Daimeng Wei
YOU?
Author Swipe
View article: A method for improving multilingual quality and diversity of instruction fine-tuning datasets
A method for improving multilingual quality and diversity of instruction fine-tuning datasets Open
Multilingual Instruction Fine-Tuning (IFT) is essential for enabling large language models (LLMs) to generalize effectively across diverse linguistic and cultural contexts. However, the scarcity of high-quality multilingual training data a…
View article: RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning
RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning Open
Logs constitute a form of evidence signaling the operational status of software systems. Automated log anomaly detection is crucial for ensuring the reliability of modern software systems. However, existing approaches face significant limi…
View article: Generative Annotation for ASR Named Entity Correction
Generative Annotation for ASR Named Entity Correction Open
End-to-end automatic speech recognition systems often fail to transcribe domain-specific named entities, causing catastrophic failures in downstream tasks. Numerous fast and lightweight named entity correction (NEC) models have been propos…
View article: MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis
MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis Open
Despite doubts on data quality, instruction synthesis has been widely applied into instruction tuning (IT) of LLMs as an economic and rapid alternative. Recent endeavors focus on improving data quality for synthesized instruction pairs in …
View article: Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation
Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation Open
Large language model (LLM) shows promising performances in a variety of downstream tasks, such as machine translation (MT). However, using LLMs for translation suffers from high computational costs and significant latency. Based on our eva…
View article: Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement
Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement Open
Recent research has shown that large language models (LLMs) can enhance translation quality through self-refinement. In this paper, we build on this idea by extending the refinement from sentence-level to document-level translation, specif…
View article: DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation
DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation Open
Document-level context is crucial for handling discourse challenges in text-to-text document-level machine translation (MT). Despite the increased discourse challenges introduced by noise from automatic speech recognition (ASR), the integr…
View article: R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning Open
Despite recent breakthroughs in reasoning-enhanced large language models (LLMs) like DeepSeek-R1, incorporating inference-time reasoning into machine translation (MT), where human translators naturally employ structured, multi-layered reas…
View article: Chain-of-Description: What I can understand, I can put into words
Chain-of-Description: What I can understand, I can put into words Open
In this paper, we propose a novel strategy defined as Chain-of-Description (CoD) Prompting, tailored for Multi-Modal Large Language Models. This approach involves having the model first provide a detailed description of the multi-modal inp…
View article: Doc-Guided Sent2Sent++: A Sent2Sent++ Agent with Doc-Guided memory for Document-level Machine Translation
Doc-Guided Sent2Sent++: A Sent2Sent++ Agent with Doc-Guided memory for Document-level Machine Translation Open
The field of artificial intelligence has witnessed significant advancements in natural language processing, largely attributed to the capabilities of Large Language Models (LLMs). These models form the backbone of Agents designed to addres…
View article: M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models
M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models Open
With the widespread application of Large Language Models (LLMs) in the field of Natural Language Processing (NLP), enhancing their performance has become a research hotspot. This paper presents a novel multi-prompt ensemble decoding approa…
View article: Context-aware and Style-related Incremental Decoding framework for Discourse-Level Literary Translation
Context-aware and Style-related Incremental Decoding framework for Discourse-Level Literary Translation Open
This report outlines our approach for the WMT24 Discourse-Level Literary Translation Task, focusing on the Chinese-English language pair in the Constrained Track. Translating literary texts poses significant challenges due to the nuanced m…
View article: Machine Translation Advancements of Low-Resource Indian Languages by Transfer Learning
Machine Translation Advancements of Low-Resource Indian Languages by Transfer Learning Open
This paper introduces the submission by Huawei Translation Center (HW-TSC) to the WMT24 Indian Languages Machine Translation (MT) Shared Task. To develop a reliable machine translation system for low-resource Indian languages, we employed …
View article: Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain
Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain Open
This article introduces the submission status of the Translation into Low-Resource Languages of Spain task at (WMT 2024) by Huawei Translation Service Center (HW-TSC). We participated in three translation tasks: spanish to aragonese (es-ar…
View article: Exploring the traditional NMT model and Large Language Model for chat translation
Exploring the traditional NMT model and Large Language Model for chat translation Open
This paper describes the submissions of Huawei Translation Services Center(HW-TSC) to WMT24 chat translation shared task on English$\leftrightarrow$Germany (en-de) bidirection. The experiments involved fine-tuning models using chat data an…
View article: HW-TSC's Submission to the CCMT 2024 Machine Translation Tasks
HW-TSC's Submission to the CCMT 2024 Machine Translation Tasks Open
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to machine translation tasks of the 20th China Conference on Machine Translation (CCMT 2024). We participate in the bilingual machine translation task and mu…
View article: Choose the Final Translation from NMT and LLM hypotheses Using MBR Decoding: HW-TSC's Submission to the WMT24 General MT Shared Task
Choose the Final Translation from NMT and LLM hypotheses Using MBR Decoding: HW-TSC's Submission to the WMT24 General MT Shared Task Open
This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT24 general machine translation (MT) shared task, where we participate in the English to Chinese (en2zh) language pair. Similar to previous years' wor…
View article: LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation
LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation Open
Recent advancements in integrating speech information into large language models (LLMs) have significantly improved automatic speech recognition (ASR) accuracy. However, existing methods often constrained by the capabilities of the speech …
View article: An End-to-End Speech Summarization Using Large Language Model
An End-to-End Speech Summarization Using Large Language Model Open
ive Speech Summarization (SSum) aims to generate human-like text summaries from spoken content. It encounters difficulties in handling long speech input and capturing the intricate cross-modal mapping between long speech inputs and short t…
View article: Speaker-Smoothed kNN Speaker Adaptation for End-to-End ASR
Speaker-Smoothed kNN Speaker Adaptation for End-to-End ASR Open
Despite recent improvements in End-to-End Automatic Speech Recognition (E2E ASR) systems, the performance can degrade due to vocal characteristic mismatches between training and testing data, particularly with limited target speaker adapta…
View article: Cross-Domain Audio Deepfake Detection: Dataset and Analysis
Cross-Domain Audio Deepfake Detection: Dataset and Analysis Open
Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a sing…
View article: A Novel Paradigm Boosting Translation Capabilities of Large Language Models
A Novel Paradigm Boosting Translation Capabilities of Large Language Models Open
This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary P…
View article: DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators
DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators Open
Generally, the decoder-only large language models (LLMs) are adapted to context-aware neural machine translation (NMT) in a concatenating way, where LLMs take the concatenation of the source sentence (i.e., intra-sentence context) and the …
View article: R-BI: Regularized Batched Inputs enhance Incremental Decoding Framework for Low-Latency Simultaneous Speech Translation
R-BI: Regularized Batched Inputs enhance Incremental Decoding Framework for Low-Latency Simultaneous Speech Translation Open
Incremental Decoding is an effective framework that enables the use of an offline model in a simultaneous setting without modifying the original model, making it suitable for Low-Latency Simultaneous Speech Translation. However, this frame…