Search Results for author:
Found 29 papers, 14 papers with code
OpenFraming: Open-sourced Tool for Computational Framing Analysis of Multilingual Data
We propose and guide users through a five-step end-to-end computational framing analysis framework grounded in media framing theory in communication research.
Did that happen? Predicting Social Media Posts that are Indicative of what happened in a scene: A case study of a TV show
While popular Television (TV) shows are airing, some users interested in these shows publish social media posts about the show.
“Wikily” Supervised Neural Translation Tailored to Cross-Lingual Tasks
Our captioning results on Arabic are slightly better than that of its supervised model.
BU-NEmo: an Affective Dataset of Gun Violence News
As such, we introduce a U. S. gun violence news dataset that contains news headline and image pairings from 840 news articles with 15K high-quality, crowdsourced annotations on emotional responses to the news pairings.
An Unsupervised Approach to Discover Media Frames
We discuss the effectiveness of our approach by comparing the frames it generates in an unsupervised manner to the domain-expert-derived frames for the issue of gun violence, for which a supervised learning model for frame recognition exists.
Resolving Pronouns in Twitter Streams: Context can Help!
Many people live-tweet televised events like Presidential debates and popular TV-shows and discuss people or characters in the event.
DriveThru: a Document Extraction Platform and Benchmark Datasets for Indonesian Local Language Archives
However, most of these efforts have been focused on creating manual resources thus difficult to scale to more languages.
Optical Character Recognition
Optical Character Recognition (OCR)
MetaMetrics-MT: Tuning Meta-Metrics for Machine Translation via Human Preference Calibration
We present MetaMetrics-MT, an innovative metric designed to evaluate machine translation (MT) tasks by aligning closely with human preferences through Bayesian optimization with Gaussian Processes.
Linguistics Theory Meets LLM: Code-Switched Text Generation via Equivalence Constrained Large Language Models
Code-switching, the phenomenon of alternating between two or more languages in a single conversation, presents unique challenges for Natural Language Processing (NLP).
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date.
MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences
This makes MetaMetrics a powerful tool for improving the evaluation of generation tasks, ensuring that metrics are more representative of human judgment across diverse contexts.
Generating Faithful and Salient Text from Multimodal Data
In this paper, we develop a framework to generate faithful and salient text from mixed-modal data, which includes images and structured data ( represented in knowledge graphs or tables).
Mitigating Translationese in Low-resource Languages: The Storyboard Approach
We conducted a comprehensive evaluation comparing our storyboard-based approach with traditional text translation-based methods in terms of accuracy and fluency.
Enhancing Emotion Prediction in News Headlines: Insights from ChatGPT and Seq2Seq Models for Free-Text Generation
Using the dataset BU-NEmo+ (Gao et al., 2022), we found that for emotion classification, the free-text explanations have a strong correlation with the dominant emotion elicited by the headlines.
Detecting Frames in News Headlines and Lead Images in U.S. Gun Violence Coverage
Additionally, we release the first multimodal news framing dataset related to gun violence in the U. S., curated and annotated by communication researchers.
Generating Faithful Text From a Knowledge Graph with Noisy Reference Text
Knowledge Graph (KG)-to-Text generation aims at generating fluent natural-language text that accurately represents the information of a given knowledge graph.
Subspace Regularizers for Few-Shot Class Incremental Learning
The key to this approach is a new family of subspace regularization schemes that encourage weight vectors for new classes to lie close to the subspace spanned by the weights of existing classes.
class-incremental learning
Few-Shot Class-Incremental Learning
+3
Cultural and Geographical Influences on Image Translatability of Words across Languages
We find that images of words are not always invariant across languages, and that language pairs with shared culture, meaning having either a common language family, ethnicity or religion, have improved image translatability (i. e., have more similar images for similar words) compared to its converse, regardless of their geographic proximity.
Cultural Vocal Bursts Intensity Prediction
Low Resource Neural Machine Translation
+5
"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks
Our captioning results on Arabic are slightly better than that of its supervised model.
Sentiment-based Candidate Selection for NMT
The explosion of user-generated content (UGC)--e. g. social media posts, comments, and reviews--has motivated the development of NLP applications tailored to these types of informal texts.
Majority Voting with Bidirectional Pre-translation For Bitext Retrieval
Obtaining high-quality parallel corpora is of paramount importance for training NMT systems.
Multi-Label and Multilingual News Framing Analysis
News framing refers to the practice in which aspects of specific issues are highlighted in the news to promote a particular interpretation.
Detecting Frames in News Headlines and Its Application to Analyzing News Framing Trends Surrounding U.S. Gun Violence
We apply our frame detection approach in a large scale study of 88k news headlines about the coverage of gun violence in the U. S. between 2016 and 2018.
Winter is here: Summarizing Twitter Streams related to Pre-Scheduled Events
Pre-scheduled events, such as TV shows and sports games, usually garner considerable attention from the public.
Learning Translations via Images with a Massively Multilingual Image Dataset
To facilitate research on the task, we introduce a large-scale multilingual corpus of images, each labeled with the word it represents.
