Related papers: $\texttt{COSMIC}$: Mutual Information for Task-Agn…
Modern abstractive summarization models often generate summaries that contain hallucinated or contradictory information. In this paper, we propose a simple but effective contrastive learning framework that incorporates recent developments…
Aligning sentences in a reference summary with their counterparts in source documents was shown as a useful auxiliary summarization task, notably for generating training data for salience detection. Despite its assessed utility, the…
Automatic text summarization has achieved high performance in high-resourced languages like English, but comparatively less attention has been given to summarization in less-resourced languages. This work compares a variety of different…
The findings section of a radiology report is often detailed and lengthy, whereas the impression section is comparatively more compact and captures key diagnostic conclusions. This research explores the use of advanced abstractive…
Opinion summarization is expected to digest larger review sets and provide summaries from different perspectives. However, most existing solutions are deficient in epitomizing extensive reviews and offering opinion summaries from various…
Multi-document summarization (MDS) is a challenging task, often decomposed to subtasks of salience and redundancy detection, followed by text generation. In this context, alignment of corresponding sentences between a reference summary and…
Automatic metrics are used as proxies to evaluate abstractive summarization systems when human annotations are too expensive. To be useful, these metrics should be fine-grained, show a high correlation with human annotations, and ideally be…
Automatically summarizing large text collections is a valuable tool for document research, with applications in journalism, academic research, legal work, and many other fields. In this work, we contrast two classes of systems for…
While the NLP community has produced numerous summarization benchmarks, none provide the rich annotations required to simultaneously address many important problems related to control and reliability. We introduce a Wikipedia-derived…
Neural metrics for machine translation evaluation, such as COMET, exhibit significant improvements in their correlation with human judgments, as compared to traditional metrics based on lexical overlap, such as BLEU. Yet, neural metrics…
In recent times, extracting valuable information from large text is making significant progress. Especially in the current era of social media, people expect quick bites of information. Automatic text summarization seeks to tackle this by…
Concept maps can be used to concisely represent important information and bring structure into large document collections. Therefore, we study a variant of multi-document summarization that produces summaries in the form of concept maps.…
In this paper we focus on the estimation of mutual information from finite samples $(\mathcal{X}\times\mathcal{Y})$. The main concern with estimations of mutual information is their robustness under the class of transformations for which it…
Automated evaluation of text generation systems has recently seen increasing attention, particularly checking whether generated text stays truthful to input sources. Existing methods frequently rely on an evaluation using task-specific…
Automatic summarization with pre-trained language models has led to impressively fluent results, but is prone to 'hallucinations', low performance on non-news genres, and outputs which are not exactly summaries. Targeting ACL 2023's…
We introduce a new approach for abstractive text summarization, Topic-Guided Abstractive Summarization, which calibrates long-range dependencies from topic-level features with globally salient content. The idea is to incorporate neural…
The complexity and accuracy of current and future precision cosmology observational campaigns has made it essential to develop an efficient technique for directly combining simulation and observational datasets to determine cosmological and…
A key trait of stochastic optimizers is that multiple runs of the same optimizer in attempting to solve the same problem can produce different results. As a result, their performance is evaluated over several repeats, or runs, on the…
Understanding the impact of scientific publications is crucial for identifying breakthroughs and guiding future research. Traditional metrics based on citation counts often miss the nuanced ways a paper contributes to its field. In this…
Trainable evaluation metrics for machine translation (MT) exhibit strong correlation with human judgements, but they are often hard to interpret and might produce unreliable scores under noisy or out-of-domain data. Recent work has…