Hong Cheng


2024

pdf bib
LLMEdgeRefine: Enhancing Text Clustering with LLM-Based Boundary Point Refinement
Zijin Feng | Luyang Lin | Lingzhi Wang | Hong Cheng | Kam-Fai Wong
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

Text clustering is a fundamental task in natural language processing with numerous applications. However, traditional clustering methods often struggle with domain-specific fine-tuning and the presence of outliers. To address these challenges, we introduce LLMEdgeRefine, an iterative clustering method enhanced by large language models (LLMs), focusing on edge points refinement. LLMEdgeRefine enhances current clustering methods by creating super-points to mitigate outliers and iteratively refining clusters using LLMs for improved semantic coherence. Our method demonstrates superior performance across multiple datasets, outperforming state-of-the-art techniques, and offering robustness, adaptability, and cost-efficiency for diverse text clustering applications.

pdf bib
Distributional Inclusion Hypothesis and Quantifications: Probing for Hypernymy in Functional Distributional Semantics
Chun Lo | Wai Lam | Hong Cheng | Guy Emerson
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Functional Distributional Semantics (FDS) models the meaning of words by truth-conditional functions. This provides a natural representation for hypernymy but no guarantee that it can be learnt when FDS models are trained on a corpus. In this paper, we probe into FDS models and study the representations learnt, drawing connections between quantifications, the Distributional Inclusion Hypothesis (DIH), and the variational-autoencoding objective of FDS model training. Using synthetic data sets, we reveal that FDS models learn hypernymy on a restricted class of corpus that strictly follows the DIH. We further introduce a training objective that both enables hypernymy learning under the reverse of the DIH and improves hypernymy detection from real corpora.

pdf bib
PACAR: Automated Fact-Checking with Planning and Customized Action Reasoning Using Large Language Models
Xiaoyan Zhao | Lingzhi Wang | Zhanghao Wang | Hong Cheng | Rui Zhang | Kam-Fai Wong
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

In an era characterized by the rapid proliferation of information, the pervasive issues of misinformation and disinformation have significantly impacted numerous individuals. Consequently, the evaluation of information’s truthfulness and accuracy has garnered substantial attention among researchers. In this work, we present a novel fact-checking framework called PACAR, fact-checking based on planning and customized action reasoning using LLMs. It comprises four modules: a claim decomposer with self-reflection, an LLM-centric planner module, an executor for carrying out planned actions, and a verifier module that assesses veracity and generates explanations based on the overall reasoning process. Unlike previous work that employs single-path decision-making and single-step verdict prediction, PACAR focuses on the use of LLMs in dynamic planning and execution of actions. Furthermore, in contrast to previous work that relied primarily on general reasoning, we introduce tailored actions such as numerical reasoning and entity disambiguation to effectively address potential challenges in fact-checking. Our PACAR framework, incorporating LLM-centric planning along with customized action reasoning, significantly outperforms baseline methods across three datasets from different domains and with varying complexity levels. Additional experiments, including multidimensional and sliced observations, demonstrate the effectiveness of PACAR and offer valuable insights for the advancement of automated fact-checking.

2023

pdf bib
Functional Distributional Semantics at Scale
Chun Hei Lo | Hong Cheng | Wai Lam | Guy Emerson
Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)

Functional Distributional Semantics is a linguistically motivated framework for modelling lexical and sentence-level semantics with truth-conditional functions using distributional information. Previous implementations of the framework focus on subjectverbobject (SVO) triples only, which largely limits the contextual information available for training and thus the capability of the learnt model. In this paper, we discuss the challenges of extending the previous architectures to training on arbitrary sentences. We address the challenges by proposing a more expressive lexical model that works over a continuous semantic space. This improves the flexibility and computational efficiency of the model, as well as its compatibility with present-day machine-learning frameworks. Our proposal allows the model to be applied to a wider range of semantic tasks, and improved performances are demonstrated from experimental results.

2022

pdf bib
Partner Personas Generation for Dialogue Response Generation
Hongyuan Lu | Wai Lam | Hong Cheng | Helen Meng
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Incorporating personas information allows diverse and engaging responses in dialogue response generation. Unfortunately, prior works have primarily focused on self personas and have overlooked the value of partner personas. Moreover, in practical applications, the availability of the gold partner personas is often not the case. This paper attempts to tackle these issues by offering a novel framework that leverages automatic partner personas generation to enhance the succeeding dialogue response generation. Our framework employs reinforcement learning with a dedicatedly designed critic network for reward judgement. Experimental results from automatic and human evaluations indicate that our framework is capable of generating relevant, interesting, coherent and informative partner personas, even compared to the ground truth partner personas. This enhances the succeeding dialogue response generation, which surpasses our competitive baselines that condition on the ground truth partner personas.

pdf bib
Semantic Composition with PSHRG for Derivation Tree Reconstruction from Graph-Based Meaning Representations
Chun Hei Lo | Wai Lam | Hong Cheng
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We introduce a data-driven approach to generating derivation trees from meaning representation graphs with probabilistic synchronous hyperedge replacement grammar (PSHRG). SHRG has been used to produce meaning representation graphs from texts and syntax trees, but little is known about its viability on the reverse. In particular, we experiment on Dependency Minimal Recursion Semantics (DMRS) and adapt PSHRG as a formalism that approximates the semantic composition of DMRS graphs and simultaneously recovers the derivations that license the DMRS graphs. Consistent results are obtained as evaluated on a collection of annotated corpora. This work reveals the ability of PSHRG in formalizing a syntax–semantics interface, modelling compositional graph-to-tree translations, and channelling explainability to surface realization.

pdf bib
On Controlling Fallback Responses for Grounded Dialogue Generation
Hongyuan Lu | Wai Lam | Hong Cheng | Helen Meng
Findings of the Association for Computational Linguistics: ACL 2022

Dialogue agents can leverage external textual knowledge to generate responses of a higher quality. To our best knowledge, most existing works on knowledge grounded dialogue settings assume that the user intention is always answerable. Unfortunately, this is impractical as there is no guarantee that the knowledge retrievers could always retrieve the desired knowledge. Therefore, this is crucial to incorporate fallback responses to respond to unanswerable contexts appropriately while responding to the answerable contexts in an informative manner. We propose a novel framework that automatically generates a control token with the generator to bias the succeeding response towards informativeness for answerable contexts and fallback for unanswerable contexts in an end-to-end manner. Since no existing knowledge grounded dialogue dataset considers this aim, we augment the existing dataset with unanswerable contexts to conduct our experiments. Automatic and human evaluation results indicate that naively incorporating fallback responses with controlled text generation still hurts informativeness for answerable context. In contrast, our proposed framework effectively mitigates this problem while still appropriately presenting fallback responses to unanswerable contexts. Such a framework also reduces the extra burden of the additional classifier and the overheads introduced in the previous works, which operates in a pipeline manner.