Related papers: Evaluating the Factual Consistency of Abstractive …
Despite the recent advances in abstractive text summarization, current summarization models still suffer from generating factually inconsistent summaries, reducing their utility for real-world application. We argue that the main reason for…
We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary. Our work addresses current limitations of models for abstractive summarization that…
Recent advancements in text summarization, particularly with the advent of Large Language Models (LLMs), have shown remarkable performance. However, a notable challenge persists as a substantial number of automatically-generated summaries…
Document Summarization is the procedure of generating a meaningful and concise summary of a given document with the inclusion of relevant and topic-important points. There are two approaches: one is picking up the most relevant statements…
Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do…
Despite substantial progress in abstractive text summarization to generate fluent and informative texts, the factual inconsistency in the generated summaries remains an important yet challenging problem to be solved. In this paper, we…
The advancements in deep learning, particularly the introduction of transformers, have been pivotal in enhancing various natural language processing (NLP) tasks. These include text-to-text applications such as machine translation, text…
We present SUMO, a neural attention-based approach that learns to establish the correctness of textual claims based on evidence in the form of text documents (e.g., news articles or Web documents). SUMO further generates an extractive…
Improving factual consistency in abstractive summarization has been a focus of current research. One promising approach is the post-editing method. However, previous works have yet to make sufficient use of factual factors in summaries and…
Judging the veracity of a sentence making one or more claims is an important and challenging problem with many dimensions. The recent FEVER task asked participants to classify input sentences as either SUPPORTED, REFUTED or NotEnoughInfo…
Abstractive document summarization is usually modeled as a sequence-to-sequence (Seq2Seq) learning problem. Unfortunately, training large Seq2Seq based summarization models on limited supervised summarization data is challenging. This paper…
Text summarization is crucial for mitigating information overload across domains like journalism, medicine, and business. This research evaluates summarization performance across 17 large language models (OpenAI, Google, Anthropic,…
Ensuring factual consistency between the summary and the original document is paramount in summarization tasks. Consequently, considerable effort has been dedicated to detecting inconsistencies. With the advent of Large Language Models…
Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…
In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…
State-of-the-art abstractive summarization systems frequently hallucinate content that is not supported by the source document, mainly due to noise in the training dataset. Existing methods opt to drop the noisy samples or tokens from the…
Current research in automatic single document summarization is dominated by two effective, yet naive approaches: summarization by sentence extraction, and headline generation via bag-of-words models. While successful in some tasks, neither…
Unsupervised extractive summarization aims to extract salient sentences from a document as the summary without labeled data. Recent literatures mostly research how to leverage sentence similarity to rank sentences in the order of salience.…
Despite recent advances in abstractive summarization, current summarization systems still suffer from content hallucinations where models generate text that is either irrelevant or contradictory to the source document. However, prior work…
Producing a reduced version of a source text, as in generic or focused summarization, inherently involves two distinct subtasks: deciding on targeted content and generating a coherent text conveying it. While some popular approaches address…