Search Results for author:
Found 81 papers, 39 papers with code
Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation
To address these challenges, first, we evaluate a multi-target and a multi-dataset training settings by training one model on each dataset and datasets of different domains, respectively.
CancerEmo: A Dataset for Fine-Grained Emotion Detection
Emotions are an important element of human nature, often affecting the overall wellbeing of a person.
EnsyNet: A Dataset for Encouragement and Sympathy Detection
More and more people turn to Online Health Communities to seek social support during their illnesses.
Detecting Optimism in Tweets using Knowledge Distillation and Linguistic Analysis of Optimism
Later, we devised a multi-task knowledge distillation framework to simultaneously learn the target task of optimism detection with the help of the auxiliary task of sentiment analysis and hate speech detection.
On the Use of Web Search to Improve Scientific Collections
We were able to obtain ~267, 000 unique research papers through our fully-automated framework using ~76, 000 queries, resulting in almost 200, 000 more papers than the number of queries.
Knowledge Distillation with BERT for Image Tag-Based Privacy Prediction
Moreover, we utilize the idea of knowledge distillation to improve tag representations in a semi-supervised learning task.
A New Public Corpus for Clinical Section Identification: MedSecId
The process by which sections in a document are demarcated and labeled is known as section identification.
Ranked #2 on
Classification
on MedSecId
Towards Summarizing Healthcare Questions in Low-Resource Setting
The current advancement in abstractive document summarization depends to a large extent on a considerable amount of human-annotated datasets.
Multimodal Semi-supervised Learning for Disaster Tweet Classification
In this paper, we investigate how to leverage the copious amounts of unlabeled data generated on social media by disaster eyewitnesses and affected individuals during disaster events.
SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents
In this paper, we release a new entity and relation extraction dataset for entities related to datasets, methods, and tasks in scientific articles.
Stanceformer: Target-Aware Transformer for Stance Detection
The task of Stance Detection involves discerning the stance expressed in a text towards a specific subject or target.
How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics
Natural Language Inference (NLI) evaluation is crucial for assessing language understanding models; however, popular datasets suffer from systematic spurious correlations that artificially inflate actual model performance.
On the Design Space Between Transformers and Recursive Neural Nets
In this paper, we study two classes of models, Recursive Neural Networks (RvNNs) and Transformers, and show that a tight connection between them emerges from the recent development of two recent models - Continuous Recursive Neural Networks (CRvNN) and Neural Data Routers (NDR).
FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding
FlowLearn contains complex scientific flowcharts and simulated flowcharts.
Optical Character Recognition (OCR)
Visual Question Answering (VQA)
Co-training for Low Resource Scientific Natural Language Inference
Scientific Natural Language Inference (NLI) is the task of predicting the semantic relation between a pair of sentences extracted from research articles.
SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions
To the best of our knowledge, SciDMT is the largest corpus for scientific entity mention detection.
A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus
Natural language inference (NLI), the task of recognizing the entailment relationship in sentence pairs, is an actively studied topic serving as a proxy for natural language understanding.
ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction
To address these limitations, we present ImplicitAVE, the first, publicly available multimodal dataset for implicit attribute value extraction.
EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLM
To address these issues, we introduce EIVEN, a data- and parameter-efficient generative framework that pioneers the use of multimodal LLM for implicit attribute value extraction.
MSciNLI: A Diverse Benchmark for Scientific Natural Language Inference
Furthermore, we show that domain shift degrades the performance of scientific NLI models which demonstrates the diverse characteristics of different domains in our dataset.
Investigating Recurrent Transformers with Dynamic Halt
In this paper, we comprehensively study the inductive biases of two major approaches to augmenting Transformers with a recurrent mechanism: (1) the approach of incorporating a depth-wise recurrence similar to Universal Transformers; and (2) the approach of incorporating a chunk-wise temporal recurrence like Temporal Latent Bottleneck.
Language Models (Mostly) Do Not Consider Emotion Triggers When Predicting Emotion
Situations and events evoke emotions in humans, but to what extent do they inform the prediction of emotion detection models?
DeCrisisMB: Debiased Semi-Supervised Learning for Crisis Tweet Classification via Memory Bank
During crisis events, people often use social media platforms such as Twitter to disseminate information about the situation, warnings, advice, and support.
CrisisMatch: Semi-Supervised Few-Shot Learning for Fine-Grained Disaster Tweet Classification
The shared real-time information about natural disasters on social media platforms like Twitter and Facebook plays a critical role in informing volunteers, emergency managers, and response organizations.
JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification
However, existing approaches based on pseudo-labeling suffer from the issues of pseudo-label bias and error accumulation.
MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins
We introduce MarginMatch, a new SSL approach combining consistency regularization and pseudo-labeling, with its main novelty arising from the use of unlabeled data training dynamics to measure pseudo-label quality.
Sarcasm Detection in a Disaster Context
This contempt is in some cases expressed as sarcasm or irony.
Unsupervised Extractive Summarization of Emotion Triggers
Second, we develop new unsupervised learning models that can jointly detect emotions and summarize their triggers.
Beam Tree Recursive Cells
We propose Beam Tree Recursive Cell (BT-Cell) - a backpropagation-friendly framework to extend Recursive Neural Networks (RvNNs) with beam search for latent structure induction.
Monotonic Location Attention for Length Generalization
We explore different ways to utilize position-based cross-attention in seq2seq networks to enable length generalization in algorithmic tasks.
Data Augmentation for Low-Resource Keyphrase Generation
Very few works address the problem of keyphrase generation in low-resource settings, but they still rely on a lot of additional unlabeled data for pretraining and on automatic methods for pseudo-annotations.
DMDD: A Large-Scale Dataset for Dataset Mentions Detection
We use DMDD to establish baseline performance for dataset mention detection and linking.
Neural Keyphrase Generation: Analysis and Evaluation
Keyphrase generation aims at generating topical phrases from a given text either by copying from the original text (present keyphrases) or by producing new keyphrases (absent keyphrases) that capture the semantic meaning of the text.
Semantic Tokenizer for Enhanced Natural Language Processing
Traditionally, NLP performance improvement has been focused on improving models and increasing the number of model parameters.
Hierarchical Multi-Label Classification of Scientific Documents
For example, a paper can be assigned to several topics in a hierarchy tree.
Hierarchical Multi-label Classification
Multi-Label Text Classification
+2
Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference
However, despite its substantial success on single sentence classification tasks where the challenge in making use of unlabeled data is to assign "good enough" pseudo-labels, for NLI tasks, the nature of unlabeled data is more complex: one of the sentences in the pair (usually the hypothesis) along with the class label are missing from the data and require human annotations, which makes SSL for NLI more challenging.
Why Do You Feel This Way? Summarizing Triggers of Emotions in Social Media Posts
This paper takes a novel angle, namely, emotion detection and trigger summarization, aiming to both detect perceived emotions in text, and summarize events and their appraisals that trigger each emotion.
A Data Cartography based MixUp for Pre-trained Language Models
MixUp is a data augmentation strategy where additional samples are generated during training by combining random pairs of training samples and their labels.
On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency
A well-calibrated neural model produces confidence (probability outputs) closely approximated by the expected accuracy.
SciNLI: A Corpus for Natural Language Inference on Scientific Text
Existing Natural Language Inference (NLI) datasets, while being instrumental in the advancement of Natural Language Understanding (NLU) research, are not related to scientific text.
Natural Language Inference
Natural Language Understanding
+1
On the Evaluation of Answer-Agnostic Paragraph-level Multi-Question Generation
Second, we compare different strategies to utilize a pre-trained seq2seq model to generate and select a set of questions related to a given paragraph.
Keyphrase Generation Beyond the Boundaries of Title and Abstract
Unlike prior large-scale datasets, FullTextKP includes the full text of the articles along with the title and abstract.
KPDrop: Improving Absent Keyphrase Generation
Keyphrase generation is the task of generating phrases (keyphrases) that summarize the main topics of a given document.
Generating Summaries for Scientific Paper Review
In this paper, we explore automatic review summary generation for scientific papers.
DeepZensols: Deep Natural Language Processing Framework
Reproducing results in publications by distributing publicly available source code is becoming ever more popular.
Stance Detection in COVID-19 Tweets
The prevalence of the COVID-19 pandemic in day-to-day life has yielded large amounts of stance detection data on social media sites, as users turn to social media to share their views regarding various issues related to the pandemic, e. g. stay at home mandates and wearing face masks when out in public.
eMLM: A New Pre-training Objective for Emotion Related Tasks
BERT has been shown to be extremely effective on a wide variety of natural language processing tasks, including sentiment analysis and emotion detection.
Emotion analysis and detection during COVID-19
Crises such as natural disasters, global pandemics, and social unrest continuously threaten our world and emotionally affect millions of people worldwide in distinct ways.
Modeling Hierarchical Structures with Continuous Recursive Neural Networks
We also show that CRvNN performs comparably or better than prior latent structure models on real-world tasks such as sentiment analysis and natural language inference.
Target-Aware Data Augmentation for Stance Detection
The goal of stance detection is to identify whether the author of a text is in favor of, neutral or against a specific target.
Identifying Medical Self-Disclosure in Online Communities
Self-disclosure in online health conversations may offer a host of benefits, including earlier detection and treatment of medical issues that may have otherwise gone unaddressed.
Exploiting Position and Contextual Word Embeddings for Keyphrase Extraction from Scientific Papers
Keyphrases associated with research papers provide an effective way to find useful information in the large and growing scholarly digital collections.
Scientific Keyphrase Identification and Classification by Pre-Trained Language Models Intermediate Task Transfer Learning
Scientific keyphrase identification and classification is the task of detecting and classifying keyphrases from scholarly text with their types from a set of predefined classes.
Identifying Documents In-Scope of a Collection from Web Archives
Web archive data usually contains high-quality documents that are very useful for creating specialized collections of documents, e. g., scientific digital libraries and repositories of technical reports.
Interpretable Multi-Step Reasoning with Knowledge Extraction on Complex Healthcare Question Answering
Unlike most other QA tasks that focus on linguistic understanding, HeadQA requires deeper reasoning involving not only knowledge extraction, but also complex reasoning with healthcare knowledge.
Cross-Lingual Disaster-related Multi-label Tweet Classification with Manifold Mixup
Distinguishing informative and actionable messages from a social media platform like Twitter is critical for facilitating disaster management.
Dynamic Classification in Web Archiving Collections
The Web archived data usually contains high-quality documents that are very useful for creating specialized collections of documents.
Detecting Perceived Emotions in Hurricane Disasters
Natural disasters (e. g., hurricanes) affect millions of people each year, causing widespread destruction in their wake.
On Identifying Hashtags in Disaster Twitter Data
Moreover, only a small number of tweets that contain actionable hashtags are useful for disaster response.
Multi-Task Stance Detection with Sentiment and Stance Lexicons
Stance detection aims to detect whether the opinion holder is in support of or against a given target.
The Myth of Double-Blind Review Revisited: ACL vs. EMNLP
We study this question on the ACL and EMNLP paper collections and present an analysis on how well deep learning techniques can infer the authors of a paper.
Keyphrase Extraction from Disaster-related Tweets
Previously, joint training of two different layers of a stacked Recurrent Neural Network for keyword discovery and keyphrase extraction had been shown to be effective in extracting keyphrases from general Twitter data.
Cleaning Noisy and Heterogeneous Metadata for Record Linking Across Scholarly Big Datasets
We introduce a system designed to match scholarly document entities with noisy metadata against a reference dataset.
Image Privacy Prediction Using Deep Neural Networks
Thus, automatically predicting images' privacy to warn users about private or sensitive content before uploading these images on social networking sites has become a necessity in our current interconnected world.
Dynamic Deep Multi-modal Fusion for Image Privacy Prediction
In this paper, we propose an approach for fusing object, scene context, and image tags modalities derived from convolutional neural networks for accurately predicting the privacy of images shared online.
Fine-Grained Emotion Detection in Health-Related Online Posts
Detecting fine-grained emotions in online health communities provides insightful information about patients{'} emotional states.
Exploring Optimism and Pessimism in Twitter Using Deep Learning
Identifying optimistic and pessimistic viewpoints and users from Twitter is useful for providing better social support to those who need such support, and for minimizing the negative influence among users and maximizing the spread of positive attitudes and ideas.
Identifying Empathetic Messages in Online Health Communities
Empathy captures one{'}s ability to correlate with and understand others{'} emotional states and experiences.
PositionRank: An Unsupervised Approach to Keyphrase Extraction from Scholarly Documents
In this paper, we propose PositionRank, an unsupervised model for keyphrase extraction from scholarly documents that incorporates information from all positions of a word{'}s occurrences into a biased PageRank.
Privacy Prediction of Images Shared on Social Media Sites Using Deep Features
In this paper, we present an approach to image privacy prediction that uses deep features and deep image tags as feature representations.
Entity-Specific Sentiment Classification of Yahoo News Comments
However, the problem of classifying the sentiment of user comments on news sites has not been addressed yet.
Keyword and Keyphrase Extraction Using Centrality Measures on Collocation Networks
Keyword and keyphrase extraction is an important problem in natural language processing, with applications ranging from summarization to semantic search to document clustering.
