With contributions from the open-source community, a vast amount of instruction tuning (IT) data has emerged. Given the significant resource allocation required by training and evaluating models, it is advantageous to have an efficient method for selecting high-quality IT data. However, existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset. In this paper, we propose an industrial-friendly, expert-aligned and diversity-preserved instruction data selection method: Clustering and Ranking (CaR). CaR consists of two steps. The first step involves ranking instruction pairs using a scoring model that is well aligned with expert preferences (achieving an accuracy of 84.25%). The second step involves preserving dataset diversity through a clustering process. In our experiment, CaR selected a subset containing only 1.96% of Alpaca’s IT data, yet the underlying AlpaCaR model trained on this subset outperforms Alpaca by an average of 32.1% in GPT-4 evaluations. Furthermore, our method utilizes small models (550M parameters) and requires only 11.2% of the monetary cost compared to existing methods, making it easily deployable in industrial scenarios.

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.

Quality estimation (QE) is a crucial technique for evaluating the quality of machine translations without the need for reference translations. This paper focuses on Huawei Translation Services Center’s (HW-TSC’s) submission to the sentence-level QE shared task, named LLMs-enhanced-CrossQE. Our system builds upon the CrossQE architecture from our submission from last year, which consists of a multilingual base model and a task-specific downstream layer. The model input is a concatenation of the source and the translated sentences. To enhance performance, we fine-tuned and ensembled multiple base models, including XLM-R, InfoXLM, RemBERT, and CometKiwi. Specifically, we employed two pseudo-data generation methods: 1) a diverse pseudo-data generation method based on the corruption-based data augmentation technique introduced last year, and 2) a pseudo-data generation method that simulates machine translation errors using large language models (LLMs). Our results demonstrate that the system achieves outstanding performance on sentence-level QE test sets.

The paper presents the submission by HW-TSC in the WMT 2024 Quality-informed Automatic Post Editing (QEAPE) shared task for the English-Hindi (En-Hi) and English-Tamil (En-Ta) language pair. We use LLM for En-Hi and Transformer for EN-ta respectively. For LLM, we first continue pertrain the Llama3, and then use the real APE data to SFT the pre-trained LLM. As for the transformer in En-Ta, we first pre-train a Machine Translation (MT) model by utilizing MT data collected from the web. Then, we fine-tune the model by employing real APE data.We also use the data augmentation method to enhance our model. Specifically, we incorporate candidate translations obtained from an external Machine Translation (MT) system.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 MT 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 HTER by -15.99 points and -0.47 points on En-Hi and En-Ta, respectively.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.