Usage of online textual media is steadily increasing. Daily, more and more news stories, blog posts and scientific articles are added to the online volumes. These are all freely accessible and have been employed extensively in multiple research areas, e.g. automatic text summarization, information retrieval, information extraction, etc. Meanwhile, online debate forums have recently become popular, but have remained largely unexplored. For this reason, there are no sufficient resources of annotated debate data available for conducting research in this genre. In this paper, we collected and annotated debate data for an automatic summarization task. Similar to extractive gold standard summary generation our data contains sentences worthy to include into a summary. Five human annotators performed this task. Inter-annotator agreement, based on semantic similarity, is 36% for Cohen's kappa and 48% for Krippendorff's alpha. Moreover, we also implement an extractive summarization system for online debates and discuss prominent features for the task of summarizing online debate data automatically.
Amazon Web Services（亚马逊云服务）；Columbia University（哥伦比亚大学）
A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The fact that automatic summarization may produce plausible-sounding yet inaccurate summaries is a major concern that limits its wide application. In this paper we present an approach to address factual consistency in summarization. We first propose an efficient automatic evaluation metric to measure factual consistency; next, we propose a novel learning algorithm that maximizes the proposed metric during model training. …
Lister Hill National Center for Biomedical Communications, U.S. National Library of Medicine, National Institutes of Health（美国国立卫生研究院美国国家医学图书馆利斯特希尔生物医学通信中心）
Automatic summarization of natural language is a widely studied area in computer science, one that is broadly applicable to anyone who routinely needs to understand large quantities of information. For example, in the medical domain, recent developments in deep learning approaches to automatic summarization have the potential to make health information more easily accessible to patients and consumers. However, to evaluate the quality of automatically generated summaries of health information, gold-standard, human generated summaries are required. Using answers provided by the National Library …
In this work, we propose a method for incorporating question-answering (QA) signals into a summarization model. Our method identifies salient noun phrases (NPs) in the input document by automatically generating wh-questions that are answered by the NPs and automatically determining whether those questions are answered in the gold summaries. This QA-based signal is incorporated into a two-stage summarization model which first marks salient NPs in the input document using a classification model, then conditionally generates a summary. Our experiments demonstrate that the models trained using QA-…
Evaluation of summarization tasks is extremely crucial to determining the quality of machine generated summaries. Over the last decade, ROUGE has become the standard automatic evaluation measure for evaluating summarization tasks. While ROUGE has been shown to be effective in capturing n-gram overlap between system and human composed summaries, there are several limitations with the existing ROUGE measures in terms of capturing synonymous concepts and coverage of topics. Thus, often times ROUGE scores do not reflect the true quality of summaries and prevents multi-faceted evaluation of summari…
Pohang University of Science and Technology（浦项科技大学）；Microsoft Research Asia（微软亚洲研究院）；Korea Advanced Institute of Science and Technology（韩国科学技术院）
Sentence summarization shortens given texts while maintaining core contents of the texts. Unsupervised approaches have been studied to summarize texts without human-written summaries. However, recent unsupervised models are extractive, which remove words from texts and thus they are less flexible than abstractive summarization. In this work, we devise an abstractive model based on reinforcement learning without ground-truth summaries. We formulate the unsupervised summarization based on the Markov decision process with rewards representing the summary quality. To further enhance the summary qu…
To mitigate the lack of diverse dialogue summarization datasets in academia, we present methods to utilize non-dialogue summarization data for enhancing dialogue summarization systems. We apply transformations to document summarization data pairs to create training data that better befit dialogue summarization. The suggested transformations also retain desirable properties of non-dialogue datasets, such as improved faithfulness to the source text. We conduct extensive experiments across both English and Korean to verify our approach. Although absolute gains in ROUGE naturally plateau as more d…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
The abstractive methods lack of creative ability is particularly a problem in automatic text summarization. The summaries generated by models are mostly extracted from the source articles. One of the main causes for this problem is the lack of dataset with abstractiveness, especially for Chinese. In order to solve this problem, we paraphrase the reference summaries in CLTS, the Chinese Long Text Summarization dataset, correct errors of factual inconsistencies, and propose the first Chinese Long Text Summarization dataset with a high level of abstractiveness, CLTS+, which contains more than 180…
Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries -- which are nearly always in difficult-to-work-with technical domains -- or by using approximate heuristics to extract them from everyday text -- which frequently yields unfaithful summaries. In this work, we turn to a slower but more straightforward approach to developing summarization benchmark data: We hire highly-qualified contractors to read stories and write original summaries from scratch. To amortize reading time, we collect five summaries per document, with the first giving an ov…
In this paper, we present a model for generating summaries of text documents with respect to a query. This is known as query-based summarization. We adapt an existing dataset of news article summaries for the task and train a pointer-generator model using this dataset. The generated summaries are evaluated by measuring similarity to reference summaries. Our results show that a neural network summarization model, similar to existing neural network models for abstractive summarization, can be constructed to make use of queries to produce targeted summaries.
Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre-trained with self-supervised methods. However, ensuring the factual consistency of the generated summaries for abstractive summarization systems is a challenge. We propose a post-editing corrector module to address this issue by identifying and correcting factual errors in generated summaries. The neural corrector model is pre-trained on artificial examples that are created by applying a series of heuristic transformations on reference summaries. These tr…
In text summarization, evaluating the efficacy of automatic metrics without human judgments has become recently popular. One exemplar work concludes that automatic metrics strongly disagree when ranking high-scoring summaries. In this paper, we revisit their experiments and find that their observations stem from the fact that metrics disagree in ranking summaries from any narrow scoring range. We hypothesize that this may be because summaries are similar to each other in a narrow scoring range and are thus, difficult to rank. Apart from the width of the scoring range of summaries, we analyze t…
University of Pittsburgh（匹兹堡大学）；McGill University（麦吉尔大学）；Microsoft Research（微软研究院）
Faceted summarization provides briefings of a document from different perspectives. Readers can quickly comprehend the main points of a long document with the help of a structured outline. However, little research has been conducted on this subject, partially due to the lack of large-scale faceted summarization datasets. In this study, we present FacetSum, a faceted summarization benchmark built on Emerald journal articles, covering a diverse range of domains. Different from traditional document-summary pairs, FacetSum provides multiple summaries, each targeted at specific sections of a long d…
Georgia Institute of Technology（佐治亚理工学院）；Stanford University（斯坦福大学）
Abstractive dialogue summarization has received increasing attention recently. Despite the fact that most of the current dialogue summarization systems are trained to maximize the likelihood of human-written summaries and have achieved significant results, there is still a huge gap in generating high-quality summaries as determined by humans, such as coherence and faithfulness, partly due to the misalignment in maximizing a single human-written summary. To this end, we propose to incorporate different levels of human feedback into the training process. This will enable us to guide the models t…
Carnegie Mellon University（卡内基梅隆大学）；Google Research（谷歌研究院）；University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Abstractive summarization models often generate inconsistent summaries containing factual errors or hallucinated content. Recent works focus on correcting factual errors in generated summaries via post-editing. Such correction models are trained using adversarial non-factual summaries constructed using heuristic rules for injecting errors. However, generating non-factual summaries using heuristics often does not generalize well to actual model errors. In this work, we propose to generate hard, representative synthetic examples of non-factual summaries through infilling language models. With th…
SCURank: Ranking Multiple Candidate Summaries with Summary Content Units for Enhanced Summarization
Department of Computer Science and Information Engineering, National Cheng Kung University（国立成功大学计算机科学与资讯工程系）；Artificial Intelligence Research Center, Chang Gung University（长庚大学人工智能研究中心）；Department of Artificial Intelligence, Chang Gung University（长庚大学人工智能系）；Department of Computer Science, National Tsing Hua University（国立清华大学计算机科学系）
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Microsoft（微软）；NEC Laboratories America（NEC美国实验室）
Text summarization has been a crucial problem in natural language processing (NLP) for several decades. It aims to condense lengthy documents into shorter versions while retaining the most critical information. Various methods have been proposed for text summarization, including extractive and abstractive summarization. The emergence of large language models (LLMs) like GPT3 and ChatGPT has recently created significant interest in using these models for text summarization tasks. Recent studies \cite{goyal2022news, zhang2023benchmarking} have shown that LLMs-generated news summaries are already…
NAVER AI Lab（NAVER人工智能实验室）；University of Richmond（里士满大学）；Seoul National University（首尔国立大学）
Despite the recent advances in abstractive summarization systems, it is still difficult to determine whether a generated summary is factual consistent with the source text. To this end, the latest approach is to train a factual consistency classifier on factually consistent and inconsistent summaries. Luckily, the former is readily available as reference summaries in existing summarization datasets. However, generating the latter remains a challenge, as they need to be factually inconsistent, yet closely relevant to the source text to be effective. In this paper, we propose to generate factual…
Riiid AI Research（Riiid人工智能研究院）；The Hong Kong University of Science and Technology（香港科技大学）
Annotating task-oriented dialogues is notorious for the expensive and difficult data collection process. Few-shot dialogue state tracking (DST) is a realistic solution to this problem. In this paper, we hypothesize that dialogue summaries are essentially unstructured dialogue states; hence, we propose to reformulate dialogue state tracking as a dialogue summarization problem. To elaborate, we train a text-to-text language model with synthetic template-based dialogue summaries, generated by a set of rules from the dialogue states. Then, the dialogue states can be recovered by inversely applying…
Megagon Labs（美乐岗实验室）；University of Edinburgh（爱丁堡大学）
Opinion summarization focuses on generating summaries that reflect popular subjective information expressed in multiple online reviews. While generated summaries offer general and concise information about a particular hotel or product, the information may be insufficient to help the user compare multiple different choices. Thus, the user may still struggle with the question "Which one should I pick?" In this paper, we propose the comparative opinion summarization task, which aims at generating two contrastive summaries and one common summary from two different candidate sets of reviews. We de…
Reference-based metrics such as ROUGE or BERTScore evaluate the content quality of a summary by comparing the summary to a reference. Ideally, this comparison should measure the summary's information quality by calculating how much information the summaries have in common. In this work, we analyze the token alignments used by ROUGE and BERTScore to compare summaries and argue that their scores largely cannot be interpreted as measuring information overlap, but rather the extent to which they discuss the same topics. Further, we provide evidence that this result holds true for many other summar…
A typical product or place often has hundreds of reviews, and summarization of these texts is an important and challenging problem. Recent progress on abstractive summarization in domains such as news has been driven by supervised systems trained on hundreds of thousands of news articles paired with human-written summaries. However for opinion texts, such large scale datasets are rarely available. Unsupervised methods, self-training, and few-shot learning approaches bridge that gap. In this work, we present a novel self-training approach, OpineSum, for abstractive opinion summarization. The su…
We present PeerSum, a new MDS dataset using peer reviews of scientific publications. Our dataset differs from the existing MDS datasets in that our summaries (i.e., the meta-reviews) are highly abstractive and they are real summaries of the source documents (i.e., the reviews) and it also features disagreements among source documents. We found that current state-of-the-art MDS models struggle to generate high-quality summaries for PeerSum, offering new research opportunities.
University of Amsterdam（阿姆斯特丹大学）；Microsoft Research（微软研究院）
Automatic text summarization has experienced substantial progress in recent years. With this progress, the question has arisen whether the types of summaries that are typically generated by automatic summarization models align with users' needs. Ter Hoeve et al (2020) answer this question negatively. Amongst others, they recommend focusing on generating summaries with more graphical elements. This is in line with what we know from the psycholinguistics literature about how humans process text. Motivated from these two angles, we propose a new task: summarization with graphical elements, and we…
This paper provides results of evaluating some text summarisation techniques for the purpose of producing call summaries for contact centre solutions. We specifically focus on extractive summarisation methods, as they do not require any labelled data and are fairly quick and easy to implement for production use. We experimentally compare several such methods by using them to produce summaries of calls, and evaluating these summaries objectively (using ROUGE-L) and subjectively (by aggregating the judgements of several annotators). We found that TopicSum and Lead-N outperform the other summaris…
National Laboratory of Pattern Recognition, Institute of Automation, CAS（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd（中科凡语科技有限公司凡语AI实验室）
Dialogue summarization has drawn much attention recently. Especially in the customer service domain, agents could use dialogue summaries to help boost their works by quickly knowing customer's issues and service progress. These applications require summaries to contain the perspective of a single speaker and have a clear topic flow structure, while neither are available in existing datasets. Therefore, in this paper, we introduce a novel Chinese dataset for Customer Service Dialogue Summarization (CSDS). CSDS improves the abstractive summaries in two aspects: (1) In addition to the overall sum…
University of Amsterdam（阿姆斯特丹大学）；Microsoft Research（微软研究院）
Automatic text summarization has enjoyed great progress over the years and is used in numerous applications, impacting the lives of many. Despite this development, there is little research that meaningfully investigates how the current research focus in automatic summarization aligns with users' needs. To bridge this gap, we propose a survey methodology that can be used to investigate the needs of users of automatically generated summaries. Importantly, these needs are dependent on the target group. Hence, we design our survey in such a way that it can be easily adjusted to investigate differe…
Northeastern University（东北大学）；King’s College London（伦敦国王学院）
We consider the problem of automatically generating a narrative biomedical evidence summary from multiple trial reports. We evaluate modern neural models for abstractive summarization of relevant article abstracts from systematic reviews previously conducted by members of the Cochrane collaboration, using the authors conclusions section of the review abstract as our target. We enlist medical professionals to evaluate generated summaries, and we find that modern summarization systems yield consistently fluent and relevant synopses, but that they are not always factual. We propose new approaches…
The amount of text data available online is increasing at a very fast pace hence text summarization has become essential. Most of the modern recommender and text classification systems require going through a huge amount of data. Manually generating precise and fluent summaries of lengthy articles is a very tiresome and time-consuming task. Hence generating automated summaries for the data and using it to train machine learning models will make these models space and time-efficient. Extractive summarization and abstractive summarization are two separate methods of generating summaries. The ext…
Beijing University of Posts and Telecommunications（北京邮电大学）；Meituan（美团）；China Mobile Communication Corporation（中国移动通信集团公司）
Previous dialogue summarization datasets mainly focus on open-domain chitchat dialogues, while summarization datasets for the broadly used task-oriented dialogue haven't been explored yet. Automatically summarizing such task-oriented dialogues can help a business collect and review needs to improve the service. Besides, previous datasets pay more attention to generate good summaries with higher ROUGE scores, but they hardly understand the structured information of dialogues and ignore the factuality of summaries. In this paper, we introduce a large-scale public Task-Oriented Dialogue Summariza…
Currently, no large-scale training data is available for the task of scientific paper summarization. In this paper, we propose a novel method that automatically generates summaries for scientific papers, by utilizing videos of talks at scientific conferences. We hypothesize that such talks constitute a coherent and concise description of the papers' content, and can form the basis for good summaries. We collected 1716 papers and their corresponding videos, and created a dataset of paper summaries. A model trained on this dataset achieves similar performance as models trained on a dataset of su…
University of Maryland（马里兰大学）；Amazon Web Service AI（亚马逊云服务人工智能）
The records of a clinical encounter can be extensive and complex, thus placing a premium on tools that can extract and summarize relevant information. This paper introduces the task of generating discharge summaries for a clinical encounter. Summaries in this setting need to be faithful, traceable, and scale to multiple long documents, motivating the use of extract-then-abstract summarization cascades. We introduce two new measures, faithfulness and hallucination rate for evaluation in this task, which complement existing measures for fluency and informativeness. Results across seven medical s…
Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning
Graduate School of Artificial Intelligence, POSTECH（浦项科技大学人工智能研究生院）；Department of Computer Science and Engineering, POSTECH（浦项科技大学计算机科学与工程系）；aiXplain Inc.（aiXplain公司）
University of Maryland, College Park（马里兰大学帕克分校）；Microsoft Research（微软研究院）
We construct Global Voices, a multilingual dataset for evaluating cross-lingual summarization methods. We extract social-network descriptions of Global Voices news articles to cheaply collect evaluation data for into-English and from-English summarization in 15 languages. Especially, for the into-English summarization task, we crowd-source a high-quality evaluation dataset based on guidelines that emphasize accuracy, coverage, and understandability. To ensure the quality of this dataset, we collect human ratings to filter out bad summaries, and conduct a survey on humans, which shows that the …
Scientific article summarization is challenging: large, annotated corpora are not available, and the summary should ideally include the article's impacts on research community. This paper provides novel solutions to these two challenges. We 1) develop and release the first large-scale manually-annotated corpus for scientific papers (on computational linguistics) by enabling faster annotation, and 2) propose summarization methods that integrate the authors' original highlights (abstract) and the article's actual impacts on the community (citations), to create comprehensive, hybrid summaries. We…
Université d’Avignon et des Pays de Vaucluse（阿维尼翁与沃克吕兹地区大学）；École Polytechnique de Montréal（蒙特利尔综合理工学院）；Université du Québec à Montréal（魁北克大学蒙特利尔分校）
Cross-Language Text Summarization (CLTS) generates summaries in a language different from the language of the source documents. Recent methods use information from both languages to generate summaries with the most informative sentences. However, these methods have performance that can vary according to languages, which can reduce the quality of summaries. In this paper, we propose a compressive framework to generate cross-language summaries. In order to analyze performance and especially stability, we tested our system and extractive baselines on a dataset available in four languages (English…
