Papers by Bo-Hsiang Tseng

13 papers
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

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

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

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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations