-training objectives of LLMs often misalign with ICL objectives. They’re mainly pre-trained with methods like masked language modeling and next-sentence prediction. On the other hand, ICL leverages example pairs to guide the model in generating task-aware responses such as text classification and question-answering tasks. The basic pre-training task-related capabilities can sometimes overshadow or conflict with task-specific subtleties required in ICL. To address this, we propose an In-context learning Ability Decoupler (IAD). The model aims to separate the ICL ability from the general ability of LLMs in the meta-training phase, where the ICL-related parameters are separately tuned to adapt for ICL tasks. Concretely, we first identify the parameters that are suitable for ICL by transference-driven gradient importance. We then propose a new max-margin loss to emphasize the separation of the general and ICL abilities. The loss is defined as the difference between the output of ICL and the original LLM, aiming to prevent the overconfidence of the LLM. By meta-training these ICL-related parameters with max-margin loss, we enable the model to learn and adapt to new tasks with limited data effectively. Experimental results show that IAD’s capability yields state-of-the-art performance on benchmark datasets by utilizing only 30% of the model’s parameters. Ablation study and detailed analysis prove the separation of the two abilities.

2023

pdf bib
Improving the Robustness of Summarization Systems with Dual Augmentation
Xiuying Chen | Guodong Long | Chongyang Tao | Mingzhe Li | Xin Gao | Chengqi Zhang | Xiangliang Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. In this work, we first explore the summarization models’ robustness against perturbations including word-level synonym substitution and noise. To create semantic-consistent substitutes, we propose a SummAttacker, which is an efficient approach to generating adversarial samples based on pre-trained language models. Experimental results show that state-of-the-art summarization models have a significant decrease in performance on adversarial and noisy test sets. Next, we analyze the vulnerability of the summarization systems and explore improving the robustness by data augmentation. Specifically, the first vulnerability factor we found is the low diversity of the training inputs. Correspondingly, we expose the encoder to more diverse cases created by SummAttacker in the input space. The second factor is the vulnerability of the decoder, and we propose an augmentation in the latent space of the decoder to improve its robustness. Concretely, we create virtual cases by manifold softmixing two decoder hidden states of similar semantic meanings. Experimental results on Gigaword and CNN/DM datasets demonstrate that our approach achieves significant improvements over strong baselines and exhibits higher robustness on noisy, attacked, and clean datasets

pdf bib
Dialogue Summarization with Static-Dynamic Structure Fusion Graph
Shen Gao | Xin Cheng | Mingzhe Li | Xiuying Chen | Jinpeng Li | Dongyan Zhao | Rui Yan
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Dialogue, the most fundamental and specially privileged arena of language, gains increasing ubiquity across the Web in recent years. Quickly going through the long dialogue context and capturing salient information scattered over the whole dialogue session benefit users in many real-world Web applications such as email thread summarization and meeting minutes draft. Dialogue summarization is a challenging task in that dialogue has dynamic interaction nature and presumably inconsistent information flow among various speakers. Many researchers address this task by modeling dialogue with pre-computed static graph structure using external linguistic toolkits. However, such methods heavily depend on the reliability of external tools and the static graph construction is disjoint with the graph representation learning phase, which makes the graph can’t be dynamically adapted for the downstream summarization task. In this paper, we propose a Static-Dynamic graph-based Dialogue Summarization model (SDDS), which fuses prior knowledge from human expertise and adaptively learns the graph structure in an end-to-end learning fashion. To verify the effectiveness of SDDS, we conduct experiments on three benchmark datasets (SAMSum, MediaSum, and DialogSum) and the results verify the superiority of SDDS.

pdf bib
UMSE: Unified Multi-scenario Summarization Evaluation
Shen Gao | Zhitao Yao | Chongyang Tao | Xiuying Chen | Pengjie Ren | Zhaochun Ren | Zhumin Chen
Findings of the Association for Computational Linguistics: ACL 2023

Summarization quality evaluation is a non-trivial task in text summarization. Contemporary methods can be mainly categorized into two scenarios: (1) reference-based: evaluating with human-labeled reference summary; (2) reference-free: evaluating the summary consistency of the document. Recent studies mainly focus on one of these scenarios and explore training neural models built on PLMs to align with human criteria. However, the models from different scenarios are optimized individually, which may result in sub-optimal performance since they neglect the shared knowledge across different scenarios. Besides, designing individual models for each scenario caused inconvenience to the user. Inspired by this, we propose Unified Multi-scenario Summarization Evaluation Model (UMSE). More specifically, we propose a perturbed prefix tuning method to share cross-scenario knowledge between scenarios and use a self-supervised training paradigm to optimize the model without extra human labeling. Our UMSE is the first unified summarization evaluation framework engaged with the ability to be used in three evaluation scenarios. Experimental results across three typical scenarios on the benchmark dataset SummEval indicate that our UMSE can achieve comparable performance with several existing strong methods which are specifically designed for each scenario.

pdf bib
Decouple knowledge from paramters for plug-and-play language modeling
Xin Cheng | Yankai Lin | Xiuying Chen | Dongyan Zhao | Rui Yan
Findings of the Association for Computational Linguistics: ACL 2023

Pre-trained language models (PLM) have made impressive results in a wide range of NLP tasks and it has been revealed that one of the key factors to their success is the parameters of these models implicitly learn various types of knowledge in the pre-training corpus. However, encoding knowledge implicitly in the model parameters has two fundamental drawbacks. First, the knowledge is neither editable nor scalable once the model is trained, which is especially problematic in that knowledge is consistently evolving. Second, it lacks interpretability and prevents us from understanding what kind of knowledge PLM needs to solve a certain task. In this paper, we introduce {pasted macro ‘MODEL’}, a pre-training model with differentiable plug-in memory (DPM). The key intuition behind is to decouple the knowledge storage from model parameters with an editable and scalable key-value memory and leverage knowledge in an explainable manner by knowledge retrieval in the {pasted macro ‘MEMORY’}. We conduct extensive experiments under various settings to justify this design choice. In domain adaptation setting, {pasted macro ‘MODEL’} could be easily adapted to different domains with pluggable in-domain memory—obtaining 3.95 F1 improvements across four domains, without any in-domain training. {pasted macro ‘MODEL’} could also keep absorbing new knowledge after pre-training is done by knowledge updating operation in the {pasted macro ‘MEMORY’} without re-training. Finally, we show that by incorporating training samples into {pasted macro ‘MEMORY’} with knowledge prompting, {pasted macro ‘MODEL’} could further be improved by the instruction of in-task knowledge.

pdf bib
Towards a Unified Framework for Reference Retrieval and Related Work Generation
Zhengliang Shi | Shen Gao | Zhen Zhang | Xiuying Chen | Zhumin Chen | Pengjie Ren | Zhaochun Ren
Findings of the Association for Computational Linguistics: EMNLP 2023

The task of related work generation aims to generate a comprehensive survey of related research topics automatically, saving time and effort for authors. Existing methods simplify this task by using human-annotated references in a large-scale scientific corpus as information sources, which is time- and cost-intensive. To this end, we propose a Unified Reference Retrieval and Related Work Generation Model (UR3WG), which combines reference retrieval and related work generation processes in a unified framework based on the large language model (LLM). Specifically, UR3WG first leverages the world knowledge of LLM to extend the abstract and generate the query for the subsequent retrieval stage. Then a lexicon-enhanced dense retrieval is proposed to search relevant references, where an importance-aware representation of the lexicon is introduced. We also propose multi-granularity contrastive learning to optimize our retriever. Since this task is not simply summarizing the main points in references, it should analyze the complex relationships and present them logically. We propose an instruction-tuning method to leverage LLM to generate related work. Extensive experiments on two wide-applied datasets demonstrate that our model outperforms the state-of-the-art baselines in both generation and retrieval metrics.

pdf bib
Stylized Dialogue Generation with Feature-Guided Knowledge Augmentation
Jinpeng Li | Zekai Zhang | Xiuying Chen | Dongyan Zhao | Rui Yan
Findings of the Association for Computational Linguistics: EMNLP 2023

Stylized dialogue generation systems aim to produce coherent and context-aware dialogues while effectively emulating the desired style. Generating stylized dialogue is valuable yet challenging due to the scarce parallel data. Existing methods often synthesize pseudo data through back translation, yet suffer from noisy and context-agnostic style signals caused by insufficient guidance on target style features. To address this, we propose the knowledge-augmented stylized dialogue generation model, which includes a feature-guided style knowledge selection module that utilizes context and response features. Specifically, we retrieve dialogue-related style sentences from style corpus to explicitly provide clear style signals. We design a feature-guided selection module with response-related contrastive learning and style responsiveness Kullback-Leibler losses to enhance generation at both semantic and stylized levels. Our approach demonstrates satisfactory performance on two public stylized dialogue benchmarks in both automatic and human evaluations.

2022

pdf bib
Unsupervised Mitigating Gender Bias by Character Components: A Case Study of Chinese Word Embedding
Xiuying Chen | Mingzhe Li | Rui Yan | Xin Gao | Xiangliang Zhang
Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)

Word embeddings learned from massive text collections have demonstrated significant levels of discriminative biases. However, debias on the Chinese language, one of the most spoken languages, has been less explored. Meanwhile, existing literature relies on manually created supplementary data, which is time- and energy-consuming. In this work, we propose the first Chinese Gender-neutral word Embedding model (CGE) based on Word2vec, which learns gender-neutral word embeddings without any labeled data. Concretely, CGE utilizes and emphasizes the rich feminine and masculine information contained in radicals, i.e., a kind of component in Chinese characters, during the training procedure. This consequently alleviates discriminative gender biases. Experimental results on public benchmark datasets show that our unsupervised method outperforms the state-of-the-art supervised debiased word embedding models without sacrificing the functionality of the embedding model.

pdf bib
Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation
Mingzhe Li | XieXiong Lin | Xiuying Chen | Jinxiong Chang | Qishen Zhang | Feng Wang | Taifeng Wang | Zhongyi Liu | Wei Chu | Dongyan Zhao | Rui Yan
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Contrastive learning has achieved impressive success in generation tasks to militate the “exposure bias” problem and discriminatively exploit the different quality of references. Existing works mostly focus on contrastive learning on the instance-level without discriminating the contribution of each word, while keywords are the gist of the text and dominant the constrained mapping relationships. Hence, in this work, we propose a hierarchical contrastive learning mechanism, which can unify hybrid granularities semantic meaning in the input text. Concretely, we first propose a keyword graph via contrastive correlations of positive-negative pairs to iteratively polish the keyword representations. Then, we construct intra-contrasts within instance-level and keyword-level, where we assume words are sampled nodes from a sentence distribution. Finally, to bridge the gap between independent contrast levels and tackle the common contrast vanishing problem, we propose an inter-contrast mechanism that measures the discrepancy between contrastive keyword nodes respectively to the instance distribution. Experiments demonstrate that our model outperforms competitive baselines on paraphrasing, dialogue generation, and storytelling tasks.

pdf bib
Scientific Paper Extractive Summarization Enhanced by Citation Graphs
Xiuying Chen | Mingzhe Li | Shen Gao | Rui Yan | Xin Gao | Xiangliang Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

In a citation graph, adjacent paper nodes share related scientific terms and topics. The graph thus conveys unique structure information of document-level relatedness that can be utilized in the paper summarization task, for exploring beyond the intra-document information.In this work, we focus on leveraging citation graphs to improve scientific paper extractive summarization under different settings.We first propose a Multi-granularity Unsupervised Summarization model (MUS) as a simple and low-cost solution to the task.MUS finetunes a pre-trained encoder model on the citation graph by link prediction tasks.Then, the abstract sentences are extracted from the corresponding paper considering multi-granularity information.Preliminary results demonstrate that citation graph is helpful even in a simple unsupervised framework.Motivated by this, we next propose a Graph-based Supervised Summarizationmodel (GSS) to achieve more accurate results on the task when large-scale labeled data are available.Apart from employing the link prediction as an auxiliary task, GSS introduces a gated sentence encoder and a graph information fusion module to take advantage of the graph information to polish the sentence representation.Experiments on a public benchmark dataset show that MUS and GSS bring substantial improvements over the prior state-of-the-art model.

pdf bib
Summarizing Procedural Text: Data and Approach
Shen Gao | Haotong Zhang | Xiuying Chen | Rui Yan | Dongyan Zhao
Findings of the Association for Computational Linguistics: EMNLP 2022

Procedural text is a widely used genre that contains many steps of instructions of how to cook a dish or how to conduct a chemical experiment and analyze the procedural text has become a popular task in the NLP field. Since the procedural text can be very long and contains many details, summarizing the whole procedural text or giving an overview for each complicated procedure step can save time for readers and help them to capture the core information in the text. In this paper, we propose the procedural text summarization task with two summarization granularity: step-view and global-view, which summarizes each step in the procedural text separately or gives an overall summary for all steps respectively. To tackle this task, we propose an Entity-State Graph-based Summarizer (ESGS) which is based on state-of-the-art entity state tracking methods and constructs a heterogeneous graph to aggregate contextual information for each procedure. In order to help the summarization model focus on the salient entities, we propose to use the contextualized procedure graph representation to predict the salient entities. Experiments conducted on two datasets verify the effectiveness of our proposed model. Our code and datasets will be released on https://github.com/gsh199449/procedural-summ.

2021

pdf bib
Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation
Xiuying Chen | Hind Alamro | Mingzhe Li | Shen Gao | Xiangliang Zhang | Dongyan Zhao | Rui Yan
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Given a set of related publications, related work section generation aims to provide researchers with an overview of the specific research area by summarizing these works and introducing them in a logical order. Most of existing related work generation models follow the inflexible extractive style, which directly extract sentences from multiple original papers to form a related work discussion. Hence, in this paper, we propose a Relation-aware Related work Generator (RRG), which generates an abstractive related work from the given multiple scientific papers in the same research area. Concretely, we propose a relation-aware multi-document encoder that relates one document to another according to their content dependency in a relation graph. The relation graph and the document representation are interacted and polished iteratively, complementing each other in the training process. We also contribute two public datasets composed of related work sections and their corresponding papers. Extensive experiments on the two datasets show that the proposed model brings substantial improvements over several strong baselines. We hope that this work will promote advances in related work generation task.

pdf bib
BioGen: Generating Biography Summary under Table Guidance on Wikipedia
Shen Gao | Xiuying Chen | Chang Liu | Dongyan Zhao | Rui Yan
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
Combining Curriculum Learning and Knowledge Distillation for Dialogue Generation
Qingqing Zhu | Xiuying Chen | Pengfei Wu | JunFei Liu | Dongyan Zhao
Findings of the Association for Computational Linguistics: EMNLP 2021

Curriculum learning, a machine training strategy that feeds training instances to the model from easy to hard, has been proven to facilitate the dialogue generation task. Meanwhile, knowledge distillation, a knowledge transformation methodology among teachers and students networks can yield significant performance boost for student models. Hence, in this paper, we introduce a combination of curriculum learning and knowledge distillation for efficient dialogue generation models, where curriculum learning can help knowledge distillation from data and model aspects. To start with, from the data aspect, we cluster the training cases according to their complexity, which is calculated by various types of features such as sentence length and coherence between dialog pairs. Furthermore, we employ an adversarial training strategy to identify the complexity of cases from model level. The intuition is that, if a discriminator can tell the generated response is from the teacher or the student, then the case is difficult that the student model has not adapted to yet. Finally, we use self-paced learning, which is an extension to curriculum learning to assign weights for distillation. In conclusion, we arrange a hierarchical curriculum based on the above two aspects for the student model under the guidance from the teacher model. Experimental results demonstrate that our methods achieve improvements compared with competitive baselines.

2020

pdf bib
Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism
Pan Xie | Zhi Cui | Xiuying Chen | XiaoHui Hu | Jianwei Cui | Bin Wang
Proceedings of the 28th International Conference on Computational Linguistics

Non-autoregressive models generate target words in a parallel way, which achieve a faster decoding speed but at the sacrifice of translation accuracy. To remedy a flawed translation by non-autoregressive models, a promising approach is to train a conditional masked translation model (CMTM), and refine the generated results within several iterations. Unfortunately, such approach hardly considers the sequential dependency among target words, which inevitably results in a translation degradation. Hence, instead of solely training a Transformer-based CMTM, we propose a Self-Review Mechanism to infuse sequential information into it. Concretely, we insert a left-to-right mask to the same decoder of CMTM, and then induce it to autoregressively review whether each generated word from CMTM is supposed to be replaced or kept. The experimental results (WMT14 En ↔ De and WMT16 En ↔ Ro) demonstrate that our model uses dramatically less training computations than the typical CMTM, as well as outperforms several state-of-the-art non-autoregressive models by over 1 BLEU. Through knowledge distillation, our model even surpasses a typical left-to-right Transformer model, while significantly speeding up decoding.

pdf bib
Selection and Generation: Learning towards Multi-Product Advertisement Post Generation
Zhangming Chan | Yuchi Zhang | Xiuying Chen | Shen Gao | Zhiqiang Zhang | Dongyan Zhao | Rui Yan
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

As the E-commerce thrives, high-quality online advertising copywriting has attracted more and more attention. Different from the advertising copywriting for a single product, an advertisement (AD) post includes an attractive topic that meets the customer needs and description copywriting about several products under its topic. A good AD post can highlight the characteristics of each product, thus helps customers make a good choice among candidate products. Hence, multi-product AD post generation is meaningful and important. We propose a novel end-to-end model named S-MG Net to generate the AD post. Targeted at such a challenging real-world problem, we split the AD post generation task into two subprocesses: (1) select a set of products via the SelectNet (Selection Network). (2) generate a post including selected products via the MGenNet (Multi-Generator Network). Concretely, SelectNet first captures the post topic and the relationship among the products to output the representative products. Then, MGenNet generates the description copywriting of each product. Experiments conducted on a large-scale real-world AD post dataset demonstrate that our proposed model achieves impressive performance in terms of both automatic metrics as well as human evaluations.

pdf bib
VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles
Mingzhe Li | Xiuying Chen | Shen Gao | Zhangming Chan | Dongyan Zhao | Rui Yan
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

A popular multimedia news format nowadays is providing users with a lively video and a corresponding news article, which is employed by influential news media including CNN, BBC, and social media including Twitter and Weibo. In such a case, automatically choosing a proper cover frame of the video and generating an appropriate textual summary of the article can help editors save time, and readers make the decision more effectively. Hence, in this paper, we propose the task of Video-based Multimodal Summarization with Multimodal Output (VMSMO) to tackle such a problem. The main challenge in this task is to jointly model the temporal dependency of video with semantic meaning of article. To this end, we propose a Dual-Interaction-based Multimodal Summarizer (DIMS), consisting of a dual interaction module and multimodal generator. In the dual interaction module, we propose a conditional self-attention mechanism that captures local semantic information within video and a global-attention mechanism that handles the semantic relationship between news text and video from a high level. Extensive experiments conducted on a large-scale real-world VMSMO dataset show that DIMS achieves the state-of-the-art performance in terms of both automatic metrics and human evaluations.

2019

pdf bib
Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders
Zhangming Chan | Juntao Li | Xiaopeng Yang | Xiuying Chen | Wenpeng Hu | Dongyan Zhao | Rui Yan
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Variational autoencoders (VAEs) and Wasserstein autoencoders (WAEs) have achieved noticeable progress in open-domain response generation. Through introducing latent variables in continuous space, these models are capable of capturing utterance-level semantics, e.g., topic, syntactic properties, and thus can generate informative and diversified responses. In this work, we improve the WAE for response generation. In addition to the utterance-level information, we also model user-level information in latent continue space. Specifically, we embed user-level and utterance-level information into two multimodal distributions, and combine these two multimodal distributions into a mixed distribution. This mixed distribution will be used as the prior distribution of WAE in our proposed model, named as PersonaWAE. Experimental results on a large-scale real-world dataset confirm the superiority of our model for generating informative and personalized responses, where both automatic and human evaluations outperform state-of-the-art models.

pdf bib
How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing
Shen Gao | Xiuying Chen | Piji Li | Zhangming Chan | Dongyan Zhao | Rui Yan
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Under special circumstances, summaries should conform to a particular style with patterns, such as court judgments and abstracts in academic papers. To this end, the prototype document-summary pairs can be utilized to generate better summaries. 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. To tackle these challenges, we design a model named Prototype Editing based Summary Generator (PESG). PESG first learns summary patterns and prototype facts by analyzing the correlation between a prototype document and its summary. Prototype facts are then utilized to help extract facts from the input document. Next, an editing generator generates new summary based on the summary pattern or extracted facts. Finally, to address the second challenge, a fact checker is used to estimate mutual information between the input document and generated summary, providing an additional signal for the generator. Extensive experiments conducted on a large-scale real-world text summarization dataset show that PESG achieves the state-of-the-art performance in terms of both automatic metrics and human evaluations.

pdf bib
Stick to the Facts: Learning towards a Fidelity-oriented E-Commerce Product Description Generation
Zhangming Chan | Xiuying Chen | Yongliang Wang | Juntao Li | Zhiqiang Zhang | Kun Gai | Dongyan Zhao | Rui Yan
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Different from other text generation tasks, in product description generation, it is of vital importance to generate faithful descriptions that stick to the product attribute information. However, little attention has been paid to this problem. To bridge this gap we propose a model named Fidelity-oriented Product Description Generator (FPDG). FPDG takes the entity label of each word into account, since the product attribute information is always conveyed by entity words. Specifically, we first propose a Recurrent Neural Network (RNN) decoder based on the Entity-label-guided Long Short-Term Memory (ELSTM) cell, taking both the embedding and the entity label of each word as input. Second, we establish a keyword memory that stores the entity labels as keys and keywords as values, and FPDG will attend to keywords through attending to their entity labels. Experiments conducted a large-scale real-world product description dataset show that our model achieves the state-of-the-art performance in terms of both traditional generation metrics as well as human evaluations. Specifically, FPDG increases the fidelity of the generated descriptions by 25%.

2018

pdf bib
Iterative Document Representation Learning Towards Summarization with Polishing
Xiuying Chen | Shen Gao | Chongyang Tao | Yan Song | Dongyan Zhao | Rui Yan
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

In this paper, we introduce Iterative Text Summarization (ITS), an iteration-based model for supervised extractive text summarization, inspired by the observation that it is often necessary for a human to read an article multiple times in order to fully understand and summarize its contents. Current summarization approaches read through a document only once to generate a document representation, resulting in a sub-optimal representation. To address this issue we introduce a model which iteratively polishes the document representation on many passes through the document. As part of our model, we also introduce a selective reading mechanism that decides more accurately the extent to which each sentence in the model should be updated. Experimental results on the CNN/DailyMail and DUC2002 datasets demonstrate that our model significantly outperforms state-of-the-art extractive systems when evaluated by machines and by humans.