Bi-modal sentence structure for language modeling
| Autor: | G. Zavaliagkos, Kristine W. Ma, Marie Meteer |
|---|---|
| Rok vydání: | 2000 |
| Předmět: |
Structure (mathematical logic)
Linguistics and Language Perplexity Computer science business.industry Communication media_common.quotation_subject Speech recognition Word error rate computer.software_genre Language and Linguistics Computer Science Applications Modeling and Simulation Word recognition Conversation Computer Vision and Pattern Recognition Artificial intelligence Language model business computer Software Word (computer architecture) Sentence Natural language processing media_common |
| Zdroj: | Speech Communication. 31:51-67 |
| ISSN: | 0167-6393 |
| DOI: | 10.1016/s0167-6393(99)00060-6 |
| Popis: | According to discourse theories in linguistics, conversational utterances possess an informational structure. That is, each sentence consists of two components: the given and the new . The given refers to information that has previously been conveyed in the conversation such as that in That's interesting . The new section of a sentence introduces additional information that is new to the conversation such as the word interesting in the previous example. In this work, we take advantage of this inherent structure for the purpose of automatic conversational speech recognition by building sub-sentence discourse language models (LMs) to represent the bi-modal nature of each conversational sentence. The internal sentence structure is captured with a statistical sentence model regardless of whether the input sentences are linguistically or acoustically segmented. The proposed model is verified on the Switchboard corpus. The resulting model contributes to a reduction in both LM perplexity and word recognition error rate. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect