Training a supervised news summarization model requires large amounts of high-quality training data consisting of news articles paired with reference summaries. However, obtaining such data is costly, and existing datasets contain considerable amount of noise. We present a new large-scale and high-quality dataset for supervised abstractive news summarization containing 1.3 million training samples, which we call CCSum. In creating this dataset, we take advantage of the journalistic inverted-pyramid style in news writing: In some articles, the first sentence can be considered a summary of the reported story. Accordingly, among 35 million CommonCrawl News articles, we identify pairs of articles about the same news story and use one article’s first sentence as the summary for the other article. To ensure high quality, we apply strict filters whose parameters we optimize using Bayesian optimization. We show that the resulting dataset is more factual and informative than established summarization datasets; less than 1% of the summaries have major factual inconsistencies with the corresponding news articles, compared to 5.5% to 15.4% in existing datasets, according to our human evaluation. Summarization models trained on our dataset are more favored compared to those trained on CNN/Daily Mail. The proposed dataset can open new opportunities for future research in abstractive summarization.
In this work, We present Unified Embeddings for Multimodal Retrieval (UniMuR), a simple but effective approach that embeds multimodal inputs and retrieves visual and textual outputs via frozen Large Language Models (LLMs). Specifically, UniMuR jointly retrieves multimodal outputs via a unified multimodal embedding and applies dual alignment training to account for both visual and textual semantics. Thus, unlike previous approaches, UniMuR significantly reduces LLM’s modality bias towards generating text-only outputs. Meanwhile, the proposed unified multimodal embedding mitigates the inconsistency between visual and textual outputs and provides coherent multimodal outputs. Furthermore, benefiting from the joint training of visual and textual semantics, UniMuR also achieves strong image/text retrieval ability. Compared to existing approaches, UniMuR achieves better zero-shot multimodal response retrieval performance on MMDialog, improving the overall R@1 by 6.5% while boosting the image retrieval rate and having better cross-modal consistency on multimodal outputs. UniMuR also achieves 2.4% and 3.9% improvement on context-based image retrieval tasks on MMDialog and VisDial respectively when compared to previous approaches, validating its generalization ability across multiple tasks.
Multimodal Large Language Models (MLLMs) excel at synthesizing key information from diverse sources. However, generating accurate and faithful multimodal summaries is challenging, primarily due to the lack of appropriate multimodal datasets for fine-tuning that meaningfully integrate textual and visual modalities. To address this gap, we present a new dataset designed specifically for image-text multimodal summarization, harnessing the capabilities of state-of-the-art MLLMs. We generate summaries from Wikipedia sections and corresponding images and evaluate them across text-based, visual and multimodal dimensions, employing reference-free metrics. To refine the dataset, we: (1) Filter the MLLM-generated summaries by training a critic model on human annotations and using its predictions to remove low-quality summaries; (2) Fine-tune the MLLM with the filtered high-quality summaries; (3) Use the fine-tuned model in turn to regenerate the summaries. This self-refinement process significantly improves summary quality, as measured by human judgements and automatic multimodal metrics, resulting in a valuable dataset for multimodal summarization research. The dataset is publicly available at https://github.com/amazon-science/refinesumm.
Neural models for abstractive summarization tend to generate output that is fluent and well-formed but lacks semantic faithfulness, or factuality, with respect to the input documents. In this paper, we analyze the tradeoff between abstractiveness and factuality of generated summaries across multiple datasets and models, using extensive human evaluations of factuality. In our analysis, we visualize the rates of change in factuality as we gradually increase abstractiveness using a decoding constraint, and we observe that, while increased abstractiveness generally leads to a drop in factuality, the rate of factuality decay depends on factors such as the data that the system was trained on. We introduce two datasets with human factuality judgements; one containing 10.2k generated summaries with systematically varied degrees of abstractiveness; the other containing 4.2k summaries from five different summarization models. We propose new factuality metrics that adjust for the degree of abstractiveness, and we use them to compare the abstractiveness-adjusted factuality of previous summarization works, providing baselines for future work.
Information extraction (IE) and summarization are closely related, both tasked with presenting a subset of the information contained in a natural language text. However, while IE extracts structural representations, summarization aims to abstract the most salient information into a generated text summary – thus potentially encountering the technical limitations of current text generation methods (e.g., hallucination). To mitigate this risk, this work uses structured IE graphs to enhance the abstractive summarization task. Specifically, we focus on improving Multi-Document Summarization (MDS) performance by using cross-document IE output, incorporating two novel components: (1) the use of auxiliary entity and event recognition systems to focus the summary generation model; (2) incorporating an alignment loss between IE nodes and their text spans to reduce inconsistencies between the IE graphs and text representations. Operationally, both the IE nodes and corresponding text spans are projected into the same embedding space and pairwise distance is minimized. Experimental results on multiple MDS benchmarks show that summaries generated by our model are more factually consistent with the source documents than baseline models while maintaining the same level of abstractiveness.
Despite significant progress in understanding and improving faithfulness in abstractive summarization, the question of how decoding strategies affect faithfulness is less studied. We present a systematic study of the effect of generation techniques such as beam search and nucleus sampling on faithfulness in abstractive summarization. We find a consistent trend where beam search with large beam sizes produces the most faithful summaries while nucleus sampling generates the least faithful ones. We propose two faithfulness-aware generation methods to further improve faithfulness over current generation techniques: (1) ranking candidates generated by beam search using automatic faithfulness metrics and (2) incorporating lookahead heuristics that produce a faithfulness score on the future summary. We show that both generation methods significantly improve faithfulness across two datasets as evaluated by four automatic faithfulness metrics and human evaluation. To reduce computational cost, we demonstrate a simple distillation approach that allows the model to generate faithful summaries with just greedy decoding.
Generating concise summaries of news events is a challenging natural language processing task. While journalists often curate timelines to highlight key sub-events, newcomers to a news event face challenges in catching up on its historical context. In this paper, we address this need by introducing the task of background news summarization, which complements each timeline update with a background summary of relevant preceding events. We construct a dataset by merging existing timeline datasets and asking human annotators to write a background summary for each timestep of each news event. We establish strong baseline performance using state-of-the-art summarization systems and propose a query-focused variant to generate background summaries. To evaluate background summary quality, we present a question-answering-based evaluation metric, Background Utility Score (BUS), which measures the percentage of questions about a current event timestep that a background summary answers. Our experiments show the effectiveness of instruction fine-tuned systems such as Flan-T5, in addition to strong zero-shot performance using GPT-3.5.
Readability refers to how easily a reader can understand a written text. Several factors affect the readability level, such as the complexity of the text, its subject matter, and the reader’s background knowledge. Generating summaries based on different readability levels is critical for enabling knowledge consumption by diverse audiences. However, current text generation approaches lack refined control, resulting in texts that are not customized to readers’ proficiency levels. In this work, we bridge this gap and study techniques to generate summaries at specified readability levels. Unlike previous methods that focus on a specific readability level (e.g., lay summarization), we generate summaries with fine-grained control over their readability. We develop three text generation techniques for controlling readability: (1) instruction-based readability control, (2) reinforcement learning to minimize the gap between requested and observed readability and (3) a decoding approach that uses lookahead to estimate the readability of upcoming decoding steps. We show that our generation methods significantly improve readability control on news summarization (CNN/DM dataset), as measured by various readability metrics and human judgement, establishing strong baselines for controllable readability in summarization.
Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples. However, in opinion summarization, large annotated datasets of reviews paired with reference summaries are not available and would be expensive to create. This calls for fine-tuning methods robust to overfitting on small datasets. In addition, generically pre-trained models are often not accustomed to the specifics of customer reviews and, after fine-tuning, yield summaries with disfluencies and semantic mistakes. To address these problems, we utilize an efficient few-shot method based on adapters which, as we show, can easily store in-domain knowledge. Instead of fine-tuning the entire model, we add adapters and pre-train them in a task-specific way on a large corpus of unannotated customer reviews, using held-out reviews as pseudo summaries. Then, fine-tune the adapters on the small available human-annotated dataset. We show that this self-supervised adapter pre-training improves summary quality over standard fine-tuning by 2.0 and 1.3 ROUGE-L points on the Amazon and Yelp datasets, respectively. Finally, for summary personalization, we condition on aspect keyword queries, automatically created from generic datasets. In the same vein, we pre-train the adapters in a query-based manner on customer reviews and then fine-tune them on annotated datasets. This results in better-organized summary content reflected in improved coherence and fewer redundancies.
Despite recent improvements in abstractive summarization, most current approaches generate summaries that are not factually consistent with the source document, severely restricting their trust and usage in real-world applications. Recent works have shown promising improvements in factuality error identification using text or dependency arc entailments; however, they do not consider the entire semantic graph simultaneously. To this end, we propose FactGraph, a method that decomposes the document and the summary into structured meaning representations (MR), which are more suitable for factuality evaluation. MRs describe core semantic concepts and their relations, aggregating the main content in both document and summary in a canonical form, and reducing data sparsity. FactGraph encodes such graphs using a graph encoder augmented with structure-aware adapters to capture interactions among the concepts based on the graph connectivity, along with text representations using an adapter-based text encoder. Experiments on different benchmarks for evaluating factuality show that FactGraph outperforms previous approaches by up to 15%. Furthermore, FactGraph improves performance on identifying content verifiability errors and better captures subsentence-level factual inconsistencies.
This paper presents an efficient graph-enhanced approach to multi-document summarization (MDS) with an encoder-decoder Transformer model. This model is based on recent advances in pre-training both encoder and decoder on very large text data (Lewis et al., 2019), and it incorporates an efficient encoding mechanism (Beltagy et al., 2020) that avoids the quadratic memory growth typical for traditional Transformers. We show that this powerful combination not only scales to large input documents commonly found when summarizing news clusters; it also enables us to process additional input in the form of auxiliary graph representations, which we derive from the multi-document clusters. We present a mechanism to incorporate such graph information into the encoder-decoder model that was pre-trained on text only. Our approach leads to significant improvements on the Multi-News dataset, overall leading to an average 1.8 ROUGE score improvement over previous work (Li et al., 2020). We also show improvements in a transfer-only setup on the DUC-2004 dataset. The graph encodings lead to summaries that are more abstractive. Human evaluation shows that they are also more informative and factually more consistent with their input documents.
We consider the problem of topic-focused abstractive summarization, where the goal is to generate an abstractive summary focused on a particular topic, a phrase of one or multiple words. We hypothesize that the task of generating topic-focused summaries can be improved by showing the model what it must not focus on. We introduce a deep reinforcement learning approach to topic-focused abstractive summarization, trained on rewards with a novel negative example baseline. We define the input in this problem as the source text preceded by the topic. We adapt the CNN-Daily Mail and New York Times summarization datasets for this task. We then show through experiments on existing rewards that the use of a negative example baseline can outperform the use of a self-critical baseline, in Rouge, BERTScore, and human evaluation metrics.
We present methods for multi-task learning that take advantage of natural groupings of related tasks. Task groups may be defined along known properties of the tasks, such as task domain or language. Such task groups represent supervised information at the inter-task level and can be encoded into the model. We investigate two variants of neural network architectures that accomplish this, learning different feature spaces at the levels of individual tasks, task groups, as well as the universe of all tasks: (1) parallel architectures encode each input simultaneously into feature spaces at different levels; (2) serial architectures encode each input successively into feature spaces at different levels in the task hierarchy. We demonstrate the methods on natural language understanding (NLU) tasks, where a grouping of tasks into different task domains leads to improved performance on ATIS, Snips, and a large in-house dataset.
The goal of semantic parsing is to map natural language to a machine interpretable meaning representation language (MRL). One of the constraints that limits full exploration of deep learning technologies for semantic parsing is the lack of sufficient annotation training data. In this paper, we propose using sequence-to-sequence in a multi-task setup for semantic parsing with focus on transfer learning. We explore three multi-task architectures for sequence-to-sequence model and compare their performance with the independently trained model. Our experiments show that the multi-task setup aids transfer learning from an auxiliary task with large labeled data to the target task with smaller labeled data. We see an absolute accuracy gain ranging from 1.0% to 4.4% in in our in-house data set and we also see good gains ranging from 2.5% to 7.0% on the ATIS semantic parsing tasks with syntactic and semantic auxiliary tasks.