The search engine process is crucial for document content retrieval. For
Khmer documents, a tool is needed to extract essential keywords. Despite the
daily generation of significant Khmer content, Cambodians struggle to find
necessary documents due to the lack of an effective semantic searching tool.
Even Google does not deliver high accuracy for Khmer content. Semantic search
engines improve search results by employing advanced algorithms to understand
various content types. With the rise in Khmer digital content such as reports,
articles, and social media feedback enhanced search capabilities are essential.
This research proposes the first Khmer Semantic Search Engine (KSE), designed
to improve traditional Khmer search methods. Utilizing semantic matching
techniques and formally annotated semantic content, our tool extracts
meaningful keywords from user queries performs precise matching, and provides
the best matching offline documents and online URL documents. We propose two
semantic search frameworks based on keyword extraction and semantic search
matching. Additionally, we developed tools for data preparation, including
document addition and manual keyword extraction. To evaluate performance, we
created a ground truth dataset and discussed issues related to searching and
semantic search. Our findings show how understanding search term semantics can
lead to more accurate results.

该研究介绍了第一种高棉语义搜索引擎（KSE），旨在改进传统高棉搜索方法，利用语义匹配和注释的语义内容从用户查询中提取有意义的关键词，进行精确匹配，并提供最匹配的离线和在线文档。研究结果表明，理解搜索术语的语义可以带来更准确的结果。

高棉语义搜索引擎：数字信息访问和文档检索

Khmer Semantic Search Engine: Digital Information Access and Document  Retrieval

Large language models (LLMs) have demonstrated impressive capabilities in
general scenarios, exhibiting a level of aptitude that approaches, in some
aspects even surpasses, human-level intelligence. Among their numerous skills,
the translation abilities of LLMs have received considerable attention. In
contrast to traditional machine translation that focuses solely on
source-target mapping, LLM-based translation can potentially mimic the human
translation process that takes many preparatory steps to ensure high-quality
translation. This work aims to explore this possibility by proposing the MAPS
framework, which stands for Multi-Aspect Prompting and Selection. Specifically,
we enable LLMs to first analyze the given source text and extract three aspects
of translation-related knowledge: keywords, topics and relevant demonstrations
to guide the translation process. To filter out the noisy and unhelpful
knowledge, we employ a selection mechanism based on quality estimation.
Experiments suggest that MAPS brings significant and consistent improvements
over text-davinci-003 and Alpaca on eight translation directions from the
latest WMT22 test sets. Our further analysis shows that the extracted knowledge
is critical in resolving up to 59% of hallucination mistakes in translation.
Code is available at this https URL

本文提出了一个名为 MAPS 框架，通过多方面提示和选择的方式，使用大型语言模型分析源文本获取三个与翻译相关的知识方面：关键词、主题和相关演示，并通过质量估计的机制过滤噪音和无用的知识来指导翻译过程，实验证明 MAPS 在最新的 WMT22 测试集上对八个翻译方向都有显著和一致的改进，为解决翻译中的幻觉错误提供了关键的知识。

探索使用大型语言模型进行人类化翻译策略

Exploring Human-Like Translation Strategy with Large Language Models

Neural sequence-to-sequence automatic speech recognition (ASR) systems are in
principle open vocabulary systems, when using appropriate modeling units. In
practice, however, they often fail to recognize words not seen during training,
e.g., named entities, numbers or technical terms. To alleviate this problem,
Huber et al. proposed to supplement an end-to-end ASR system with a word/phrase
memory and a mechanism to access this memory to recognize the words and phrases
correctly. In this paper we study, a) methods to acquire important words for
this memory dynamically and, b) the trade-off between improvement in
recognition accuracy of new words and the potential danger of false alarms for
those added words. We demonstrate significant improvements in the detection
rate of new words with only a minor increase in false alarms (F1 score 0.30
$\rightarrow$ 0.80), when using an appropriate number of new words. In
addition, we show that important keywords can be extracted from supporting
documents and used effectively.

本文研究了如何动态地获取重要的词汇以及将重要的关键词从支持性文档中提取并用于标记单词记忆，以显著提高新词的检测率，并在只添加少量单词的情况下仅轻微增加误报率。