Papers by Bo-Hsiang Tseng
Actor-Double-Critic: Incorporating Model-Based Critic for Task-Oriented Dialogue Systems (2020.findings-emnlp)
Copied to clipboard
| Challenge: | In order to improve the sample-efficiency of deep reinforcement learning, we implemented imagination augmented agent (I2A) in spoken dialogue systems (SDS). |
| Approach: | They propose to use an actor-double-critic to improve the stability and overall performance of imagination augmented agent (I2A) in spoken dialogue systems. |
| Outcome: | The proposed model-based agent (ADC) improves the stability and sample-efficiency of deep reinforcement learning (DRL) on a restaurant booking task. |
CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues (2021.naacl-main)
Copied to clipboard
Bo-Hsiang Tseng, Shruti Bhargava, Jiarui Lu, Joel Ruben Antony Moniz, Dhivya Piraviperumal, Lin Li, Hong Yu
| Challenge: | Traditionally, anaphora resolution and ellipses resolution are limited in dialogues . despite rapid progress in dialogue systems, several difficulties remain . |
| Approach: | They propose a joint learning framework for modeling coreference resolution and query rewriting for complex, multi-turn dialogues. |
| Outcome: | The proposed model outperforms the state-of-the-art model on a rewritten dialogue dataset. |
Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for dialogue state tracking are based on Graph Attention Networks . if the relationship between slots and values is modelled explicitly, this can be improved . |
| Approach: | They propose a model architecture that augments GPT-2 with Graph Attention Networks to allow sequential prediction of slot values. |
| Outcome: | The proposed architecture improves performance against a strong GPT-2 baseline and with sparsely supervised training. |
Can Large Language Models Understand Context? (2024.findings-eacl)
Copied to clipboard
Yilun Zhu, Joel Moniz, Shruti Bhargava, Jiarui Lu, Dhivya Piraviperumal, Site Li, Yuan Zhang, Hong Yu, Bo-Hsiang Tseng
| Challenge: | Existing evaluation methodologies for Large Language Models (LLMs) have been inadequate to evaluate their ability to understand contextual features. |
| Approach: | They propose a benchmark to assess large language models' ability to understand context by adapting existing datasets to suit their evaluation. |
| Outcome: | The proposed model performs better under the in-context learning pretraining scenario than state-of-the-art models. |
SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking (2024.eacl-long)
Copied to clipboard
| Challenge: | In-context learning with Large Language Models (LLMs) is a promising avenue of research in Dialog State Tracking (DST). |
| Approach: | They propose a data generation framework tailored for Dialog State Tracking that uses large language models to synthesize natural, coherent, and free-flowing dialogues with DST annotations. |
| Outcome: | The proposed framework improves joint goal accuracy by 4-5% over the zero-shot baseline on MultiWOZ 2.1 and 2.4. |
ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution (2025.acl-long)
Copied to clipboard
Alexandru Coca, Mark Gaynor, Zhenxing Zhang, Jianpeng Cheng, Bo-Hsiang Tseng, Peter Boothroyd, Hector Martinez Alonso, Diarmuid O Seaghdha, Anders Johannsen
| Challenge: | ASPERA framework allows developers to guide LLM generation of high-quality tasks based on user queries, simulation state and corresponding validation programs. |
| Approach: | They develop a framework comprising an assistant library simulation and a human-assisted LLM data generation engine to guide LLM generation of high-quality tasks . they use a dataset to evaluate 250 tasks generated using ASPERA . |
| Outcome: | The proposed framework can guide LLM generation of high-quality tasks tackling data availability and evaluation robustness challenges. |
More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Ranking (2023.findings-eacl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) can track only slots drawn from a database or domain ontology. |
| Approach: | They propose a framework for generating synthetic schemas which uses tree-based ranking to optimise lexical diversity and semantic faithfulness. |
| Outcome: | The proposed framework improves the generalisation of strong baselines by augmenting training data with prompts generated by the framework. |
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (D18-1)
Copied to clipboard
Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, Milica Gašić
| Challenge: | a dataset of 10k human-human written conversations is one order of magnitude larger than previous annotated task-oriented corpora. |
| Approach: | They propose to collect 10k human-human written conversations from a crowd-sourced dataset using crowd-sourcing. |
| Outcome: | The proposed dataset is one order of magnitude larger than previous annotated task-oriented corpora and shows the usability of the data and sets a baseline for future studies. |
Evaluating Evaluation Metrics – The Mirage of Hallucination Detection (2025.findings-emnlp)
Copied to clipboard
Atharva Kulkarni, Yuan Zhang, Joel Ruben Antony Moniz, Xiou Ge, Bo-Hsiang Tseng, Dhivya Piraviperumal, Swabha Swayamdipta, Hong Yu
| Challenge: | a large-scale empirical evaluation of hallucination detection metrics is conducted . hallucinosity is a significant obstacle to the reliability and widespread adoption of language models . |
| Approach: | They conduct large-scale empirical evaluation of hallucination detection metrics . they compare hallucinian language models, language models and decoding methods . |
| Outcome: | The results show that the evaluations of hallucination detection metrics fail to align with human judgments, they say . they also show that evaluations with LLM-based evaluation yield the best overall results . |
A Generative Model for Joint Natural Language Understanding and Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Natural language understanding (NLU) and natural language generation (NLG) have opposite goals. |
| Approach: | They propose a generative model which couples NLU and NLG through a shared latent variable. |
| Outcome: | The proposed model achieves state-of-the-art performance on two dialogue datasets with flat and tree-structured formal representations. |
Feudal Reinforcement Learning for Dialogue Management in Large Domains (N18-2)
Copied to clipboard
Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Stefan Ultes, Lina M. Rojas-Barahona, Bo-Hsiang Tseng, Milica Gašić
| Challenge: | Reinforcement learning (RL) is a promising approach to model dialogue policy optimisation but fails to scale to large domains due to the curse of dimensionality. |
| Approach: | They propose a novel approach to dialogue policy optimisation using reinforcement learning . they propose to decompose the decision into two steps using a domain ontology . |
| Outcome: | The proposed architecture outperforms state-of-the-art in several dialogue domains without any additional reward signal. |
Semi-Supervised Bootstrapping of Dialogue State Trackers for Task-Oriented Modelling (D19-1)
Copied to clipboard
| Challenge: | Existing systems rely on modular, domain-focused frameworks for analyzing complex problems. |
| Approach: | They propose semi-supervised learning methods that can reduce the amount of required intermediate labelling by leveraging un-annotated data instead of transcribed utterances. |
| Outcome: | The proposed model reduces the amount of turn-level annotations by 30% while maintaining equivalent system performance. |
Transferable Dialogue Systems and User Simulators (2021.acl-long)
Copied to clipboard
| Challenge: | a lack of training data is limiting the development of dialogue systems . we develop a framework for creating dialogue data through self-play between agents . |
| Approach: | They propose a framework that can incorporate new dialogue scenarios through self-play between two agents. |
| Outcome: | The proposed framework is highly effective in bootstrapping the performance of two agents in transfer learning. |