Collections of research article data harvested from the web have become common recently since they are important resources for experimenting on tasks such as named entity recognition, text summarization, or keyword generation. In fact, certain types of experiments require collections that are both large and topically structured, with records assigned to separate research disciplines. Unfortunately, the current collections of publicly available research articles are either small or heterogeneous and unstructured. In this work, we perform topic segmentation of a paper data collection that we crawled and produce a multitopic dataset of roughly seven million paper data records. We construct a taxonomy of topics extracted from the data records and then annotate each document with its corresponding topic from that taxonomy. As a result, it is possible to use this newly proposed dataset in two modalities: as a heterogeneous collection of documents from various disciplines or as a set of homogeneous collections, each from a single research topic.
We present ViT5, a pretrained Transformer-based encoder-decoder model for the Vietnamese language. With T5-style self-supervised pretraining, ViT5 is trained on a large corpus of high-quality and diverse Vietnamese texts. We benchmark ViT5 on two downstream text generation tasks, Abstractive Text Summarization and Named Entity Recognition. Although Abstractive Text Summarization has been widely studied for the English language thanks to its rich and large source of data, there has been minimal research into the same task in Vietnamese, a much lower resource language. In this work, we perform exhaustive experiments on both Vietnamese Abstractive Summarization and Named Entity Recognition, validating the performance of ViT5 against many other pretrained Transformer-based encoder-decoder models. Our experiments show that ViT5 significantly outperforms existing models and achieves state-of-the-art results on Vietnamese Text Summarization. On the task of Named Entity Recognition, ViT5 is competitive against previous best results from pretrained encoder-based Transformer models. Further analysis shows the importance of context length during the self-supervised pretraining on downstream performance across different settings.
Welsh is an official language in Wales and is spoken by an estimated 884,300 people (29.2% of the population of Wales). Despite this status and estimated increase in speaker numbers since the last (2011) census, Welsh remains a minority language undergoing revitalization and promotion by Welsh Government and relevant stakeholders. As part of the effort to increase the availability of Welsh digital technology, this paper introduces the first Welsh summarisation dataset, which we provide freely for research purposes to help advance the work on Welsh text summarization. The dataset was created by Welsh speakers by manually summarising Welsh Wikipedia articles. In addition, the paper discusses the implementation and evaluation of different summarisation systems for Welsh. The summarization systems and results will serve as benchmarks for the development of summarises in other minority language contexts.
We propose the shared task of cross-lingual conversation summarization, \emph{ConvSumX Challenge}, opening new avenues for researchers to investigate solutions that integrate conversation summarization and machine translation. This task can be particularly useful due to the emergence of online meetings and conferences. We construct a new benchmark, covering 2 real-world scenarios and 3 language directions, including a low-resource language. We hope that \emph{ConvSumX} can motivate researches to go beyond English and break the barrier for non-English speakers to benefit from recent advances of conversation summarization.
In zero-shot multilingual extractive text summarization, a model is typically trained on English summarization dataset and then applied on summarization datasets of other languages. Given English gold summaries and documents, sentence-level labels for extractive summarization are usually generated using heuristics. However, these monolingual labels created on English datasets may not be optimal on datasets of other languages, for that there is the syntactic or semantic discrepancy between different languages. In this way, it is possible to translate the English dataset to other languages and obtain different sets of labels again using heuristics. To fully leverage the information of these different sets of labels, we propose NLSSum (Neural Label Search for Summarization), which jointly learns hierarchical weights for these different sets of labels together with our summarization model. We conduct multilingual zero-shot summarization experiments on MLSUM and WikiLingua datasets, and we achieve state-of-the-art results using both human and automatic evaluations across these two datasets.
Text summarization is a technique for condensing a big piece of text into a few key elements that give a general impression of the content. When someone requires a quick and precise summary of a large amount of information, it becomes vital. If done manually, summarizing text can be costly and time-consuming. Natural Language Processing (NLP) is the sub-division of Artificial Intelligence that narrows down the gap between technology and human cognition by extracting the relevant information from the pile of data. In the present work, scientific information regarding the Friction Stir Welding of Aluminum alloys was collected from the abstract of scholarly research papers. For extracting the relevant information from these research abstracts four Natural Language Processing based algorithms i.e. Latent Semantic Analysis (LSA), Luhn Algorithm, Lex Rank Algorithm, and KL-Algorithm were used. In order to evaluate the accuracy score of these algorithms, Recall-Oriented Understudy for Gisting Evaluation (ROUGE) was used. The results showed that the Luhn Algorithm resulted in the highest f1-Score of 0.413 in comparison to other algorithms.
In real-world scenarios with naturally occurring datasets, reference summaries are noisy and may contain information that cannot be inferred from the source text. On large news corpora, removing low quality samples has been shown to reduce model hallucinations. Yet, for smaller, and/or noisier corpora, filtering is detrimental to performance. To improve reference quality while retaining all data, we propose a new approach: to selectively re-write unsupported reference sentences to better reflect source data. We automatically generate a synthetic dataset of positive and negative revisions by corrupting supported sentences and learn to revise reference sentences with contrastive learning. The intensity of revisions is treated as a controllable attribute so that, at inference, diverse candidates can be over-generated-then-rescored to balance faithfulness and abstraction. To test our methods, we extract noisy references from publicly available MIMIC-III discharge summaries for the task of hospital-course summarization, and vary the data on which models are trained. According to metrics and human evaluation, models trained on revised clinical references are much more faithful, informative, and fluent than models trained on original or filtered data.
Model-based, reference-free evaluation metrics have been proposed as a fast and cost-effective approach to evaluate Natural Language Generation (NLG) systems. Despite promising recent results, we find evidence that reference-free evaluation metrics of summarization and dialog generation may be relying on spurious correlations with measures such as word overlap, perplexity, and length. We further observe that for text summarization, these metrics have high error rates when ranking current state-of-the-art abstractive summarization systems. We demonstrate that these errors can be mitigated by explicitly designing evaluation metrics to avoid spurious features in reference-free evaluation.
Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and natural language processing communities. While NAR generation can significantly accelerate inference speed for machine translation, the speedup comes at the cost of sacrificed translation accuracy compared to its counterpart, autoregressive (AR) generation. In recent years, many new models and algorithms have been designed/proposed to bridge the accuracy gap between NAR generation and AR generation. In this paper, we conduct a systematic survey with comparisons and discussions of various non-autoregressive translation (NAT) models from different aspects. Specifically, we categorize the efforts of NAT into several groups, including data manipulation, modeling methods, training criterion, decoding algorithms, and the benefit from pre-trained models. Furthermore, we briefly review other applications of NAR models beyond machine translation, such as grammatical error correction, text summarization, text style transfer, dialogue, semantic parsing, automatic speech recognition, and so on. In addition, we also discuss potential directions for future exploration, including releasing the dependency of KD, reasonable training objectives, pre-training for NAR, and wider applications, etc. We hope this survey can help researchers capture the latest progress in NAR generation, inspire the design of advanced NAR models and algorithms, and enable industry practitioners to choose appropriate solutions for their applications. The web page of this survey is at \url{https://github.com/LitterBrother-Xiao/Overview-of-Non-autoregressive-Applications}.
Data augmentations (DA) are the cores to achieving robust sequence-to-sequence learning on various natural language processing (NLP) tasks. However, most of the DA approaches force the decoder to make predictions conditioned on the perturbed input representation, underutilizing supervised information provided by perturbed input. In this work, we propose a framework-level robust sequence-to-sequence learning approach, named BLISS, via self-supervised input representation, which has the great potential to complement the data-level augmentation approaches. The key idea is to supervise the sequence-to-sequence framework with both the \textit{supervised} ("input$\rightarrow$output") and \textit{self-supervised} ("perturbed input$\rightarrow$input") information. We conduct comprehensive experiments to validate the effectiveness of BLISS on various tasks, including machine translation, grammatical error correction, and text summarization. The results show that BLISS outperforms significantly the vanilla Transformer and consistently works well across tasks than the other five contrastive baselines. Extensive analyses reveal that BLISS learns robust representations and rich linguistic knowledge, confirming our claim. Source code will be released upon publication.
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 verify that these summaries are helpful for a critical mass of people. We collect a high quality human labeled dataset to support research into the task. We present a number of baseline methods that show that the task is interesting and challenging. Hence, with this work we hope to inspire a new line of research within the automatic summarization community.
Text generation with beam search has proven successful in a wide range of applications. We point out that, though largely overlooked in the literature, the commonly-used implementation of beam decoding (e.g., Hugging Face Transformers and fairseq) uses a first come, first served heuristic: it keeps a set of already completed sequences over time steps and stops when the size of this set reaches the beam size. Based on this finding, we introduce a patience factor, a simple modification to this beam decoding implementation, that generalizes the stopping criterion and provides flexibility to the depth of search. Empirical results demonstrate that adjusting this patience factor improves decoding performance of strong pretrained models on news text summarization and machine translation over diverse language pairs, with a negligible inference slowdown. Our approach only modifies one line of code and can be thus readily incorporated in any implementation. Further, we find that different versions of beam decoding result in large performance differences in summarization, demonstrating the need for clarity in specifying the beam search implementation in research work. Our code will be available upon publication.
For summarization, human preference is critical to tame outputs of the summarizer in favor of human interests, as ground-truth summaries are scarce and ambiguous. Practical settings require dynamic exchanges between human and AI agent wherein feedback is provided in an online manner, a few at a time. In this paper, we introduce a new framework to train summarization models with preference feedback interactively. By properly leveraging offline data and a novel reward model, we improve the performance regarding ROUGE scores and sample-efficiency. Our experiments on three various datasets confirm the benefit of the proposed framework in active, few-shot and online settings of preference learning.
Despite some recent advances, automatic text summarization remains unreliable, elusive, and of limited practical use in applications. Two main problems with current summarization methods are well known: evaluation and factual consistency. To address these issues, we propose a new automatic reference-less text summarization evaluation system that can measure the quality of any text summarization model with a set of generated facts based on factual consistency, comprehensiveness, and compression rate. As far as we know, our evaluation system is the first system that measures the overarching quality of the text summarization models based on factuality, information coverage, and compression rate.
A key problem in text summarization is finding a salience function which determines what information in the source should be included in the summary. This paper describes the use of machine learning on a training corpus of documents and their abstracts to discover salience functions which describe what combination of features is optimal for a given summarization task. The method addresses both "generic" and user-focused summaries.
One of the most pressing issues that have arisen due to the rapid growth of the Internet is known as information overloading. Simplifying the relevant information in the form of a summary will assist many people because the material on any topic is plentiful on the Internet. Manually summarising massive amounts of text is quite challenging for humans. So, it has increased the need for more complex and powerful summarizers. Researchers have been trying to improve approaches for creating summaries since the 1950s, such that the machine-generated summary matches the human-created summary. This study provides a detailed state-of-the-art analysis of text summarization concepts such as summarization approaches, techniques used, standard datasets, evaluation metrics and future scopes for research. The most commonly accepted approaches are extractive and abstractive, studied in detail in this work. Evaluating the summary and increasing the development of reusable resources and infrastructure aids in comparing and replicating findings, adding competition to improve the outcomes. Different evaluation methods of generated summaries are also discussed in this study. Finally, at the end of this study, several challenges and research opportunities related to text summarization research are mentioned that may be useful for potential researchers working in this area.
The distribution of fake news is not a new but a rapidly growing problem. The shift to news consumption via social media has been one of the drivers for the spread of misleading and deliberately wrong information, as in addition to it of easy use there is rarely any veracity monitoring. Due to the harmful effects of such fake news on society, the detection of these has become increasingly important. We present an approach to the problem that combines the power of transformer-based language models while simultaneously addressing one of their inherent problems. Our framework, CMTR-BERT, combines multiple text representations, with the goal of circumventing sequential limits and related loss of information the underlying transformer architecture typically suffers from. Additionally, it enables the incorporation of contextual information. Extensive experiments on two very different, publicly available datasets demonstrates that our approach is able to set new state-of-the-art performance benchmarks. Apart from the benefit of using automatic text summarization techniques we also find that the incorporation of contextual information contributes to performance gains.
While there has been recent progress in abstractive summarization as applied to different domains including news articles, scientific articles, and blog posts, the application of these techniques to clinical text summarization has been limited. This is primarily due to the lack of large-scale training data and the messy/unstructured nature of clinical notes as opposed to other domains where massive training data come in structured or semi-structured form. Further, one of the least explored and critical components of clinical text summarization is factual accuracy of clinical summaries. This is specifically crucial in the healthcare domain, cardiology in particular, where an accurate summary generation that preserves the facts in the source notes is critical to the well-being of a patient. In this study, we propose a framework for improving the factual accuracy of abstractive summarization of clinical text using knowledge-guided multi-objective optimization. We propose to jointly optimize three cost functions in our proposed architecture during training: generative loss, entity loss and knowledge loss and evaluate the proposed architecture on 1) clinical notes of patients with heart failure (HF), which we collect for this study; and 2) two benchmark datasets, Indiana University Chest X-ray collection (IU X-Ray), and MIMIC-CXR, that are publicly available. We experiment with three transformer encoder-decoder architectures and demonstrate that optimizing different loss functions leads to improved performance in terms of entity-level factual accuracy.
Abstractive summarization models are commonly trained using maximum likelihood estimation, which assumes a deterministic (one-point) target distribution in which an ideal model will assign all the probability mass to the reference summary. This assumption may lead to performance degradation during inference, where the model needs to compare several system-generated (candidate) summaries that have deviated from the reference summary. To address this problem, we propose a novel training paradigm which assumes a non-deterministic distribution so that different candidate summaries are assigned probability mass according to their quality. Our method achieves a new state-of-the-art result on the CNN/DailyMail (47.78 ROUGE-1) and XSum (49.07 ROUGE-1) datasets. Further analysis also shows that our model can estimate probabilities of candidate summaries that are more correlated with their level of quality.
In this paper, we survey Text Summarization (TS) datasets in Indian Languages (ILs), which are also low-resource languages (LRLs). We seek to answer one primary question: is the pool of Indian Language Text Summarization (ILTS) dataset growing or is there a resource poverty? To an-swer the primary question, we pose two sub-questions that we seek about ILTS datasets: first, what characteristics: format and domain do ILTS datasets have? Second, how different are those characteristics of ILTS datasets from high-resource languages (HRLs) particularly English. We focus on datasets reported in published ILTS research works during 2012-2022. The survey of ILTS and English datasets reveals two similarities and one contrast. The two similarities are: first, the domain of dataset commonly is news (Hermann et al., 2015). The second similarity is the format of the dataset which is both extractive and abstractive. The contrast is in how the research in dataset development has progressed. ILs face a slow speed of development and public release of datasets as compared with English. We argue that the relatively lower number of ILTS datasets is because of two reasons: first, absence of a dedicated forum for developing TS tools and resources; and second, lack of shareable standard datasets in the public domain.