Papers by Giuseppe Castellucci
VoiSeR: A New Benchmark for Voice-Based Search Refinement (2021.eacl-main)
Copied to clipboard
| Challenge: | a new study shows that voice-based search systems are challenging to support in the context of the user intent of voice searches . support for voice-driven search, exploration, and refinement is a fundamental aspect of voice assistants . |
| Approach: | They propose to use crowdsourcing to collect voice-based search refinements . they use 10,000 search refinement utterances to annotate a search intent . |
| Outcome: | The proposed dataset shows that voice-based search refinements can support most common tasks . the study shows that the proposed dataset can support research in conversational query understanding . |
Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers (2024.acl-long)
Copied to clipboard
Lütfi Kerem Senel, Besnik Fetahu, Davis Yoshida, Zhiyu Chen, Giuseppe Castellucci, Nikhita Vedula, Jason Ingyu Choi, Shervin Malmasi
| Challenge: | Large Language Models (LLMs) have given rise to generative recommenders . however, improving the generated content through user feedback is prohibitively expensive . |
| Approach: | They propose a generative explore-exploit method that exploits items with high engagement and actively explores hidden population preferences to improve recommendation quality. |
| Outcome: | The proposed approach exploits items with high engagement and actively explores hidden population preferences to improve recommendation quality. |
External Knowledge Acquisition for End-to-End Document-Oriented Dialog Systems (2023.eacl-main)
Copied to clipboard
| Challenge: | End-to-end neural models for conversational AI often assume that a response can be generated by considering only the knowledge acquired during training. |
| Approach: | They propose an architecture for document-oriented conversations with access to external knowledge sources. |
| Outcome: | The proposed architecture outperforms baseline models on the Wizard of Wikipedia dataset by 10.3% and 7.4%. |
Learning to Generate Examples for Semantic Processing Tasks (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent data augmentation techniques can help to deal with low resource settings, such as BERT, but they can hurt the results. |
| Approach: | They propose a neural approach to automatically learn to generate new examples using a pre-trained sequence-to-sequence model. |
| Outcome: | The proposed approach outperforms existing methods on text classification and natural language inference tasks by 10%. |
GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples (2020.acl-main)
Copied to clipboard
| Challenge: | Recent Transformer-based architectures provide impressive results in many NLP tasks, but obtaining high-quality annotated data is expensive and time consuming. |
| Approach: | They propose a semisupervised learning method that ex- tends the fine-tuning of BERT-like architectures with unlabeled data in a generative adversarial setting. |
| Outcome: | The proposed method reduces the requirement for annotated examples while achieving good performance in sentence classification tasks. |
Wizard of Tasks: A Novel Conversational Dataset for Solving Real-World Tasks in Conversational Settings (2022.coling-1)
Copied to clipboard
Jason Ingyu Choi, Saar Kuzi, Nikhita Vedula, Jie Zhao, Giuseppe Castellucci, Marcus Collins, Shervin Malmasi, Oleg Rokhlenko, Eugene Agichtein
| Challenge: | Existing Conversational Task Assistants fail to provide a comprehensive natural conversation that includes search, context-aware QA, step-by-step instructions. |
| Approach: | They present a corpus of conversations in two domains: cooking and home improvement . they crowd-sourced 549 conversations with an asynchronous Wizard-of-Oz setup . |
| Outcome: | The proposed model performs well in both Intent Classification and Abstractive Question Answering tasks, but the performance is poor on AQA tasks. |
Generative Product Recommendations for Implicit Superlative Queries (2025.naacl-srw)
Copied to clipboard
| Challenge: | Existing retrieval and ranking systems struggle with implicit superlative queries . lack of explicit attribute mentions and complexity of the query complicates ranking . |
| Approach: | They propose a four-point schema for annotating the best product candidates for superlative queries . they propose pointwise, deliberated pointwise and pairwise methods to analyze the results . |
| Outcome: | The proposed schema can be used to rank products with implicit attributes and reason over them. |
Learning to Solve NLP Tasks in an Incremental Number of Languages (2021.acl-short)
Copied to clipboard
| Challenge: | Existing models that support multiple languages are expensive and time-consuming to retrain . retraining only with the new language data will result in Catastrophic Forgetting of previously acquired knowledge. |
| Approach: | They propose a Continual Learning strategy that updates a model to support new languages over time while maintaining consistent results on previously learned languages. |
| Outcome: | The proposed model is based on an existing model that "teaches" to a student while the student is also trained on a new language. |
Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks. |
| Approach: | They propose to make Large Language Models (LLMs) operating in 0-shot or few-shot settings as efficient as 0- shot text classifiers by leveraging a small number of samples. |
| Outcome: | The proposed model is able to perform better on multiple datasets than existing models on 0-shot or few-shot settings. |
Follow-on Question Suggestion via Voice Hints for Voice Assistants (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Query suggestion is a standard feature of screen-based search experiences, but it is not trivial to implement in voice-based settings. |
| Approach: | They propose a task of suggesting questions with compact voice hints to allow users to ask follow-up questions. |
| Outcome: | The proposed approach is based on a dataset of 6681 input questions and human written hints and is highly linguistically motivated. |