Papers by Iris Hendrickx
Discovering the Language of Wine Reviews: A Text Mining Account (L18-1)
Copied to clipboard
| Challenge: | odors and flavors are often expressed in wine reviews, but they are often not. |
| Approach: | They use a corpus of wine reviews to find out what wine is like in a review . they use lexical bag-of-words features, domain-specific terminology features and word embedding features to train machine learning. |
| Outcome: | The proposed model predicts the wine's color, grape variety, and country of origin based on the review text alone. |
Negation Detection in Dutch Spoken Human-Computer Conversations (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing negation detection methods in English are not available. |
| Approach: | They propose to annotate a Dutch dialogue corpus with negation cues and their scopes. |
| Outcome: | The proposed method can detect negation cues and scope in Dutch dialogues with high precision and recall. |
BLISS: An Agent for Collecting Spoken Dialogue Data about Health and Well-being (2020.lrec-1)
Copied to clipboard
Jelte van Waterschoot, Iris Hendrickx, Arif Khan, Esther Klabbers, Marcel de Korte, Helmer Strik, Catia Cucchiarini, Mariët Theune
| Challenge: | Structured interviews are a time-consuming and inefficient way to gather information about people's well-being. |
| Approach: | They propose to build an artificial intelligence agent which asks questions about happiness . they build a prototype of the agent and collect 55 spoken dialogues . |
| Outcome: | The proposed agent collects 55 spoken dialogues and asks users about happiness and well-being. |
A Multilingual Wikified Data Set of Educational Material (L18-1)
Copied to clipboard
Iris Hendrickx, Eirini Takoulidou, Thanasis Naskos, Katia Lida Kermanidis, Vilelmini Sosoni, Hugo de Vos, Maria Stasimioti, Menno van Zaanen, Panayota Georgakopoulou, Valia Kordoni, Maja Popovic, Markus Egg, Antal van den Bosch
| Challenge: | a crowdsourcing effort to annotate and link parallel texts has been unsuccessful . a data set of parallel texts in eleven languages is presented . |
| Approach: | They present a wikified data set of English sentences linked to Wikipedia pages . they use crowdsourcing to annotate the texts and perform crowdsourcing for complex annotations . |
| Outcome: | The proposed data set is valuable as it constitutes a rich resource . it includes annotated data of English sentences linked to translations in eleven languages . |
Creating a Data Set of Abstractive Summaries of Turn-labeled Spoken Human-Computer Conversations (2022.lrec-1)
Copied to clipboard
| Challenge: | Digital recorded written and spoken dialogues are becoming more available due to the growing popularity of online messenger services and chatbots. |
| Approach: | They propose to use Dutch spoken human-computer conversations, an annotation layer of turn labels, and conversational abstractive summaries of user answers to build a conversational agent. |
| Outcome: | The proposed system can be integrated into a conversational agent. |
How Well Can Large Language Models Reflect? A Human Evaluation of LLM-generated Reflections for Motivational Interviewing Dialogues (2025.coling-main)
Copied to clipboard
Erkan Basar, Xin Sun, Iris Hendrickx, Jan de Wit, Tibor Bosse, Gert-Jan De Bruijn, Jos A. Bosch, Emiel Krahmer
| Challenge: | Motivational Interviewing (MI) is a counseling technique that promotes behavioral change through reflective responses to mirror or refine client statements. |
| Approach: | They assess the potential of Large Language Models (LLMs) to generate MI reflections via three LLMs: GPT-4, Llama-2, and BLOOM. |
| Outcome: | The proposed models generate meaningful reflections comparable to human therapists, but significant challenges remain. |
A Multi- versus a Single-classifier Approach for the Identification of Modality in the Portuguese Language (L18-1)
Copied to clipboard
| Challenge: | Comparative study of two different approaches to build an automatic classification system for Modality values in the Portuguese language. |
| Approach: | They propose to use a single multi-class classifier with the full Portuguese language dataset that includes eleven modal verbs and a weighted average approach to build different classifiers for each verb. |
| Outcome: | The proposed system is based on a Portuguese language dataset with 11 modal verbs and two different classifiers, one for each verb. |
Evaluating Large Language Models for Confidence-based Check Set Selection (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models have shown promise in automating high-labor data tasks, but their tendency to answer despite uncertainty and their difficulty handling long input contexts robustly are key challenges for adoption. |
| Approach: | They propose to use LLMs to prioritize information needing human judgment to identify low-confidence outputs for human review through "check set selection" using social media monitoring, they define the "check sets" as a list of tweets escalated to the disaster manager when the LLM has the least confidence. |
| Outcome: | The proposed approach outperforms random-sample check set selection in disaster tweet classification. |