Yichun Zhao


2024

pdf
Probe Then Retrieve and Reason: Distilling Probing and Reasoning Capabilities into Smaller Language Models
Yichun Zhao | Shuheng Zhou | Huijia Zhu
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Step-by-step reasoning methods, such as the Chain-of-Thought (CoT), have been demonstrated to be highly effective in harnessing the reasoning capabilities of Large Language Models (LLMs). Recent research efforts have sought to distill LLMs into Small Language Models (SLMs), with a significant focus on transferring the reasoning capabilities of LLMs to SLMs via CoT. However, the outcomes of CoT distillation are inadequate for knowledge-intensive reasoning tasks. This is because generating accurate rationales requires crucial factual knowledge, which SLMs struggle to retain due to their parameter constraints. We propose a retrieval-based CoT distillation framework, named Probe then Retrieve and Reason (PRR), which distills the question probing and reasoning capabilities from LLMs into SLMs. We train two complementary distilled SLMs, a probing model and a reasoning model, in tandem. When presented with a new question, the probing model first identifies the necessary knowledge to answer it, generating queries for retrieval. Subsequently, the reasoning model uses the retrieved knowledge to construct a step-by-step rationale for the answer. In knowledge-intensive reasoning tasks, such as StrategyQA and OpenbookQA, our distillation framework yields superior performance for SLMs compared to conventional methods, including simple CoT distillation and knowledge-augmented distillation using raw questions.

2022

pdf
TransAdv: A Translation-based Adversarial Learning Framework for Zero-Resource Cross-Lingual Named Entity Recognition
Yichun Zhao | Jintao Du | Gongshen Liu | Huijia Zhu
Findings of the Association for Computational Linguistics: EMNLP 2022

Zero-Resource Cross-Lingual Named Entity Recognition aims at training an NER model of the target language using only labeled source language data and unlabeled target language data. Existing methods are mainly divided into three categories: model transfer based, data transfer based and knowledge transfer based. Each method has its own disadvantages, and combining more than one of them often leads to better performance. However, the performance of data transfer based methods is often limited by inevitable noise in the translation process. To handle the problem, we propose a framework named TransAdv to mitigate lexical and syntactic errors of word-by-word translated data, better utilizing the data by multi-level adversarial learning and multi-model knowledge distillation. Extensive experiments are conducted over 6 target languages with English as the source language, and the results show that TransAdv achieves competitive performance to the state-of-the-art models.

pdf
A Multi-Task Dual-Tree Network for Aspect Sentiment Triplet Extraction
Yichun Zhao | Kui Meng | Gongshen Liu | Jintao Du | Huijia Zhu
Proceedings of the 29th International Conference on Computational Linguistics

Aspect Sentiment Triplet Extraction (ASTE) aims at extracting triplets from a given sentence, where each triplet includes an aspect, its sentiment polarity, and a corresponding opinion explaining the polarity. Existing methods are poor at detecting complicated relations between aspects and opinions as well as classifying multiple sentiment polarities in a sentence. Detecting unclear boundaries of multi-word aspects and opinions is also a challenge. In this paper, we propose a Multi-Task Dual-Tree Network (MTDTN) to address these issues. We employ a constituency tree and a modified dependency tree in two sub-tasks of Aspect Opinion Co-Extraction (AOCE) and ASTE, respectively. To enhance the information interaction between the two sub-tasks, we further design a Transition-Based Inference Strategy (TBIS) that transfers the boundary information from tags of AOCE to ASTE through a transition matrix. Extensive experiments are conducted on four popular datasets, and the results show the effectiveness of our model.