首页> 外文期刊>Audio, Speech, and Language Processing, IEEE Transactions on >Comparing Stochastic Approaches to Spoken Language Understanding in Multiple Languages
【24h】

Comparing Stochastic Approaches to Spoken Language Understanding in Multiple Languages

机译:比较使用多种语言进行口语理解的随机方法

获取原文
获取原文并翻译 | 示例
       

摘要

One of the first steps in building a spoken language understanding (SLU) module for dialogue systems is the extraction of flat concepts out of a given word sequence, usually provided by an automatic speech recognition (ASR) system. In this paper, six different modeling approaches are investigated to tackle the task of concept tagging. These methods include classical, well-known generative and discriminative methods like Finite State Transducers (FSTs), Statistical Machine Translation (SMT), Maximum Entropy Markov Models (MEMMs), or Support Vector Machines (SVMs) as well as techniques recently applied to natural language processing such as Conditional Random Fields (CRFs) or Dynamic Bayesian Networks (DBNs). Following a detailed description of the models, experimental and comparative results are presented on three corpora in different languages and with different complexity. The French MEDIA corpus has already been exploited during an evaluation campaign and so a direct comparison with existing benchmarks is possible. Recently collected Italian and Polish corpora are used to test the robustness and portability of the modeling approaches. For all tasks, manual transcriptions as well as ASR inputs are considered. Additionally to single systems, methods for system combination are investigated. The best performing model on all tasks is based on conditional random fields. On the MEDIA evaluation corpus, a concept error rate of 12.6% could be achieved. Here, additionally to attribute names, attribute values have been extracted using a combination of a rule-based and a statistical approach. Applying system combination using weighted ROVER with all six systems, the concept error rate (CER) drops to 12.0%.
机译:建立用于对话系统的口语理解(SLU)模块的第一步之一是从给定的单词序列中提取平面概念,通常由自动语音识别(ASR)系统提供。在本文中,研究了六种不同的建模方法来解决概念标记的任务。这些方法包括经典的,众所周知的生成和判别方法,例如有限状态换能器(FST),统计机器翻译(SMT),最大熵马尔可夫模型(MEMM)或支持向量机(SVM)以及最近应用于自然的技术语言处理,例如条件随机字段(CRF)或动态贝叶斯网络(DBN)。在对模型进行了详细描述之后,在三种语料库上以不同的语言和不同的复杂性给出了实验和比较结果。在评估活动中已经利用了法国MEDIA语料库,因此可以与现有基准进行直接比较。最近收集的意大利和波兰语料库用于测试建模方法的鲁棒性和可移植性。对于所有任务,都将考虑手动转录以及ASR输入。除了单个系统,还研究了系统组合的方法。在所有任务上表现最佳的模型是基于条件随机字段的。在MEDIA评估语料库上,概念错误率可以达到12.6%。在这里,除了属性名称之外,还使用基于规则的方法和统计方法的组合来提取属性值。将加权ROVER与所有六个系统一起应用系统组合,概念错误率(CER)降至12.0%。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号