论文信息 - Richer syntactic dependencies for structured language modeling

Richer syntactic dependencies for structured language modeling

The paper investigates the use of richer syntactic dependencies in the structured language model (SLM). We present two simple methods of enriching the dependencies in the syntactic parse trees used for initializing the SLM. We evaluate the impact of both methods on the perplexity (PPL) and word-error-rate (WER, N-best rescoring) performance of the SLM. We show that the new model achieves an improvement in PPL and WER over the baseline results reported using the SLM on the UPenn Treebank and Wall Street Journal (WSJ) corpora, respectively.

Peng Xu | Ciprian Chelba | Ciprian Chelba | P. Xu

[1] Beatrice Santorini,et al. Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[2] Janet M. Baker,et al. The Design for the Wall Street Journal-based CSR Corpus , 1992, HLT.

[3] Brian Roark,et al. Robust Probabilistic Predictive Syntactic Processing , 2001, ArXiv.

[4] Providen e RIe. Immediate-Head Parsing for Language Models , 2001 .

[5] Eugene Charniak,et al. A Maximum-Entropy-Inspired Parser , 2000, ANLP.

[6] Adwait Ratnaparkhi,et al. A Linear Observed Time Statistical Parser Based on Maximum Entropy Models , 1997, EMNLP.

[7] Frederick Jelinek,et al. Structured language modeling , 2000, Comput. Speech Lang..

[8] Mark Johnson,et al. Robust probabilistic predictive syntactic processing: motivations, models, and applications , 2001 .

[9] D. Rubin,et al. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[10] Michael Collins,et al. Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.