Papers by Julia Hirschberg
Collecting Code-Switched Data from Social Media (L18-1)
Copied to clipboard
| Challenge: | a new method to identify code-switched data from the web is needed . code-witching is defined as the tendency of bilinguals to switch between languages . |
| Approach: | They propose a method that automatically collects code-switched tweets from the web . they use crowd-sourcing to obtain language identifiers for a subset of 8,000 tweets . |
| Outcome: | The proposed method identifies tweets as code-switched in languages L1 and L2 . it is compared to a Spanish-English corpus of code-witched tweets . |
EDEN: Empathetic Dialogues for English Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that student passion and perseverance, or grit, is associated with language learning success. |
| Approach: | They hypothesize that as students perceive their English teachers to be more supportive, their grit improves. |
| Outcome: | The proposed chatbot improves student persistence in learning a second language. |
“Talk to me with left, right, and angles”: Lexical entrainment in spoken Hebrew dialogue (2021.eacl-main)
Copied to clipboard
| Challenge: | entrainment is a widespread phenomenon in human interaction that leads interlocutors to adapt their linguistic productions to become more similar to each other. |
| Approach: | They propose to use existing measures to analyze Hebrew speakers interacting in a Map Task to find evidence of lexical entrainment. |
| Outcome: | The proposed study is the first to examine lexical entrainment in Hebrew using two existing measures. |
Measuring Entrainment in Spontaneous Code-switched Speech (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing studies of entrainment in code-switched domains have been limited to human-machine textual interactions. |
| Approach: | They propose to use acoustic-prosodic features to identify multiple dimensions and feature sets of entrainment in code-switched speech. |
| Outcome: | The findings give rise to important implications for the potentially “universal” nature of entrainment as a communication phenomenon and potential applications in inclusive and interactive speech technology. |
Evaluating the WordsEye Text-to-Scene System: Imaginative and Realistic Sentences (L18-1)
Copied to clipboard
| Challenge: | WordsEye is a system for automatically converting natural language text into 3D scenes representing the meaning of that text. |
| Approach: | They evaluate WordsEye's output vs. simple search methods to find a picture to illustrate a sentence. |
| Outcome: | The WordsEye system produced imaginative sentences and realistic sentences . the results show that wordsEyed produced better results than standard image search engines . |
Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect Lies (2020.tacl-1)
Copied to clipboard
| Challenge: | LieCatcher collects ratings of perceived deception using corpus of deceptive and truthful interviews . acoustic-prosodic and linguistic characteristics of language trusted and mistrusted are not reliable cues . |
| Approach: | They used a game framework to collect ratings of perceived deception using deceptive and truthful interviews to understand how perception aligns with reality. |
| Outcome: | The proposed framework detects deception using a corpus of deceptive and truthful interviews. |
DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines (2023.findings-emnlp)
Copied to clipboard
Prakhar Gupta, Yang Liu, Di Jin, Behnam Hedayatnia, Spandana Gella, Sijia Liu, Patrick Lange, Julia Hirschberg, Dilek Hakkani-Tur
| Challenge: | Dialogue models are able to generate fluent and interesting responses, but they can be difficult to control and may produce non-engaging, unsafe results. |
| Approach: | They propose a framework for controlling dialogue model behavior using natural language rules, or guidelines, which provide information about the context they are applicable to and what should be included in the response. |
| Outcome: | The proposed framework is effective in three open-domain dialogue response generation tasks and is consistent with the developer's expectations and intent. |
Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges (2025.acl-long)
Copied to clipboard
Bolei Ma, Yuting Li, Wei Zhou, Ziwei Gong, Yang Janet Liu, Katja Jasinskaja, Annemarie Friedrich, Julia Hirschberg, Frauke Kreuter, Barbara Plank
| Challenge: | linguistics studies how context influences meaning of language and how people use it to convey implied meanings, emotions, and intentions. |
| Approach: | They analyze task designs, data collection methods, evaluation approaches and their relevance to real-world applications. |
| Outcome: | The findings highlight emerging trends, challenges, and gaps in existing benchmarks . the findings will contribute to more nuanced and context-aware NLP models . |
EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control (2024.emnlp-main)
Copied to clipboard
| Challenge: | EmoKnob framework allows fine-grained emotion control in speech synthesis with few-shot demonstrative samples of arbitrary emotion. |
| Approach: | They propose a framework that allows fine-grained emotion control in speech synthesis . they propose two methods to apply emotion control on emotions described by open-ended text . |
| Outcome: | The proposed framework allows fine-grained emotion control in speech synthesis with few-shot demonstrative samples of arbitrary emotion. |
Defending Against Social Engineering Attacks in the Age of LLMs (2024.emnlp-main)
Copied to clipboard
Lin Ai, Tharindu Kumarage, Amrita Bhattacharjee, Zizhou Liu, Zheng Hui, Michael Davinroy, James Cook, Laura Cassani, Kirill Trapeznikov, Matthias Kirchner, Arslan Basharat, Anthony Hoogs, Joshua Garland, Huan Liu, Julia Hirschberg
| Challenge: | Existing research has developed frameworks to understand human-to-human CSE attacks. |
| Approach: | They propose a modular defense pipeline that improves detection at both the message and conversation levels. |
| Outcome: | The proposed model can be exploited to facilitate chat-based social engineering attacks and generate high-quality CSE content, but their detection capabilities are suboptimal, leading to increased operational costs for defense. |
NovAScore: A New Automated Metric for Evaluating Document Level Novelty (2025.coling-main)
Copied to clipboard
Lin Ai, Ziwei Gong, Harshsaiprasad Deshpande, Alexander Johnson, Emmy Phung, Ahmad Emami, Julia Hirschberg
| Challenge: | Recent research has focused on identifying text that introduces new, previously unknown information, but has seen a decline in novelty detection due to the rise of large language models. |
| Approach: | They propose a novel automated metric for evaluating document-level novelty that aggregates the novelty and salience scores of atomic information and provides high interpretability and a detailed analysis of a document's novelty. |
| Outcome: | The proposed metric scores high on the TAP-DLND 1.0 dataset and a human-annotated dataset. |
Multimodal Multi-loss Fusion Network for Sentiment Analysis (2024.naacl-long)
Copied to clipboard
| Challenge: | This paper examines the optimal selection and fusion of feature encoders across multiple modalities and combines them in one neural network to improve sentiment detection. |
| Approach: | They propose to combine feature encoders across multiple modalities into one neural network to improve sentiment detection. |
| Outcome: | The proposed model achieves state-of-the-art performance for three datasets . it also shows that integrating context significantly improves model performance. |
SMARTMiner: Extracting and Evaluating SMART Goals from Low-Resource Health Coaching Notes (2025.findings-emnlp)
Copied to clipboard
Iva Bojic, Qi Chwen Ong, Stephanie Hilary Xinyi Ma, Lin Ai, Zheng Liu, Ziwei Gong, Julia Hirschberg, Andy Hau Yan Ho, Andy W. H. Khong
| Challenge: | SMARTMiner extracts specific, measurable, attainable, relevant, time-bound (SMART) goals from unstructured health coaching notes. |
| Approach: | They propose a framework for extracting and evaluating specific, measurable, attainable, relevant, time-bound (SMART) goals from unstructured health coaching notes. |
| Outcome: | The framework extracts behavior change goal spans and categorizes their SMARTness. |
Enhancing Pre-Trained Generative Language Models with Question Attended Span Extraction on Machine Reading Comprehension (2024.emnlp-main)
Copied to clipboard
| Challenge: | Extractive Machine Reading Comprehension (MRC) is a challenging field in the field of Natural Language Processing. |
| Approach: | They propose a Question-Attended Span Extraction module to address the limitations of generative approaches for extractive machine reading comprehension (MRC) . module significantly enhances performance of pre-trained generative language models, enabling them to surpass the extractive capabilities of advanced Large Language Models (LLMs) |
| Outcome: | The QASE module surpasses state-of-the-art models in few-shot settings. |
From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that robots display human-like characteristics in dialogues . this anthropomorphism raises concerns about the accuracy of AI and its capabilities . |
| Approach: | They propose to use a dataset to analyze self-anthropomorphic and non-self-anthropophilic responses in robots . they propose to combine these two types of responses to create a new category of bot responses . |
| Outcome: | The proposed approach preserves the original dialogues from existing corpora and enhances them with paired responses: self-anthropomorphic and non-self-anthropophilic for each original bot response. |
Akan Cinematic Emotions (ACE): A Multimodal Multi-party Dataset for Emotion Recognition in Movie Dialogues (2025.findings-acl)
Copied to clipboard
David Sasu, Zehui Wu, Ziwei Gong, Run Chen, Pengyuan Shi, Lin Ai, Julia Hirschberg, Natalie Schluter
| Challenge: | Akan Cinematic Emotions (AkaCE) is the first multimodal emotion dialogue dataset for an African language . it contains 385 emotion-labeled dialogues and 6162 utterances across audio, visual, and textual modalities, along with word-level prosodic prominence annotations. |
| Approach: | They propose to use AkaCE to analyze African cinematic emotions using word-level prosodic prominence annotations. |
| Outcome: | The Akan Cinematic Emotions (AkaCE) dataset addresses the significant lack of resources for low-resource languages in emotion recognition research. |
Discourse-Driven Code-Switching: Analyzing the Role of Content and Communicative Function in Spanish-English Bilingual Speech (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has shown that a range of speaker and listener attributes affect or correlate with the prevalence of code-switching during conversation. |
| Approach: | They analyze the names of entities and dialogue acts present in a Spanish-English spontaneous speech corpus and build a predictive model of CSW. |
| Outcome: | The proposed model is the first to take a discourse-sensitive approach to understanding pragmatic and referential cues of bilingual speech. |
PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing research has studied privacy in LLM training data memorization, but it does not prevent users from disclosing PII at inference time. |
| Approach: | They propose a task for chaining API-based and local LLMs that uses public data to construct a benchmark that contains personally identifiable information (PII) |
| Outcome: | The proposed model maintains high response quality for 85.5% of user queries while restricting privacy leakage to only 7.5%. |
Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have demonstrated that Large Language Models possess a form of emotional intelligence, capable of interpreting emotional stimuli in text. |
| Approach: | They propose a method that translates speech characteristics into natural language descriptions and integrates them into LLMs to perform multimodal emotion analysis via text prompts. |
| Outcome: | The proposed method outperforms baseline models that require structural modifications on two datasets showing significant improvements in emotion recognition accuracy. |
Read to Hear: A Zero-Shot Pronunciation Assessment Using Textual Descriptions and LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Automatic pronunciation assessment is typically performed by acoustic models trained on audio-score pairs. |
| Approach: | They propose a zero-shot, textual description-based Pronunciation Assessment approach that utilizes human-readable representations of speech signals fed into an LLM to assess pronunciation accuracy and fluency. |
| Outcome: | The proposed approach is cost-efficient and competitive in performance . it significantly improves the performance of conventional audio-score-trained models on out-of-domain data . |
Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal Emotion Recognition in Conversations (MERC) is a new way to enhance human-computer interaction. |
| Approach: | This survey offers a systematic overview of Multimodal Emotion Recognition in Conversations . it examines motivations, core tasks, representative methods, and evaluation strategies . |
| Outcome: | The survey examines the effectiveness of MERC and its evaluation strategies. |
PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent (2025.coling-main)
Copied to clipboard
Jiateng Liu, Lin Ai, Zizhou Liu, Payam Karisani, Zheng Hui, Yi Fung, Preslav Nakov, Julia Hirschberg, Heng Ji
| Challenge: | Existing research on propaganda detection does not capture the motives behind the content or its broader impact. |
| Approach: | They propose a framework that dissects propaganda into techniques, arousal appeals, and underlying intent. |
| Outcome: | The proposed framework improves performance in a wide range of scenarios and can be used to identify and categorize propaganda techniques. |
Linguistic Cues to Deception and Perceived Deception in Interview Dialogues (N18-1)
Copied to clipboard
| Challenge: | a recent study examined deception detection in several domains, including fake reviews, mock crime scenes, and opinions about topics such as abortion or the death penalty. |
| Approach: | They analyze linguistic features in truthful and deceptive interview dialogues . they also examine interviewer perceptions of deception, identifying characteristics of deceptives . |
| Outcome: | The proposed model outperforms human classifications using linguistic features and individual traits. |
Does Context Matter? A Prosodic Comparison of English and Spanish in Monolingual and Multilingual Discourse Settings (2025.emnlp-main)
Copied to clipboard
| Challenge: | a large number of studies on prosody in languages have focused on monolingual discourse contexts . a recent study focused on the prosodic features of monolingual speech in multilingual contexts. |
| Approach: | They compare prosody of monolingual English and Spanish in monolingual and multilingual settings . they find that monolingual speech produced in a monolingual context is prosodically different from that produced in multilingual context . |
| Outcome: | The proposed study is the first to incorporate multilingual discourse contexts into the study of native-level monolingual prosody. |
A Survey on Open Information Extraction from Rule-based Model to Large Language Model (2024.findings-emnlp)
Copied to clipboard
Liu Pai, Wenyang Gao, Wenjie Dong, Lin Ai, Ziwei Gong, Songfang Huang, Li Zongsheng, Ehsan Hoque, Julia Hirschberg, Yue Zhang
| Challenge: | Open Information Extraction (OpenIE) is a key NLP task aimed at extracting structured information from unstructured text sources. |
| Approach: | They propose to categorize OpenIE into rule-based, neural, and pre-trained large language models and discuss each within a chronological framework. |
| Outcome: | The paper categorizes OpenIE approaches into rule-based, neural, and pre-trained large language models, discussing each within a chronological framework. |
A Review of Incorporating Psychological Theories in LLMs (2026.eacl-long)
Copied to clipboard
Zizhou Liu, Ziwei Gong, Lin Ai, Zheng Hui, Run Chen, Colin Wayne Leach, Michelle R. Greene, Julia Hirschberg
| Challenge: | a holistic review systematically integrating psychology across the LLM lifecycle remains missing. |
| Approach: | They examine how psychological theories can inform stages of LLM development . they highlight current trends and gaps in how psychological theory is applied . |
| Outcome: | The authors highlight current trends and gaps in how psychological theories are applied . they argue that psychological insights have shaped pivotal NLP breakthroughs . |
CHoRaL: Collecting Humor Reaction Labels from Millions of Social Media Users (2021.emnlp-main)
Copied to clipboard
| Challenge: | Humor detection is difficult due to individualistic and cultural differences in humor perception . authors propose a framework to generate perceived humor labels on Facebook posts . |
| Approach: | They propose a framework to generate perceived humor labels on Facebook posts . they use the naturally available user reactions to these posts to generate the labels . |
| Outcome: | The proposed framework generates perceived humor labels on Facebook posts with no manual annotation needed. |