Daniel Zeng


2023

pdf bib
LDM2: A Large Decision Model Imitating Human Cognition with Dynamic Memory Enhancement
Xingjin Wang | Linjing Li | Daniel Zeng
Findings of the Association for Computational Linguistics: EMNLP 2023

With the rapid development of large language models (LLMs), it is highly demanded that LLMs can be adopted to make decisions to enable the artificial general intelligence. Most approaches leverage manually crafted examples to prompt the LLMs to imitate the decision process of human. However, designing optimal prompts is difficult and the patterned prompts can hardly be generalized to more complex environments. In this paper, we propose a novel model named Large Decision Model with Memory (LDM2), which leverages a dynamic memory mechanism to construct dynamic prompts, guiding the LLMs in making proper decisions according to the faced state. LDM2 consists of two stages: memory formation and memory refinement. In the former stage, human behaviors are decomposed into state-action tuples utilizing the powerful summarizing ability of LLMs. Then, these tuples are stored in the memory, whose indices are generated by the LLMs, to facilitate the retrieval of the most relevant subset of memorized tuples based on the current state. In the latter stage, our LDM2 employs tree exploration to discover more suitable decision processes and enrich the memory by adding valuable state-action tuples. The dynamic circle of exploration and memory enhancement provides LDM2 a better understanding of the global environment. Extensive experiments conducted in two interactive environments have shown that our LDM2 outperforms the baselines in terms of both score and success rate, which demonstrates its effectiveness.

pdf bib
Modeling Conceptual Attribute Likeness and Domain Inconsistency for Metaphor Detection
Yuan Tian | Nan Xu | Wenji Mao | Daniel Zeng
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Metaphor detection is an important and challenging task in natural language processing, which aims to distinguish between metaphorical and literal expressions in text. Previous studies mainly leverage the incongruity of source and target domains and contextual clues for detection, neglecting similar attributes shared between source and target concepts in metaphorical expressions. Based on conceptual metaphor theory, these similar attributes are essential to infer implicit meanings conveyed by the metaphor. Under the guidance of conceptual metaphor theory, in this paper, we model the likeness of attribute for the first time and propose a novel Attribute Likeness and Domain Inconsistency Learning framework (AIDIL) for word-pair metaphor detection. Specifically, we propose an attribute siamese network to mine similar attributes between source and target concepts. We then devise a domain contrastive learning strategy to learn the semantic inconsistency of concepts in source and target domains. Extensive experiments on four datasets verify that our method significantly outperforms the previous state-of-the-art methods, and demonstrate the generalization ability of our method.

2020

pdf bib
Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs
Zikang Wang | Linjing Li | Daniel Zeng
Proceedings of the 28th International Conference on Computational Linguistics

Natural Language Inference (NLI) is a vital task in natural language processing. It aims to identify the logical relationship between two sentences. Most of the existing approaches make such inference based on semantic knowledge obtained through training corpus. The adoption of background knowledge is rarely seen or limited to a few specific types. In this paper, we propose a novel Knowledge Graph-enhanced NLI (KGNLI) model to leverage the usage of background knowledge stored in knowledge graphs in the field of NLI. KGNLI model consists of three components: a semantic-relation representation module, a knowledge-relation representation module, and a label prediction module. Different from previous methods, various kinds of background knowledge can be flexibly combined in the proposed KGNLI model. Experiments on four benchmarks, SNLI, MultiNLI, SciTail, and BNLI, validate the effectiveness of our model.