Xiaofeng Zhao


2024

pdf bib
HW-TSC 2024 Submission for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR)
Mengyao Piao | Su Chang | Yuang Li | Xiaosong Qiao | Xiaofeng Zhao | Yinglu Li | Min Zhang | Hao Yang
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)

The degree of semantic relatedness of two units of language has long been considered fundamental to understanding meaning. In this paper, we present the system of Huawei Translation Services Center (HW-TSC) for Task 1 of SemEval 2024, which aims to automatically measure the semantic relatedness of sentence pairs in African and Asian languages. The task dataset for this task covers about 14 different languages, These languages originate from five distinct language families and are predominantly spoken in Africa and Asia. For this shared task, we describe our proposed solutions, including ideas and the implementation steps of the task, as well as the outcomes of each experiment on the development dataset. To enhance the performance, we leverage these experimental outcomes and construct an ensemble one. Our results demonstrate that our system achieves impressive performance on test datasets in unsupervised track B and ranked first place for the Punjabi language pair.

pdf bib
HW-TSC at SemEval-2024 Task 9: Exploring Prompt Engineering Strategies for Brain Teaser Puzzles Through LLMs
Yinglu Li | Zhao Yanqing | Min Zhang | Yadong Deng | Aiju Geng | Xiaoqin Liu | Mengxin Ren | Yuang Li | Su Chang | Xiaofeng Zhao
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)

Large Language Models (LLMs) have demonstrated impressive performance on many Natural Language Processing (NLP) tasks. However, their ability to solve more creative, lateral thinking puzzles remains relatively unexplored. In this work, we develop methods to enhance the lateral thinking and puzzle-solving capabilities of LLMs. We curate a dataset of word-type and sentence-type brain teasers requiring creative problem-solving abilities beyond commonsense reasoning. We first evaluate the zero-shot performance of models like GPT-3.5 and GPT-4 on this dataset. To improve their puzzle-solving skills, we employ prompting techniques like providing reasoning clues and chaining multiple examples to demonstrate the desired thinking process. We also fine-tune the state-of-the-art Mixtral 7x8b LLM on ourdataset. Our methods enable the models to achieve strong results, securing 2nd and 3rd places in the brain teaser task. Our work highlights the potential of LLMs in acquiring complex reasoning abilities with the appropriate training. The efficacy of our approaches opens up new research avenues into advancing lateral thinking and creative problem-solving with AI systems.

pdf bib
HW-TSC at SemEval-2024 Task 5: Self-Eval? A Confident LLM System for Auto Prediction and Evaluation for the Legal Argument Reasoning Task
Xiaofeng Zhao | Xiaosong Qiao | Kaiwen Ou | Min Zhang | Su Chang | Mengyao Piao | Yuang Li | Yinglu Li | Ming Zhu | Yilun Liu
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)

In this article, we present an effective system for semeval-2024 task 5. The task involves assessing the feasibility of a given solution in civil litigation cases based on relevant legal provisions, issues, solutions, and analysis. This task demands a high level of proficiency in U.S. law and natural language reasoning. In this task, we designed a self-eval LLM system that simultaneously performs reasoning and self-assessment tasks. We created a confidence interval and a prompt instructing the LLM to output the answer to a question along with its confidence level. We designed a series of experiments to prove the effectiveness of the self-eval mechanism. In order to avoid the randomness of the results, the final result is obtained by voting on three results generated by the GPT-4. Our submission was conducted under zero-resource setting, and we achieved first place in the task with an F1-score of 0.8231 and an accuracy of 0.8673.

pdf bib
HW-TSC at TextGraphs-17 Shared Task: Enhancing Inference Capabilities of LLMs with Knowledge Graphs
Wei Tang | Xiaosong Qiao | Xiaofeng Zhao | Min Zhang | Chang Su | Yuang Li | Yinglu Li | Yilun Liu | Feiyu Yao | Shimin Tao | Hao Yang | He Xianghui
Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing

In this paper, we present an effective method for TextGraphs-17 Shared Task. This task requires selecting an entity from the candidate entities that is relevant to the given question and answer. The selection process is aided by utilizing the shortest path graph in the knowledge graph, connecting entities in the query to the candidate entity. This task aims to explore how to enhance LLMs output with KGs, although current LLMs have certain logical reasoning capabilities, they may not be certain about their own outputs, and the answers they produce may be correct by chance through incorrect paths. In this case, we have introduced a LLM prompt design strategy based on self-ranking and emotion. Specifically, we let the large model score its own answer choices to reflect its confidence in the answer. Additionally, we add emotional incentives to the prompts to encourage the model to carefully examine the questions. Our submissions was conducted under zero-resource setting, and we achieved the second place in the task with an F1-score of 0.8321.

2023

pdf bib
Leveraging Multilingual Knowledge Graph to Boost Domain-specific Entity Translation of ChatGPT
Min Zhang | Limin Liu | Zhao Yanqing | Xiaosong Qiao | Su Chang | Xiaofeng Zhao | Junhao Zhu | Ming Zhu | Song Peng | Yinglu Li | Yilun Liu | Wenbing Ma | Mengyao Piao | Shimin Tao | Hao Yang | Yanfei Jiang
Proceedings of Machine Translation Summit XIX, Vol. 2: Users Track

Recently, ChatGPT has shown promising results for Machine Translation (MT) in general domains and is becoming a new paradigm for translation. In this paper, we focus on how to apply ChatGPT to domain-specific translation and propose to leverage Multilingual Knowledge Graph (MKG) to help ChatGPT improve the domain entity translation quality. To achieve this, we extract the bilingual entity pairs from MKG for the domain entities that are recognized from source sentences. We then introduce these pairs into translation prompts, instructing ChatGPT to use the correct translations of the domain entities. To evaluate the novel MKG method for ChatGPT, we conduct comparative experiments on three Chinese-English (zh-en) test datasets constructed from three specific domains, of which one domain is from biomedical science, and the other two are from the Information and Communications Technology (ICT) industry — Visible Light Communication (VLC) and wireless domains. Experimental results demonstrate that both the overall translation quality of ChatGPT (+6.21, +3.13 and +11.25 in BLEU scores) and the translation accuracy of domain entities (+43.2%, +30.2% and +37.9% absolute points) are significantly improved with MKG on the three test datasets.

pdf bib
Empowering a Metric with LLM-assisted Named Entity Annotation: HW-TSC’s Submission to the WMT23 Metrics Shared Task
Zhanglin Wu | Yilun Liu | Min Zhang | Xiaofeng Zhao | Junhao Zhu | Ming Zhu | Xiaosong Qiao | Jingfei Zhang | Ma Miaomiao | Zhao Yanqing | Song Peng | Shimin Tao | Hao Yang | Yanfei Jiang
Proceedings of the Eighth Conference on Machine Translation

This paper presents the submission of Huawei Translation Service Center (HW-TSC) to the WMT23 metrics shared task, in which we submit two metrics: KG-BERTScore and HWTSC-EE-Metric. Among them, KG-BERTScore is our primary submission for the reference-free metric, which can provide both segment-level and system-level scoring. While HWTSC-EE-Metric is our primary submission for the reference-based metric, which can only provide system-level scoring. Overall, our metrics show relatively high correlations with MQM scores on the metrics tasks of previous years. Especially on system-level scoring tasks, our metrics achieve new state-of-the-art in many language pairs.

pdf bib
HW-TSC’s Participation in the WMT 2023 Automatic Post Editing Shared Task
Jiawei Yu | Min Zhang | Zhao Yanqing | Xiaofeng Zhao | Yuang Li | Su Chang | Yinglu Li | Ma Miaomiao | Shimin Tao | Hao Yang
Proceedings of the Eighth Conference on Machine Translation

The paper presents the submission by HW-TSC in the WMT 2023 Automatic Post Editing (APE) shared task for the English-Marathi (En-Mr) language pair. Our method encompasses several key steps. First, we pre-train an APE model by utilizing synthetic APE data provided by the official task organizers. Then, we fine-tune the model by employing real APE data. For data augmentation, we incorporate candidate translations obtained from an external Machine Translation (MT) system. Furthermore, we integrate the En-Mr parallel corpus from the Flores-200 dataset into our training data. To address the overfitting issue, we employ R-Drop during the training phase. Given that APE systems tend to exhibit a tendency of ‘over-correction’, we employ a sentence-level Quality Estimation (QE) system to select the final output, deciding between the original translation and the corresponding output generated by the APE model. Our experiments demonstrate that pre-trained APE models are effective when being fine-tuned with the APE corpus of a limited size, and the performance can be further improved with external MT augmentation. Our approach improves the TER and BLEU scores on the development set by -2.42 and +3.76 points, respectively.

pdf bib
HW-TSC at SemEval-2023 Task 7: Exploring the Natural Language Inference Capabilities of ChatGPT and Pre-trained Language Model for Clinical Trial
Xiaofeng Zhao | Min Zhang | Miaomiao Ma | Chang Su | Yilun Liu | Minghan Wang | Xiaosong Qiao | Jiaxin Guo | Yinglu Li | Wenbing Ma
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

In this paper, we describe the multi strategy system for SemEval-2022 Task 7, This task aims to determine whether a given statement is supported by one or two Clinical Trial reports, and to identify evidence that supports the statement. This is a task that requires high natural language inference capabilities. In Subtask 1, we compare our strategy based on prompt learning and ChatGPT with a baseline constructed using BERT in zero-shot setting, and validate the effectiveness of our strategy. In Subtask 2, we fine-tune DeBERTaV3 for classification without relying on the results from Subtask 1, and we observe that early stopping can effectively prevent model overfitting, which performs well in Subtask 2. In addition, we did not use any ensemble strategies. Ultimately, we achieved the 10th place in Subtask 1 and the 2nd place in Subtask 2.

2022

pdf bib
Partial Could Be Better than Whole. HW-TSC 2022 Submission for the Metrics Shared Task
Yilun Liu | Xiaosong Qiao | Zhanglin Wu | Su Chang | Min Zhang | Yanqing Zhao | Song Peng | Shimin Tao | Hao Yang | Ying Qin | Jiaxin Guo | Minghan Wang | Yinglu Li | Peng Li | Xiaofeng Zhao
Proceedings of the Seventh Conference on Machine Translation (WMT)

In this paper, we present the contribution of HW-TSC to WMT 2022 Metrics Shared Task. We propose one reference-based metric, HWTSC-EE-BERTScore*, and four referencefree metrics including HWTSC-Teacher-Sim, HWTSC-TLM, KG-BERTScore and CROSSQE. Among these metrics, HWTSC-Teacher-Sim and CROSS-QE are supervised, whereas HWTSC-EE-BERTScore*, HWTSC-TLM and KG-BERTScore are unsupervised. We use these metrics in the segment-level and systemlevel tracks. Overall, our systems achieve strong results for all language pairs on previous test sets and a new state-of-the-art in many sys-level case sets.

2021

pdf bib
A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
Shilei Liu | Xiaofeng Zhao | Bochao Li | Feiliang Ren | Longhui Zhang | Shujuan Yin
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Neural conversation models have shown great potentials towards generating fluent and informative responses by introducing external background knowledge. Nevertheless, it is laborious to construct such knowledge-grounded dialogues, and existing models usually perform poorly when transfer to new domains with limited training samples. Therefore, building a knowledge-grounded dialogue system under the low-resource setting is a still crucial issue. In this paper, we propose a novel three-stage learning framework based on weakly supervised learning which benefits from large scale ungrounded dialogues and unstructured knowledge base. To better cooperate with this framework, we devise a variant of Transformer with decoupled decoder which facilitates the disentangled learning of response generation and knowledge incorporation. Evaluation results on two benchmarks indicate that our approach can outperform other state-of-the-art methods with less training data, and even in zero-resource scenario, our approach still performs well.

pdf bib
A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling
Feiliang Ren | Longhui Zhang | Shujuan Yin | Xiaofeng Zhao | Shilei Liu | Bochao Li | Yaduo Liu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Table filling based relational triple extraction methods are attracting growing research interests due to their promising performance and their abilities on extracting triples from complex sentences. However, this kind of methods are far from their full potential because most of them only focus on using local features but ignore the global associations of relations and of token pairs, which increases the possibility of overlooking some important information during triple extraction. To overcome this deficiency, we propose a global feature-oriented triple extraction model that makes full use of the mentioned two kinds of global associations. Specifically, we first generate a table feature for each relation. Then two kinds of global associations are mined from the generated table features. Next, the mined global associations are integrated into the table feature of each relation. This “generate-mine-integrate” process is performed multiple times so that the table feature of each relation is refined step by step. Finally, each relation’s table is filled based on its refined table feature, and all triples linked to this relation are extracted based on its filled table. We evaluate the proposed model on three benchmark datasets. Experimental results show our model is effective and it achieves state-of-the-art results on all of these datasets. The source code of our work is available at: https://github.com/neukg/GRTE.