Search Results for author:
Found 52 papers, 29 papers with code
The Role of Conversation Context for Sarcasm Detection in Online Interactions
To address the first issue, we investigate several types of Long Short-Term Memory (LSTM) networks that can model both the conversation context and the sarcastic response.
"With 1 follower I must be AWESOME :P". Exploring the role of irony markers in irony recognition
Conversations in social media often contain the use of irony or sarcasm, when the users say the opposite of what they really mean.
ChangeMyView Through Concessions: Do Concessions Increase Persuasion?
Drawing from a theoretically-informed typology of concessions, we conduct an annotation task to label a set of polysemous lexical markers as introducing an argumentative concession or not and we observe their distribution in threads that achieved and did not achieve persuasion.
Sarcasm Analysis using Conversation Context
To address the first issue, we investigate several types of Long Short-Term Memory (LSTM) networks that can model both the conversation context and the current turn.
Fine-Tuned Neural Models for Propaganda Detection at the Sentence and Fragment levels
This paper presents the CUNLP submission for the NLP4IF 2019 shared-task on FineGrained Propaganda Detection.
Interpreting Verbal Irony: Linguistic Strategies and the Connection to the Type of Semantic Incongruity
Human communication often involves the use of verbal irony or sarcasm, where the speakers usually mean the opposite of what they say.
DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking
The increased focus on misinformation has spurred development of data and systems for detecting the veracity of a claim as well as retrieving authoritative evidence.
$R^3$: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge
We propose an unsupervised approach for sarcasm generation based on a non-sarcastic input sentence.
AMPERSAND: Argument Mining for PERSuAsive oNline Discussions
Our approach for relation prediction uses contextual information in terms of fine-tuning a pre-trained language model and leveraging discourse relations based on Rhetorical Structure Theory.
A Report on the 2020 Sarcasm Detection Shared Task
Detecting sarcasm and verbal irony is critical for understanding people's actual sentiments and beliefs.
Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation
We also show how replacing literal sentences with similes from our best model in machine generated stories improves evocativeness and leads to better acceptance by human judges.
To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging
Leveraging large amounts of unlabeled data using Transformer-like architectures, like BERT, has gained popularity in recent times owing to their effectiveness in learning general representations that can then be further fine-tuned for downstream tasks to much success.
Fact vs. Opinion: the Role of Argumentation Features in News Classification
A 2018 study led by the Media Insight Project showed that most journalists think that a clearmarking of what is news reporting and what is commentary or opinion (e. g., editorial, op-ed)is essential for gaining public trust.
White Paper: Challenges and Considerations for the Creation of a Large Labelled Repository of Online Videos with Questionable Content
This white paper presents a summary of the discussions regarding critical considerations to develop an extensive repository of online videos annotated with labels indicating questionable content.
"Laughing at you or with you": The Role of Sarcasm in Shaping the Disagreement Space
We exploit joint modeling in terms of (a) applying discrete features that are useful in detecting sarcasm to the task of argumentative relation classification (agree/disagree/none), and (b) multitask learning for argumentative relation classification and sarcasm detection using deep learning architectures (e. g., dual Long Short-Term Memory (LSTM) with hierarchical attention and Transformer-based architectures).
MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding
Generating metaphors is a challenging task as it requires a proper understanding of abstract concepts, making connections between unrelated concepts, and deviating from the literal meaning.
ENTRUST: Argument Reframing with Language Models and Entailment
Framing involves the positive or negative presentation of an argument or issue depending on the audience and goal of the speaker (Entman 1983).
``Laughing at you or with you'': The Role of Sarcasm in Shaping the Disagreement Space
We exploit joint modeling in terms of (a) applying discrete features that are useful in detecting sarcasm to the task of argumentative relation classification (agree/disagree/none), and (b) multitask learning for argumentative relation classification and sarcasm detection using deep learning architectures (e. g., dual Long Short-Term Memory (LSTM) with hierarchical attention and Transformer-based architectures).
Emotion-Infused Models for Explainable Psychological Stress Detection
The problem of detecting psychological stress in online posts, and more broadly, of detecting people in distress or in need of help, is a sensitive application for which the ability to interpret models is vital.
Metaphor Generation with Conceptual Mappings
Guided by conceptual metaphor theory, we propose to control the generation process by encoding conceptual mappings between cognitive domains to generate meaningful metaphoric expressions.
Figurative Language in Recognizing Textual Entailment
We introduce a collection of recognizing textual entailment (RTE) datasets focused on figurative language.
Weakly-Supervised Methods for Suicide Risk Assessment: Role of Related Domains
Social media has become a valuable resource for the study of suicidal ideation and the assessment of suicide risk.
COVID-Fact: Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemic
The dataset contains claims, evidence for the claims, and contradictory claims refuted by the evidence.
Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction
Detecting what emotions are expressed in text is a well-studied problem in natural language processing.
Don't Go Far Off: An Empirical Study on Neural Poetry Translation
Moreover, multilingual fine-tuning on poetic data outperforms \emph{bilingual} fine-tuning on poetic data.
Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models
Enthymemes are defined as arguments where a premise or conclusion is left implicit.
Fine-tuned Language Models are Continual Learners
In spite of the limited success of Continual Learning we show that Language Models can be continual learners.
FLUTE: Figurative Language Understanding through Textual Explanations
Figurative language understanding has been recently framed as a recognizing textual entailment (RTE) task (a. k. a.
Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis
Aspect-based Sentiment Analysis (ABSA) is a fine-grained sentiment analysis task which involves four elements from user-generated texts: aspect term, aspect category, opinion term, and sentiment polarity.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly
Norm discovery is important for understanding and reasoning about the acceptable behaviors and potential violations in human communication and interactions.
CONSISTENT: Open-Ended Question Generation From News Articles
Recent work on question generation has largely focused on factoid questions such as who, what, where, when about basic facts.
Multitask Instruction-based Prompting for Fallacy Recognition
To move towards solving the fallacy recognition task, we approach these differences across datasets as multiple tasks and show how instruction-based prompting in a multitask setup based on the T5 model improves the results against approaches built for a specific dataset such as T5, BERT or GPT-3.
A Weak Supervision Approach for Few-Shot Aspect Based Sentiment
We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks.
Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment
Embedding Chain-of-Thought prompting in a human-AI collaborative framework, we build a high-quality dataset of 3, 069 social norms aligned with social situations across Chinese and American cultures alongside corresponding free-text explanations.
I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors
We propose to solve the task through the collaboration between Large Language Models (LLMs) and Diffusion Models: Instruct GPT-3 (davinci-002) with Chain-of-Thought prompting generates text that represents a visual elaboration of the linguistic metaphor containing the implicit meaning and relevant objects, which is then used as input to the diffusion-based text-to-image models. Using a human-AI collaboration framework, where humans interact both with the LLM and the top-performing diffusion model, we create a high-quality dataset containing 6, 476 visual metaphors for 1, 540 linguistic metaphors and their associated visual elaborations.
ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer
We propose a framework to augment and improve a formality style transfer dataset with explanations via model distillation from ChatGPT.
Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers
The development of large language models (LLMs) capable of following instructions and engaging in conversational interactions sparked increased interest in their utilization across various support tools.
Art or Artifice? Large Language Models and the False Promise of Creativity
Inspired by the Torrance Test of Creative Thinking (TTCT), which measures creativity as a process, we use the Consensual Assessment Technique [3] and propose the Torrance Test of Creative Writing (TTCW) to evaluate creativity as a product.
NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation
Social norms fundamentally shape interpersonal communication.
Learning to Follow Object-Centric Image Editing Instructions Faithfully
Current approaches focusing on image editing with natural language instructions rely on automatically generated paired data, which, as shown in our investigation, is noisy and sometimes nonsensical, exacerbating the above issues.
Identifying Self-Disclosures of Use, Misuse and Addiction in Community-based Social Media Posts
In the last decade, the United States has lost more than 500, 000 people from an overdose involving prescription and illicit opioids making it a national public health emergency (USDHHS, 2017).
Large Language Models are Few-Shot Training Example Generators: A Case Study in Fallacy Recognition
In this study, we aim to enhance existing models for fallacy recognition by incorporating additional context and by leveraging large language models to generate synthetic data, thus increasing the representation of the infrequent classes.
Navigating the Landscape of Hint Generation Research: From the Past to the Future
Digital education has gained popularity in the last decade, especially after the COVID-19 pandemic.
What to Fact-Check: Guiding Check-Worthy Information Detection in News Articles through Argumentative Discourse Structure
We discuss the connection between argument structure and check-worthy statements and develop several baseline models for detecting check-worthy statements in the climate change domain.
BeSt: The Belief and Sentiment Corpus
We present the BeSt corpus, which records cognitive state: who believes what (i. e., factuality), and who has what sentiment towards what.
Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource Languages
Our results show that the stem-based approach improves the POS models for all the target languages, with an average relative error reduction of 10. 3% in accuracy per target language, and outperforms the word-based approach that operates on three-times more data for about two thirds of the language pairs we consider.
Don’t Go Far Off: An Empirical Study on Neural Poetry Translation
Moreover, multilingual fine-tuning on poetic data outperforms bilingual fine-tuning on poetic data.
Unsupervised Cross-Lingual Part-of-Speech Tagging for Truly Low-Resource Scenarios
Our approach innovates in three ways: 1) a robust approach of selecting training instances via cross-lingual annotation projection that exploits best practices of unsupervised type and token constraints, word-alignment confidence and density of projected POS, 2) a Bi-LSTM architecture that uses contextualized word embeddings, affix embeddings and hierarchical Brown clusters, and 3) an evaluation on 12 diverse languages in terms of language family and morphological typology.
