An official website of the United States government
This paper details the features and the methodology adopted in the construction of the CNN-corpus, a test corpus for single document extractive text summarization of news articles. The current version of the CNN-corpus encompasses 3,000 texts in English, and each of them has an abstractive and an extractive summary. The corpus allows quantitative and qualitative assessments of extractive summarization strategies.
more »
« less
Prosody Prediction from Syntactic, Lexical, and Word Embedding Features
Accurate prosody prediction from text leads to more natural-sounding TTS. In this work, we employ a new set of fea- tures to predict ToBI pitch accent and phrase boundaries from text. We investigate a wide variety of text-based features, in- cluding many new syntactic features, several types of word em- beddings, co-reference features, LIWC features, and specificity information. We focus our work on the Boston Radio News Corpus, a ToBI-labeled corpus of relatively clean news broad- casts, but also test our classifiers on Audix, a smaller corpus of read news, and on the Columbia Games Corpus, a corpus of conversational speech, in order to test the applicability of our model in cross-corpus settings. Our results show strong per- formance on both tasks, as well as some promising results for cross-corpus applications of our models.
more »
« less
- Award ID(s):
- 1717680
- PAR ID:
- 10177402
- Date Published:
- Journal Name:
- 10th ISCA Speech Synthesis Workshop
- Page Range / eLocation ID:
- 269 to 274
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Headlines play an important role in both news audiences' attention decisions online and in news organizations’ efforts to attract that attention. A large body of research focuses on developing generally applicable heuristics for more effective headline writing. In this work, we measure the importance of a number of theoretically motivated textual features to headline performance. Using a corpus of hundreds of thousands of headline A/B tests run by hundreds of news publishers, we develop and evaluate a machine-learned model to predict headline testing outcomes. We find that the model exhibits modest performance above baseline and further estimate an empirical upper bound for such content-based prediction in this domain, indicating an important role for non-content-based factors in test outcomes. Together, these results suggest that any particular headline writing approach has only a marginal impact, and that understanding reader behavior and headline context are key to predicting news attention decisions.more » « less
-
The proliferation of Internet-enabled smartphones has ushered in an era where events are reported on social media websites such as Twitter and Facebook. However, the short text nature of social media posts, combined with a large volume of noise present in such datasets makes event detection challenging. This problem can be alleviated by using other sources of information, such as news articles, that employ a precise and factual vocabulary, and are more descriptive in nature. In this paper, we propose Spatio-Temporal Event Detection (STED), a probabilistic model to discover events, their associated topics, time of occurrence, and the geospatial distribution from multiple data sources, such as news and Twitter. The joint modeling of news and Twitter enables our model to distinguish events from other noisy topics present in Twitter data. Furthermore, the presence of geocoordinates and timestamps in tweets helps find the spatio-temporal distribution of the events. We evaluate our model on a large corpus of Twitter and news data, and our experimental results show that STED can effectively discover events, and outperforms state-of-the-art techniques.more » « less
-
Recent works have demonstrated the effectiveness of machine learning (ML) techniques in detecting anxiety and stress using physiological signals, but it is unclear whether ML models are learning physiological features specific to stress. To address this ambiguity, we evaluated the generalizability of physiological features that have been shown to be correlated with anxiety and stress to high-arousal emotions. Specifically, we examine features extracted from electrocardiogram (ECG) and electrodermal (EDA) signals from the following three datasets: Anxiety Phases Dataset (APD), Wearable Stress and Affect Detection (WESAD), and the Continuously Annotated Signals of Emotion (CASE) dataset. We aim to understand whether these features are specific to anxiety or general to other high-arousal emotions through a statistical regression analysis, in addition to a within-corpus, cross-corpus, and leave-one-corpus-out cross-validation across instances of stress and arousal. We used the following classifiers: Support Vector Machines, LightGBM, Random Forest, XGBoost, and an ensemble of the aforementioned models. We found that models trained on an arousal dataset perform relatively well on a previously unseen stress dataset, and vice versa. Our experimental results suggest that the evaluated models may be identifying emotional arousal instead of stress. This work is the first cross-corpus evaluation across stress and arousal from ECG and EDA signals, contributing new findings about the generalizability of stress detection.more » « less
-
null (Ed.)Understanding who blames or supports whom in news text is a critical research question in computational social science. Traditional methods and datasets for sentiment analysis are, however, not suitable for the domain of political text as they do not consider the direction of sentiments expressed between entities. In this paper, we propose a novel NLP task of identifying directed sentiment relationship between political entities from a given news document, which we call directed sentiment extraction. From a million-scale news corpus, we construct a dataset of news sentences where sentiment relations of political entities are manually annotated. We present a simple but effective approach for utilizing a pretrained transformer, which infers the target class by predicting multiple question-answering tasks and combining the outcomes. We demonstrate the utility of our proposed method for social science research questions by analyzing positive and negative opinions between political entities in two major events: 2016 U.S. presidential election and COVID-19. The newly proposed problem, data, and method will facilitate future studies on interdisciplinary NLP methods and applications.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.21437/SSW.2019-48
