Search Results for author: Smaranda Muresan

Found 55 papers, 31 papers with code

Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource Languages

1 code implementation NAACL 2022 Ramy Eskander, Cass Lowry, Sujay Khandagale, Judith Klavans, Maria Polinsky, Smaranda Muresan

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.

Part-Of-Speech Tagging POS +1

What to Fact-Check: Guiding Check-Worthy Information Detection in News Articles through Argumentative Discourse Structure

1 code implementation SIGDIAL (ACL) 2021 Tariq Alhindi, Brennan McManus, Smaranda Muresan

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.

Fact Checking

Unsupervised Cross-Lingual Part-of-Speech Tagging for Truly Low-Resource Scenarios

no code implementations EMNLP 2020 Ramy Eskander, Smaranda Muresan, Michael Collins

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.

Cross-Lingual Transfer Part-Of-Speech Tagging +4

"Is ChatGPT a Better Explainer than My Professor?": Evaluating the Explanation Capabilities of LLMs in Conversation Compared to a Human Baseline

no code implementations26 Jun 2024 Grace Li, Milad Alshomary, Smaranda Muresan

Explanations form the foundation of knowledge sharing and build upon communication principles, social dynamics, and learning theories.

V-FLUTE: Visual Figurative Language Understanding with Textual Explanations

1 code implementation2 May 2024 Arkadiy Saakyan, Shreyas Kulkarni, Tuhin Chakrabarty, Smaranda Muresan

We frame the visual figurative language understanding problem as an explainable visual entailment task, where the model has to predict whether the image (premise) entails a claim (hypothesis) and justify the predicted label with a textual explanation.

Question Answering Visual Entailment +1

Large Language Models are Few-Shot Training Example Generators: A Case Study in Fallacy Recognition

no code implementations16 Nov 2023 Tariq Alhindi, Smaranda Muresan, Preslav Nakov

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.

Identifying Self-Disclosures of Use, Misuse and Addiction in Community-based Social Media Posts

1 code implementation15 Nov 2023 Chenghao Yang, Tuhin Chakrabarty, Karli R Hochstatter, Melissa N Slavin, Nabila El-Bassel, Smaranda Muresan

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).

Learning to Follow Object-Centric Image Editing Instructions Faithfully

1 code implementation29 Oct 2023 Tuhin Chakrabarty, Kanishk Singh, Arkadiy Saakyan, Smaranda Muresan

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.

Object Question Answering +1

Art or Artifice? Large Language Models and the False Promise of Creativity

no code implementations25 Sep 2023 Tuhin Chakrabarty, Philippe Laban, Divyansh Agarwal, Smaranda Muresan, Chien-Sheng Wu

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.

Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers

no code implementations22 Sep 2023 Tuhin Chakrabarty, Vishakh Padmakumar, Faeze Brahman, Smaranda Muresan

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.

ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer

1 code implementation15 Sep 2023 Arkadiy Saakyan, Smaranda Muresan

Via automatic and human evaluation, we show that specialized student models fine-tuned on our datasets outperform generalist teacher models on the explainable style transfer task in one-shot settings, and perform competitively compared to few-shot teacher models, highlighting the quality of the data and the role of expert feedback.

Authorship Attribution Authorship Verification +3

I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors

1 code implementation24 May 2023 Tuhin Chakrabarty, Arkadiy Saakyan, Olivia Winn, Artemis Panagopoulou, Yue Yang, Marianna Apidianaki, Smaranda Muresan

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.

Visual Entailment

Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment

1 code implementation23 May 2023 Sky CH-Wang, Arkadiy Saakyan, Oliver Li, Zhou Yu, Smaranda Muresan

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.

Descriptive In-Context Learning +1

A Weak Supervision Approach for Few-Shot Aspect Based Sentiment

no code implementations19 May 2023 Robert Vacareanu, Siddharth Varia, Kishaloy Halder, Shuai Wang, Giovanni Paolini, Neha Anna John, Miguel Ballesteros, Smaranda Muresan

We explore how weak supervision on abundant unlabeled data can be leveraged to improve few-shot performance in aspect-based sentiment analysis (ABSA) tasks.

Aspect-Based Sentiment Analysis Aspect Extraction +3

Multitask Instruction-based Prompting for Fallacy Recognition

no code implementations24 Jan 2023 Tariq Alhindi, Tuhin Chakrabarty, Elena Musi, Smaranda Muresan

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.

Sentence valid

CONSISTENT: Open-Ended Question Generation From News Articles

1 code implementation20 Oct 2022 Tuhin Chakrabarty, Justin Lewis, Smaranda Muresan

Recent work on question generation has largely focused on factoid questions such as who, what, where, when about basic facts.

Question Generation Question-Generation

NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly

1 code implementation16 Oct 2022 Yi R. Fung, Tuhin Chakraborty, Hao Guo, Owen Rambow, Smaranda Muresan, Heng Ji

Norm discovery is important for understanding and reasoning about the acceptable behaviors and potential violations in human communication and interactions.

Cultural Vocal Bursts Intensity Prediction Hallucination +1

Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysis

1 code implementation12 Oct 2022 Siddharth Varia, Shuai Wang, Kishaloy Halder, Robert Vacareanu, Miguel Ballesteros, Yassine Benajiba, Neha Anna John, Rishita Anubhai, Smaranda Muresan, Dan Roth

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

FLUTE: Figurative Language Understanding through Textual Explanations

1 code implementation24 May 2022 Tuhin Chakrabarty, Arkadiy Saakyan, Debanjan Ghosh, Smaranda Muresan

Figurative language understanding has been recently framed as a recognizing textual entailment (RTE) task (a. k. a.

Natural Language Inference RTE

Fine-tuned Language Models are Continual Learners

1 code implementation24 May 2022 Thomas Scialom, Tuhin Chakrabarty, Smaranda Muresan

In spite of the limited success of Continual Learning we show that Language Models can be continual learners.

Continual Learning

Don't Go Far Off: An Empirical Study on Neural Poetry Translation

1 code implementation7 Sep 2021 Tuhin Chakrabarty, Arkadiy Saakyan, Smaranda Muresan

Moreover, multilingual fine-tuning on poetic data outperforms \emph{bilingual} fine-tuning on poetic data.

Machine Translation Translation

Weakly-Supervised Methods for Suicide Risk Assessment: Role of Related Domains

1 code implementation ACL 2021 Chenghao Yang, Yudong Zhang, Smaranda Muresan

Social media has become a valuable resource for the study of suicidal ideation and the assessment of suicide risk.

Metaphor Generation with Conceptual Mappings

1 code implementation ACL 2021 Kevin Stowe, Tuhin Chakrabarty, Nanyun Peng, Smaranda Muresan, Iryna Gurevych

Guided by conceptual metaphor theory, we propose to control the generation process by encoding conceptual mappings between cognitive domains to generate meaningful metaphoric expressions.


Emotion-Infused Models for Explainable Psychological Stress Detection

1 code implementation NAACL 2021 Elsbeth Turcan, Smaranda Muresan, Kathleen McKeown

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.

Language Modelling Multi-Task Learning

``Laughing at you or with you'': The Role of Sarcasm in Shaping the Disagreement Space

1 code implementation EACL 2021 Debanjan Ghosh, Ritvik Shrivastava, Smaranda Muresan

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).

Classification Relation +2

ENTRUST: Argument Reframing with Language Models and Entailment

no code implementations NAACL 2021 Tuhin Chakrabarty, Christopher Hidey, Smaranda Muresan

Framing involves the positive or negative presentation of an argument or issue depending on the audience and goal of the speaker (Entman 1983).

Text Generation

MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding

1 code implementation NAACL 2021 Tuhin Chakrabarty, Xurui Zhang, Smaranda Muresan, Nanyun Peng

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.

Language Modelling Masked Language Modeling +1

"Laughing at you or with you": The Role of Sarcasm in Shaping the Disagreement Space

1 code implementation26 Jan 2021 Debanjan Ghosh, Ritvik Shrivastava, Smaranda Muresan

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).

Classification General Classification +3

White Paper: Challenges and Considerations for the Creation of a Large Labelled Repository of Online Videos with Questionable Content

no code implementations25 Jan 2021 Thamar Solorio, Mahsa Shafaei, Christos Smailis, Mona Diab, Theodore Giannakopoulos, Heng Ji, Yang Liu, Rada Mihalcea, Smaranda Muresan, Ioannis Kakadiaris

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.

Fact vs. Opinion: the Role of Argumentation Features in News Classification

no code implementations COLING 2020 Tariq Alhindi, Smaranda Muresan, Daniel Preotiuc-Pietro

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.

Event Extraction Fact Checking +1

To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging

no code implementations EMNLP 2020 Kasturi Bhattacharjee, Miguel Ballesteros, Rishita Anubhai, Smaranda Muresan, Jie Ma, Faisal Ladhak, Yaser Al-Onaizan

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.

Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation

1 code implementation EMNLP 2020 Tuhin Chakrabarty, Smaranda Muresan, Nanyun Peng

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.

Common Sense Reasoning Sentence +1

AMPERSAND: Argument Mining for PERSuAsive oNline Discussions

1 code implementation IJCNLP 2019 Tuhin Chakrabarty, Christopher Hidey, Smaranda Muresan, Kathy Mckeown, Alyssa Hwang

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.

Argument Mining Language Modelling

DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking

1 code implementation ACL 2020 Christopher Hidey, Tuhin Chakrabarty, Tariq Alhindi, Siddharth Varia, Kriste Krstovski, Mona Diab, Smaranda Muresan

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.

Fact Checking Misinformation +1

Interpreting Verbal Irony: Linguistic Strategies and the Connection to the Type of Semantic Incongruity

no code implementations3 Nov 2019 Debanjan Ghosh, Elena Musi, Kartikeya Upasani, Smaranda Muresan

Human communication often involves the use of verbal irony or sarcasm, where the speakers usually mean the opposite of what they say.

Sarcasm Analysis using Conversation Context

no code implementations CL 2018 Debanjan Ghosh, Alexander R. Fabbri, Smaranda Muresan

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.

Sarcasm Detection Sentence

ChangeMyView Through Concessions: Do Concessions Increase Persuasion?

no code implementations8 Jun 2018 Elena Musi, Debanjan Ghosh, Smaranda Muresan

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.

"With 1 follower I must be AWESOME :P". Exploring the role of irony markers in irony recognition

no code implementations14 Apr 2018 Debanjan Ghosh, Smaranda Muresan

Conversations in social media often contain the use of irony or sarcasm, when the users say the opposite of what they really mean.

General Classification TAG

The Role of Conversation Context for Sarcasm Detection in Online Interactions

2 code implementations WS 2017 Debanjan Ghosh, Alexander Richard Fabbri, Smaranda Muresan

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.

Sarcasm Detection Sentence

Cannot find the paper you are looking for? You can Submit a new open access paper.