A Study on Richer Syntactic Dependencies for Structured Language Modeling
نویسندگان
چکیده
We study the impact of richer syntactic dependencies on the performance of the structured language model (SLM) along three dimensions: parsing accuracy (LP/LR), perplexity (PPL) and worderror-rate (WER, N-best re-scoring). We show that our models achieve an improvement in LP/LR, PPL and/or WER over the reported baseline results using the SLM on the UPenn Treebank and Wall Street Journal (WSJ) corpora, respectively. Analysis of parsing performance shows correlation between the quality of the parser (as measured by precision/recall) and the language model performance (PPL and WER). A remarkable fact is that the enriched SLM outperforms the baseline 3-gram model in terms of WER by 10% when used in isolation as a second pass (N-best re-scoring) language model.
منابع مشابه
Richer Syntactic Dependencies for Structured Language Modeling
two simple methods of enriching the dependencies in the syntactic parse trees used for intializing the structured language model (SLM) achieve improvement in perplexity (PPL) and word-error-rate (WER, N-best rescoring) over the baseline results reported using the SLM on the UPenn Treebank and Wall Street Journal (WSJ) corpora, respectively Structured Language Model ✔Generalize trigram modeling ...
متن کاملCombining semantic and syntactic structure for language modeling
Structured language models for speech recognition have been shown to remedy the weaknesses of n -gram models. All current structured language models, however, are limited in that they do not take into account dependencies between non-headwords. We show that non-headword dependencies contribute significantly to improved word error rate, and that a data-oriented parsing model trained on semantica...
متن کاملGender-Based investigation of the Syntactic Development of Iranian EFL Learners: A Focus on Processabilty Theory
Pienemann (1998, 2015) put forward Processability Theory to enlighten why language learners follow definite developmental paths. The aim of the present study was to run a comparative investigation into the difficulty order of different grammatical structures for male and female Iranian EFL learners predicted by Processability Theory. 185 Iranian university students took part in this study. They...
متن کاملMaximum Entropy Language Modeling with Non-Local and Syntactic Dependencies
Standard N -gram language models exploit information only from the immediate past to predict the future word. To improve the performance of a language model, two di erent kinds of long-range dependence, the syntactic structure and the topic of sentences are taken into consideration. The likelihood of many words varies greatly with the topic of discussion and topics capture this di erence. Synta...
متن کاملSmoothing issues in the structured language model
The Structured Language Model (SLM) recently introduced by Chelba and Jelinek is a powerful general formalism for exploiting syntactic dependencies in a left-to-right language model for applications such as speech and handwriting recognition, spelling correction, machine translation, etc. Unlike traditional N-gram models, optimal smoothing techniques – discounting methods and hierarchical struc...
متن کامل