Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
We present a method to produce abstractive summaries of long documents that exceed several thousand words via neural abstractive summarizati… (voir plus)on. We perform a simple extractive step before generating a summary, which is then used to condition the transformer language model on relevant information before being tasked with generating a summary. We also show that this approach produces more abstractive summaries compared to prior work that employs a copy mechanism while still achieving higher ROUGE scores. We provide extensive comparisons with strong baseline methods, prior state of the art work as well as multiple variants of our approach including those using only transformers, only extractive techniques and combinations of the two. We examine these models using four different summarization tasks and datasets: arXiv papers, PubMed papers, the Newsroom and BigPatent datasets. We find that transformer based methods produce summaries with fewer n-gram copies, leading to n-gram copying statistics that are more similar to human generated abstracts. We include a human evaluation, finding that transformers are ranked highly for coherence and fluency, but purely extractive methods score higher for informativeness and relevance. We hope that these architectures and experiments may serve as strong points of comparison for future work. Note: The abstract above was collaboratively written by the authors and one of the models presented in this paper based on an earlier draft of this paper.
2020-11-01
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (publié)
Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre… (voir plus)-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 transformations are inspired by an error analysis of state-of-the-art summarization model outputs. Experimental results show that our model is able to correct factual errors in summaries generated by other neural summarization models and outperforms previous models on factual consistency evaluation on the CNN/DailyMail dataset. We also find that transferring from artificial error correction to downstream settings is still very challenging.
2020-11-01
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (publié)
Multi-document summarization is a challenging task for which there exists little large-scale datasets. We propose Multi-XScience, a large-sc… (voir plus)ale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challenging multi-document summarization task: writing the related-work section of a paper based on its abstract and the articles it references. Our work is inspired by extreme summarization, a dataset construction protocol that favours abstractive modeling approaches. Descriptive statistics and empirical results—using several state-of-the-art models trained on the Multi-XScience dataset—reveal that Multi-XScience is well suited for abstractive models.
2020-11-01
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (publié)
Inferring missing facts in temporal knowledge graphs (TKGs) is a fundamental and challenging task. Previous works have approached this probl… (voir plus)em by augmenting methods for static knowledge graphs to leverage time-dependent representations. However, these methods do not explicitly leverage multi-hop structural information and temporal facts from recent time steps to enhance their predictions. Additionally, prior work does not explicitly address the temporal sparsity and variability of entity distributions in TKGs. We propose the Temporal Message Passing (TeMP) framework to address these challenges by combining graph neural networks, temporal dynamics models, data imputation and frequency-based gating techniques. Experiments on standard TKG tasks show that our approach provides substantial gains compared to the previous state of the art, achieving a 10.7% average relative improvement in Hits@10 across three standard benchmarks. Our analysis also reveals important sources of variability both within and across TKG datasets, and we introduce several simple but strong baselines that outperform the prior state of the art in certain settings.
2020-11-01
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (publié)
Human-written texts contain frequent generalizations and semantic aggregation of content. In a document, they may refer to a pair of named e… (voir plus)ntities such as ‘London’ and ‘Paris’ with different expressions: “the major cities”, “the capital cities” and “two European cities”. Yet generation, especially, abstractive summarization systems have so far focused heavily on paraphrasing and simplifying the source content, to the exclusion of such semantic abstraction capabilities. In this paper, we present a new dataset and task aimed at the semantic aggregation of entities. TESA contains a dataset of 5.3K crowd-sourced entity aggregations of Person, Organization, and Location named entities. The aggregations are document-appropriate, meaning that they are produced by annotators to match the situational context of a given news article from the New York Times. We then build baseline models for generating aggregations given a tuple of entities and document context. We finetune on TESA an encoder-decoder language model and compare it with simpler classification methods based on linguistically informed features. Our quantitative and qualitative evaluations show reasonable performance in making a choice from a given list of expressions, but free-form expressions are understandably harder to generate and evaluate.
2020-11-01
Conference on Empirical Methods in Natural Language Processing (publié)
For most neuroimaging questions the huge range of possible analytic choices leads to the possibility that conclusions from any single analyt… (voir plus)ic approach may be misleading. Examples of possible choices include the motion regression approach used and smoothing and threshold factors applied during the processing pipeline. Although it is possible to perform a multiverse analysis that evaluates all possible analytic choices, this can be computationally challenging and repeated sequential analyses on the same data can compromise inferential and predictive power. Here, we establish how active learning on a low-dimensional space that captures the inter-relationships between analysis approaches can be used to efficiently approximate the whole multiverse of analyses. This approach balances the benefits of a multiverse analysis without the accompanying cost to statistical power, computational power and the integrity of inferences. We illustrate this approach with a functional MRI dataset of functional connectivity across adolescence, demonstrating how a multiverse of graph theoretic and simple pre-processing steps can be efficiently navigated using active learning. Our study shows how this approach can identify the subset of analysis techniques (i.e., pipelines) which are best able to predict participants’ ages, as well as allowing the performance of different approaches to be quantified.
