An official website of the United States government
The propensity of abstractive summarization models to make factual errors has been studied extensively, including design of metrics to detect factual errors and annotation of errors in current systems’ outputs. However, the ever-evolving nature of summarization systems, metrics, and annotated benchmarks makes factuality evaluation a moving target, and drawing clear comparisons among metrics has become increasingly difficult. In this work, we aggregate factuality error annotations from nine existing datasets and stratify them according to the underlying summarization model. We compare performance of state-of-the-art factuality metrics, including recent ChatGPT-based metrics, on this stratified benchmark and show that their performance varies significantly across different types of summarization models. Critically, our analysis shows that much of the recent improvement in the factuality detection space has been on summaries from older (pre-Transformer) models instead of more relevant recent summarization models. We further perform a finer-grained analysis per error-type and find similar performance variance across error types for different factuality metrics. Our results show that no one metric is superior in all settings or for all error types, and we provide recommendations for best practices given these insights.
more »
« less
He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics
Abstract We investigate how well BERT performs on predicting factuality in several existing English datasets, encompassing various linguistic constructions. Although BERT obtains a strong performance on most datasets, it does so by exploiting common surface patterns that correlate with certain factuality labels, and it fails on instances where pragmatic reasoning is necessary. Contrary to what the high performance suggests, we are still far from having a robust system for factuality prediction.
more »
« less
- Award ID(s):
- 1845122
- PAR ID:
- 10344633
- Date Published:
- Journal Name:
- Transactions of the Association for Computational Linguistics
- Volume:
- 9
- ISSN:
- 2307-387X
- Page Range / eLocation ID:
- 1081 to 1097
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Recent Transformer-based contextual word representations, including BERT and XLNet, have shown state-of-the-art performance in multiple disciplines within NLP. Fine-tuning the trained contextual models on task-specific datasets has been the key to achieving superior performance downstream. While fine-tuning these pre-trained models is straightforward for lexical applications (applications with only language modality), it is not trivial for multimodal language (a growing area in NLP focused on modeling face-to-face communication). More specifically, this is due to the fact that pre-trained models don’t have the necessary components to accept two extra modalities of vision and acoustic. In this paper, we proposed an attachment to BERT and XLNet called Multimodal Adaptation Gate (MAG). MAG allows BERT and XLNet to accept multimodal nonverbal data during fine-tuning. It does so by generating a shift to internal representation of BERT and XLNet; a shift that is conditioned on the visual and acoustic modalities. In our experiments, we study the commonly used CMU-MOSI and CMU-MOSEI datasets for multimodal sentiment analysis. Fine-tuning MAG-BERT and MAG-XLNet significantly boosts the sentiment analysis performance over previous baselines as well as language-only fine-tuning of BERT and XLNet. On the CMU-MOSI dataset, MAG-XLNet achieves human-level multimodal sentiment analysis performance for the first time in the NLP community.more » « less
-
Evaluating the factual consistency of automatically generated summaries is essential for the progress and adoption of reliable summarization systems. Despite recent advances, existing factuality evaluation models are not robust, being especially prone to entity and relation errors in new domains. We propose FactKB{---}a simple new approach to factuality evaluation that is generalizable across domains, in particular with respect to entities and relations. FactKB is based on language models pretrained using facts extracted from external knowledge bases. We introduce three types of complementary factuality pretraining objectives based on entity-specific facts, facts extracted from auxiliary knowledge about entities, and facts constructed compositionally through knowledge base walks. The resulting factuality evaluation model achieves state-of-the-art performance on two in-domain news summarization benchmarks as well as on three out-of-domain scientific literature datasets. Further analysis of FactKB shows improved ability to detect erroneous entities and relations in summaries and is robust and easily generalizable across domains.more » « less
-
Effectively filtering and categorizing the large volume of user-generated content on social media during disaster events can help emergency management and disaster response prioritize their resources. Deep learning approaches, including recurrent neural networks and transformer-based models, have been previously used for this purpose. Capsule Neural Networks (CapsNets), initially proposed for image classification, have been proven to be useful for text analysis as well. However, to the best of our knowledge, CapsNets have not been used for classifying crisis-related messages, and have not been extensively compared with state-of-the-art transformer-based models, such as BERT. Therefore, in this study, we performed a thorough comparison between CapsNet models, state-of-the-art BERT models and two popular recurrent neural network models that have been successfully used for tweet classification, specifically, LSTM and Bi-LSTM models, on the task of classifying crisis tweets both in terms of their informativeness (binary classification), as well as their humanitarian content (multi-class classification). For this purpose, we used several benchmark datasets for crisis tweet classification, namely CrisisBench, CrisisNLP and CrisisLex. Experimental results show that the performance of the CapsNet models is on a par with that of LSTM and Bi-LSTM models for all metrics considered, while the performance obtained with BERT models have surpassed the performance of the other three models across different datasets and classes for both classification tasks, and thus BERT could be considered the best overall model for classifying crisis tweets.more » « less
-
This work introduces an novel approach to improving cybersecurity systems to focus on spam email-based cyberattacks. The proposed technique tackles the challenge of training Machine Learning (ML) models with limited data samples by leveraging Bidirectional Encoder Representations from Transformers (BERT) for contextualized embeddings. Unlike traditional embedding methods, BERT offers a nuanced representation of smaller datasets, enabling more effective ML model training. The methodology will use several pre-trained BERT models for generating contextualized embeddings using data samples, and these embeddings will be fed to various ML algorithms for effective training. This approach demonstrates that even with scarce data, BERT embeddings significantly enhance model performance compared to conventional embedding approaches like Word2Vec. The technique proves especially advantageous for insufficient instances of high-quality dataset. The result of this proposed work outperforms traditional techniques to mitigate phishing attacks with few data samples. This work provides a robust accuracy of 99.25% when we use multilingual BERT (M-BERT) to embed dataset.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1162/tacl_a_00414
