In recent years, the task of Question Answering over passages, also pitched as a reading comprehension, has evolved into a very active research area. A reading comprehension system extracts a span of text, comprising of named entities, dates, small phrases, etc., which serve as the answer to a given question. However, these spans of text would result in an unnatural reading experience in a conversational system. Usually, dialogue systems solve this issue by using template-based language generation. These systems, though adequate for a domain specific task, are too restrictive and predefined for a domain independent system. In order to present the user with a more conversational experience, we propose a pointer generator based full-length answer generator which can be used with most QA systems. Our system generates a full length answer given a question and the extracted factoid/span answer without relying on the passage from where the answer was extracted. We also present a dataset of 315000 question, factoid answer and full length answer triples. We have evaluated our system using ROUGE-1,2,L and BLEU and achieved 74.05 BLEU score and 86.25 Rogue-L score.
As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary. However, the existing models in this framework mostly rely on sentence-level rewards or suboptimal labels, causing a mismatch between a training objective and evaluation metric. In this paper, we present a novel training signal that directly maximizes summary-level ROUGE scores through reinforcement learning. In addition, we incorporate BERT into our model, making good use of its ability on natural language understanding. In extensive experiments, we show that a combination of our proposed model and training procedure obtains new state-of-the-art performance on both CNN/Daily Mail and New York Times datasets. We also demonstrate that it generalizes better on DUC-2002 test set.
Timeline summarization (TLS) automatically identifies key dates of major events and provides short descriptions of what happened on these dates. Previous approaches to TLS have focused on extractive methods. In contrast, we suggest an abstractive timeline summarization system. Our system is entirely unsupervised, which makes it especially suited to TLS where there are very few gold summaries available for training of supervised systems. In addition, we present the first abstractive oracle experiments for TLS. Our system outperforms extractive competitors in terms of ROUGE when the number of input documents is high and the output requires strong compression. In these cases, our oracle experiments confirm that our approach also has a higher upper bound for ROUGE scores than extractive methods. A study with human judges shows that our abstractive system also produces output that is easy to read and understand.
Linking facts across documents is a challenging task, as the language used to express the same information in a sentence can vary significantly, which complicates the task of multi-document summarization. Consequently, existing approaches heavily rely on hand-crafted features, which are domain-dependent and hard to craft, or additional annotated data, which is costly to gather. To overcome these limitations, we present a novel method, which makes use of two types of sentence embeddings: universal embeddings, which are trained on a large unrelated corpus, and domain-specific embeddings, which are learned during training. To this end, we develop SemSentSum, a fully data-driven model able to leverage both types of sentence embeddings by building a sentence semantic relation graph. SemSentSum achieves competitive results on two types of summary, consisting of 665 bytes and 100 words. Unlike other state-of-the-art models, neither hand-crafted features nor additional annotated data are necessary, and the method is easily adaptable for other tasks. To our knowledge, we are the first to use multiple sentence embeddings for the task of multi-document summarization.
User-generated reviews of products or services provide valuable information to customers. However, it is often impossible to read each of the potentially thousands of reviews: it would therefore save valuable time to provide short summaries of their contents. We address opinion summarization, a multi-document summarization task, with an unsupervised abstractive summarization neural system. Our system is based on (i) a language model that is meant to encode reviews to a vector space, and to generate fluent sentences from the same vector space (ii) a clustering step that groups together reviews about the same aspects and allows the system to generate summary sentences focused on these aspects. Our experiments on the Oposum dataset empirically show the importance of the clustering step.
Automatic summarization methods have been studied on a variety of domains, including news and scientific articles. Yet, legislation has not previously been considered for this task, despite US Congress and state governments releasing tens of thousands of bills every year. In this paper, we introduce BillSum, the first dataset for summarization of US Congressional and California state bills. We explain the properties of the dataset that make it more challenging to process than other domains. Then, we benchmark extractive methods that consider neural sentence representations and traditional contextual features. Finally, we demonstrate that models built on Congressional bills can be used to summarize California billa, thus, showing that methods developed on this dataset can transfer to states without human-written summaries.
We suggest a new idea of Editorial Network – a mixed extractive-abstractive summarization approach, which is applied as a post-processing step over a given sequence of extracted sentences. We further suggest an effective way for training the “editor” based on a novel soft-labeling approach. Using the CNN/DailyMail dataset we demonstrate the effectiveness of our approach compared to state-of-the-art extractive-only or abstractive-only baselines.
Highlighting is a powerful tool to pick out important content and emphasize. Creating summary highlights at the sub-sentence level is particularly desirable, because sub-sentences are more concise than whole sentences. They are also better suited than individual words and phrases that can potentially lead to disfluent, fragmented summaries. In this paper we seek to generate summary highlights by annotating summary-worthy sub-sentences and teaching classifiers to do the same. We frame the task as jointly selecting important sentences and identifying a single most informative textual unit from each sentence. This formulation dramatically reduces the task complexity involved in sentence compression. Our study provides new benchmarks and baselines for generating highlights at the sub-sentence level.
This paper introduces the SAMSum Corpus, a new dataset with abstractive dialogue summaries. We investigate the challenges it poses for automated summarization by testing several models and comparing their results with those obtained on a corpus of news articles. We show that model-generated summaries of dialogues achieve higher ROUGE scores than the model-generated summaries of news – in contrast with human evaluators’ judgement. This suggests that a challenging task of abstractive dialogue summarization requires dedicated models and non-standard quality measures. To our knowledge, our study is the first attempt to introduce a high-quality chat-dialogues corpus, manually annotated with abstractive summarizations, which can be used by the research community for further studies.
In this paper, we take stock of the current state of summarization datasets and explore how different factors of datasets influence the generalization behaviour of neural extractive summarization models. Specifically, we first propose several properties of datasets, which matter for the generalization of summarization models. Then we build the connection between priors residing in datasets and model designs, analyzing how different properties of datasets influence the choices of model structure design and training methods. Finally, by taking a typical dataset as an example, we rethink the process of the model design based on the experience of the above analysis. We demonstrate that when we have a deep understanding of the characteristics of datasets, a simple approach can bring significant improvements to the existing state-of-the-art model.
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 remaining summaries are preferred over the social-network summaries. We study the effect of translation quality in cross-lingual summarization, comparing a translate-then-summarize approach with several baselines. Our results highlight the limitations of the ROUGE metric that are overlooked in monolingual summarization.
Emerged as one of the best performing techniques for extractive summarization, determinantal point processes select a most probable set of summary sentences according to a probabilistic measure defined by respectively modeling sentence prominence and pairwise repulsion. Traditionally, both aspects are modelled using shallow and linguistically informed features, but the rise of deep contextualized representations raises an interesting question. Whether, and to what extent, could contextualized sentence representations be used to improve the DPP framework? Our findings suggest that, despite the success of deep semantic representations, it remains necessary to combine them with surface indicators for effective identification of summary-worthy sentences.
While recent work in abstractive summarization has resulted in higher scores in automatic metrics, there is little understanding on how these systems combine information taken from multiple document sentences. In this paper, we analyze the outputs of five state-of-the-art abstractive summarizers, focusing on summary sentences that are formed by sentence fusion. We ask assessors to judge the grammaticality, faithfulness, and method of fusion for summary sentences. Our analysis reveals that system sentences are mostly grammatical, but often fail to remain faithful to the original article.
Concept maps are visual summaries, structured as directed graphs: important concepts from a dataset are displayed as vertexes, and edges between vertexes show natural language descriptions of the relationships between the concepts on the map. Thus far, preliminary attempts at automatically creating concept maps have focused on building static summaries. However, in interactive settings, users will need to dynamically investigate particular relationships between pairs of concepts. For instance, a historian using a concept map browser might decide to investigate the relationship between two politicians in a news archive. We present a model which responds to such queries by returning one or more short, importance-ranked, natural language descriptions of the relationship between two requested concepts, for display in a visual interface. Our model is trained on a new public dataset, collected for this task.
Extractive summarization selects and concatenates the most essential text spans in a document. Most, if not all, neural approaches use sentences as the elementary unit to select content for summarization. However, semantic segments containing supplementary information or descriptive details are often nonessential in the generated summaries. In this work, we propose to exploit discourse-level segmentation as a finer-grained means to more precisely pinpoint the core content in a document. We investigate how the sub-sentential segmentation improves extractive summarization performance when content selection is modeled through two basic neural network architectures and a deep bi-directional transformer. Experiment results on the CNN/Daily Mail dataset show that discourse-level segmentation is effective in both cases. In particular, we achieve state-of-the-art performance when discourse-level segmentation is combined with our adapted contextual representation model.