Papers by James Gung
NatCS: Eliciting Natural Customer Support Dialogues (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing task-oriented dialogue datasets do not reflect the expected characteristics of real customer support conversations. |
| Approach: | They propose to collect real customer service conversations from real conversations . they show that dialogue act annotations provide more effective training data . |
| Outcome: | The proposed approach is more representative of real human-to-human conversations compared to existing dialogue datasets . the proposed approach can be used to facilitate open research in natural dialog systems . |
Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification (2023.emnlp-main)
Copied to clipboard
Mujeen Sung, James Gung, Elman Mansimov, Nikolaos Pappas, Raphael Shu, Salvatore Romeo, Yi Zhang, Vittorio Castelli
| Challenge: | Existing methods for IC training do not provide sufficient examples for each intent . a novel pre-training method is proposed to provide a better understanding of intents . |
| Approach: | They propose a method that uses contrastive learning with intent psuedo-labels to produce embeddings that are well-suited for IC tasks. |
| Outcome: | The proposed method achieves 5.4% and 4.0% higher accuracy than the current state-of-the-art method on four IC datasets. |
CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions (2025.acl-long)
Copied to clipboard
Tamer Alkhouli, Katerina Margatina, James Gung, Raphael Shu, Claudia Zaghi, Monica Sunkara, Yi Zhang
| Challenge: | Current benchmarks lack comprehensive assessment of large language models in complex conversational scenarios. |
| Approach: | They introduce a conversational benchmark to evaluate function-calling capabilities of large language models. |
| Outcome: | The proposed benchmark evaluates the function-calling capabilities and response quality of large language models. |
PropBank Comes of Age—Larger, Smarter, and more Diverse (2022.starsem-1)
Copied to clipboard
Sameer Pradhan, Julia Bonn, Skatje Myers, Kathryn Conger, Tim O’gorman, James Gung, Kristin Wright-bettner, Martha Palmer
| Challenge: | The PropBank has been used for semantic role labeling for over 20 years . it includes non-verbal predicates, adjectives, prepositions and multi-word expressions . |
| Approach: | They describe the evolution of the PropBank approach to semantic role labeling over the last 20 years . they describe the substantial effort that has gone into ensuring consistency and reliability of the various annotated datasets and resources . |
| Outcome: | The PropBank has been used for more than 20 years to test semantic role labeling systems. |
The New Propbank: Aligning Propbank with AMR through POS Unification (L18-1)
Copied to clipboard
| Challenge: | Existing Propbank corpus converts sense labels to a format which is more compatible with AMR and more robust to sparsity. |
| Approach: | They propose a corpus which converts existing Propbank sense labels to a new unified format which is more compatible with AMR and more robust to sparsity. |
| Outcome: | The proposed format is more compatible with AMR and robust to sparsity. |
Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In task-oriented semantic parsing, the system aims to translate users’ utterances in natural language to machine-interpretable programs (API calls) However, Large Language Models (LLMs) are known to hallucinate and therefore pose a formidable challenge in constraining generated content. |
| Approach: | They propose to use large language models to translate user's utterances to machine-interpretable programs (API calls) they identify constraints violations in task-oriented utterrances and define fine-grained metrics that complement traditional ones. |
| Outcome: | The proposed methods reduce constraints violations and improve quality of the generated API calls, but require careful consideration given their implementation complexity and latency. |
Structured List-Grounded Question Answering (2025.coling-main)
Copied to clipboard
| Challenge: | Document-grounded dialogue systems aim to answer user queries by leveraging external information. |
| Approach: | They propose a dataset to evaluate QA systems' ability to interpret and use structured lists . they use language models and model-based filtering processes to enhance data quality . |
| Outcome: | The proposed model outperforms baselines on the LIST2QA dataset . it shows that the proposed model is more accurate and complete than baselines . |