The goal of text summarization is to compress documents to the relevant information while excluding background information already known to the receiver. So far, summarization researchers have given considerably more attention to relevance than to background knowledge. In contrast, this work puts background knowledge in the foreground. Building on the realization that the choices made by human summarizers and annotators contain implicit information about their background knowledge, we develop and compare techniques for inferring background knowledge from summarization data. Based on this framework, we define summary scoring functions that explicitly model background knowledge, and show that these scoring functions fit human judgments significantly better than baselines. We illustrate some of the many potential applications of our framework. First, we provide insights into human information importance priors. Second, we demonstrate that averaging the background knowledge of multiple, potentially biased annotators or corpora greatly improves summary-scoring performance. Finally, we discuss potential applications of our framework beyond summarization.
Neural network-based models augmented with unsupervised pre-trained knowledge have achieved impressive performance on text summarization. However, most existing evaluation methods are limited to an in-domain setting, where summarizers are trained and evaluated on the same dataset. We argue that this approach can narrow our understanding of the generalization ability for different summarization systems. In this paper, we perform an in-depth analysis of characteristics of different datasets and investigate the performance of different summarization models under a cross-dataset setting, in which a summarizer trained on one corpus will be evaluated on a range of out-of-domain corpora. A comprehensive study of 11 representative summarization systems on 5 datasets from different domains reveals the effect of model architectures and generation ways (i.e. abstractive and extractive) on model generalization ability. Further, experimental results shed light on the limitations of existing summarizers. Brief introduction and supplementary code can be found in https://github.com/zide05/CDEvalSumm.
Fact verification models have enjoyed a fast advancement in the last two years with the development of pre-trained language models like BERT and the release of large scale datasets such as FEVER. However, the challenging problem of fake news detection has not benefited from the improvement of fact verification models, which is closely related to fake news detection. In this paper, we propose a simple yet effective approach to connect the dots between fact verification and fake news detection. Our approach first employs a text summarization model pre-trained on news corpora to summarize the long news article into a short claim. Then we use a fact verification model pre-trained on the FEVER dataset to detect whether the input news article is real or fake. Our approach makes use of the recent success of fact verification models and enables zero-shot fake news detection, alleviating the need of large-scale training data to train fake news detection models. Experimental results on FakenewsNet, a benchmark dataset for fake news detection, demonstrate the effectiveness of our proposed approach.
Deep learning has led to significant improvement in text summarization with various methods investigated and improved ROUGE scores reported over the years. However, gaps still exist between summaries produced by automatic summarizers and human professionals. Aiming to gain more understanding of summarization systems with respect to their strengths and limits on a fine-grained syntactic and semantic level, we consult the Multidimensional Quality Metric(MQM) and quantify 8 major sources of errors on 10 representative summarization models manually. Primarily, we find that 1) under similar settings, extractive summarizers are in general better than their abstractive counterparts thanks to strength in faithfulness and factual-consistency; 2) milestone techniques such as copy, coverage and hybrid extractive/abstractive methods do bring specific improvements but also demonstrate limitations; 3) pre-training techniques, and in particular sequence-to-sequence pre-training, are highly effective for improving text summarization, with BART giving the best results.
Unsupervised methods are promising for abstractive text summarization in that the parallel corpora is not required. However, their performance is still far from being satisfied, therefore research on promising solutions is on-going. In this paper, we propose a new approach based on Q-learning with an edit-based summarization. The method combines two key modules to form an Editorial Agent and Language Model converter (EALM). The agent predicts edit actions (e.t., delete, keep, and replace), and then the LM converter deterministically generates a summary on the basis of the action signals. Q-learning is leveraged to train the agent to produce proper edit actions. Experimental results show that EALM delivered competitive performance compared with the previous encoder-decoder-based methods, even with truly zero paired data (i.e., no validation set). Defining the task as Q-learning enables us not only to develop a competitive method but also to make the latest techniques in reinforcement learning available for unsupervised summarization. We also conduct qualitative analysis, providing insights into future study on unsupervised summarizers.
We propose a family of metrics to assess language generation derived from population estimation methods widely used in ecology. More specifically, we use mark-recapture and maximum-likelihood methods that have been applied over the past several decades to estimate the size of closed populations in the wild. We propose three novel metrics: ME$_\text{Petersen}$ and ME$_\text{CAPTURE}$, which retrieve a single-valued assessment, and ME$_\text{Schnabel}$ which returns a double-valued metric to assess the evaluation set in terms of quality and diversity, separately. In synthetic experiments, our family of methods is sensitive to drops in quality and diversity. Moreover, our methods show a higher correlation to human evaluation than existing metrics on several challenging tasks, namely unconditional language generation, machine translation, and text summarization.
We present an empirical study in favor of a cascade architecture to neural text summarization. Summarization practices vary widely but few other than news summarization can provide a sufficient amount of training data enough to meet the requirement of end-to-end neural abstractive systems which perform content selection and surface realization jointly to generate abstracts. Such systems also pose a challenge to summarization evaluation, as they force content selection to be evaluated along with text generation, yet evaluation of the latter remains an unsolved problem. In this paper, we present empirical results showing that the performance of a cascaded pipeline that separately identifies important content pieces and stitches them together into a coherent text is comparable to or outranks that of end-to-end systems, whereas a pipeline architecture allows for flexible content selection. We finally discuss how we can take advantage of a cascaded pipeline in neural text summarization and shed light on important directions for future research.
Pre-trained neural abstractive summarization systems have dominated extractive strategies on news summarization performance, at least in terms of ROUGE. However, system-generated abstractive summaries often face the pitfall of factual inconsistency: generating incorrect facts with respect to the source text. To address this challenge, we propose Span-Fact, a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text, while retaining the syntactic structure of summaries generated by abstractive summarization models. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
Text summarization is one of the most challenging and interesting problems in NLP. Although much attention has been paid to summarizing structured text like news reports or encyclopedia articles, summarizing conversations---an essential part of human-human/machine interaction where most important pieces of information are scattered across various utterances of different speakers---remains relatively under-investigated. This work proposes a multi-view sequence-to-sequence model by first extracting conversational structures of unstructured daily chats from different views to represent conversations and then utilizing a multi-view decoder to incorporate different views to generate dialogue summaries. Experiments on a large-scale dialogue summarization corpus demonstrated that our methods significantly outperformed previous state-of-the-art models via both automatic evaluations and human judgment. We also discussed specific challenges that current approaches faced with this task. We have publicly released our code at https://github.com/GT-SALT/Multi-View-Seq2Seq.
Text entailment, the task of determining whether a piece of text logically follows from another piece of text, is a key component in NLP, providing input for many semantic applications such as question answering, text summarization, information extraction, and machine translation, among others. Entailment scenarios can range from a simple syntactic variation to more complex semantic relationships between pieces of text, but most approaches try a one-size-fits-all solution that usually favors some scenario to the detriment of another. Furthermore, for entailments requiring world knowledge, most systems still work as a "black box", providing a yes/no answer that does not explain the underlying reasoning process. In this work, we introduce XTE - Explainable Text Entailment - a novel composite approach for recognizing text entailment which analyzes the entailment pair to decide whether it must be resolved syntactically or semantically. Also, if a semantic matching is involved, we make the answer interpretable, using external knowledge bases composed of structured lexical definitions to generate natural language justifications that explain the semantic relationship holding between the pieces of text. Besides outperforming well-established entailment algorithms, our composite approach gives an important step towards Explainable AI, allowing the inference model interpretation, making the semantic reasoning process explicit and understandable.
Keyphrases are a very short summary of an input text and provide the main subjects discussed in the text. Keyphrase extraction is a useful upstream task and can be used in various natural language processing problems, for example, text summarization and information retrieval, to name a few. However, not all the keyphrases are explicitly mentioned in the body of the text. In real-world examples there are always some topics that are discussed implicitly. Extracting such keyphrases requires a generative approach, which is adopted here. In this paper, we try to tackle the problem of keyphrase generation and extraction from news articles using deep sequence-to-sequence models. These models significantly outperform the conventional methods such as Topic Rank, KPMiner, and KEA in the task of keyphrase extraction.
Keyphrases provide an extremely dense summary of a text. Such information can be used in many Natural Language Processing tasks, such as information retrieval and text summarization. Since previous studies on Persian keyword or keyphrase extraction have not published their data, the field suffers from the lack of a human extracted keyphrase dataset. In this paper, we introduce PerKey, a corpus of 553k news articles from six Persian news websites and agencies with relatively high quality author extracted keyphrases, which is then filtered and cleaned to achieve higher quality keyphrases. The resulted data was put into human assessment to ensure the quality of the keyphrases. We also measured the performance of different supervised and unsupervised techniques, e.g. TFIDF, MultipartiteRank, KEA, etc. on the dataset using precision, recall, and F1-score.
Knowledge graphs capture entities and relations from long documents and can facilitate reasoning in many downstream applications. Extracting compact knowledge graphs containing only salient entities and relations is important but challenging for understanding and summarizing long documents. We introduce a new text-to-graph task of predicting summarized knowledge graphs from long documents. We develop a dataset of 200k document/graph pairs using automatic and human annotations. We also develop strong baselines for this task based on graph learning and text summarization, and provide quantitative and qualitative studies of their effect.
In recent years, the Natural Language Inference (NLI) task has garnered significant attention, with new datasets and models achieving near human-level performance on it. However, the full promise of NLI -- particularly that it learns knowledge that should be generalizable to other downstream NLP tasks -- has not been realized. In this paper, we study this unfulfilled promise from the lens of two downstream tasks: question answering (QA), and text summarization. We conjecture that a key difference between the NLI datasets and these downstream tasks concerns the length of the premise; and that creating new long premise NLI datasets out of existing QA datasets is a promising avenue for training a truly generalizable NLI model. We validate our conjecture by showing competitive results on the task of QA and obtaining the best reported results on the task of Checking Factual Correctness of Summaries.
In this paper we apply self-knowledge distillation to text summarization which we argue can alleviate problems with maximum-likelihood training on single reference and noisy datasets. Instead of relying on one-hot annotation labels, our student summarization model is trained with guidance from a teacher which generates smoothed labels to help regularize training. Furthermore, to better model uncertainty during training, we introduce multiple noise signals for both teacher and student models. We demonstrate experimentally on three benchmarks that our framework boosts the performance of both pretrained and non-pretrained summarizers achieving state-of-the-art results.
High-quality dialogue-summary paired data is expensive to produce and domain-sensitive, making abstractive dialogue summarization a challenging task. In this work, we propose the first unsupervised abstractive dialogue summarization model for tete-a-tetes (SuTaT). Unlike standard text summarization, a dialogue summarization method should consider the multi-speaker scenario where the speakers have different roles, goals, and language styles. In a tete-a-tete, such as a customer-agent conversation, SuTaT aims to summarize for each speaker by modeling the customer utterances and the agent utterances separately while retaining their correlations. SuTaT consists of a conditional generative module and two unsupervised summarization modules. The conditional generative module contains two encoders and two decoders in a variational autoencoder framework where the dependencies between two latent spaces are captured. With the same encoders and decoders, two unsupervised summarization modules equipped with sentence-level self-attention mechanisms generate summaries without using any annotations. Experimental results show that SuTaT is superior on unsupervised dialogue summarization for both automatic and human evaluations, and is capable of dialogue classification and single-turn conversation generation.
We propose a novel method to sparsify attention in the Transformer model by learning to select the most-informative token representations during the training process, thus focusing on the task-specific parts of an input. A reduction of quadratic time and memory complexity to sublinear was achieved due to a robust trainable top-$k$ operator. Our experiments on a challenging long document summarization task show that even our simple baseline performs comparably to the current SOTA, and with trainable pooling, we can retain its top quality, while being $1.8\times$ faster during training, $4.5\times$ faster during inference, and up to $13\times$ more computationally efficient in the decoder.
The novel corona-virus disease (also known as COVID-19) has led to a pandemic, impacting more than 200 countries across the globe. With its global impact, COVID-19 has become a major concern of people almost everywhere, and therefore there are a large number of tweets coming out from every corner of the world, about COVID-19 related topics. In this work, we try to analyze the tweets and detect the trending topics and major concerns of people on Twitter, which can enable us to better understand the situation, and devise better planning. More specifically we propose a model based on the universal sentence encoder to detect the main topics of Tweets in recent months. We used universal sentence encoder in order to derive the semantic representation and the similarity of tweets. We then used the sentence similarity and their embeddings, and feed them to K-means clustering algorithm to group similar tweets (in semantic sense). After that, the cluster summary is obtained using a text summarization algorithm based on deep learning, which can uncover the underlying topics of each cluster. Through experimental results, we show that our model can detect very informative topics, by processing a large number of tweets on sentence level (which can preserve the overall meaning of the tweets). Since this framework has no restriction on specific data distribution, it can be used to detect trending topics from any other social media and any other context rather than COVID-19. Experimental results show superiority of our proposed approach to other baselines, including TF-IDF, and latent Dirichlet allocation (LDA).
We propose Corder, a self-supervised contrastive learning framework for source code model. Corder is designed to alleviate the need of labeled data for code retrieval and code summarization tasks. The pre-trained model of Corder can be used in two ways: (1) it can produce vector representation of code which can be applied to code retrieval tasks that do not have labeled data; (2) it can be used in a fine-tuning process for tasks that might still require label data such as code summarization. The key innovation is that we train the source code model by asking it to recognize similar and dissimilar code snippets through a contrastive learning objective. To do so, we use a set of semantic-preserving transformation operators to generate code snippets that are syntactically diverse but semantically equivalent. Through extensive experiments, we have shown that the code models pretrained by Corder substantially outperform the other baselines for code-to-code retrieval, text-to-code retrieval, and code-to-text summarization tasks.
Machine based text comprehension has always been a significant research field in natural language processing. Once a full understanding of the text context and semantics is achieved, a deep learning model can be trained to solve a large subset of tasks, e.g. text summarization, classification and question answering. In this paper we focus on the question answering problem, specifically the multiple choice type of questions. We develop a model based on BERT, a state-of-the-art transformer network. Moreover, we alleviate the ability of BERT to support large text corpus by extracting the highest influence sentences through a semantic similarity model. Evaluations of our proposed model demonstrate that it outperforms the leading models in the MovieQA challenge and we are currently ranked first in the leader board with test accuracy of 87.79%. Finally, we discuss the model shortcomings and suggest possible improvements to overcome these limitations.