Punctuation Prediction using Linear Chain Conditional Random Fields
نویسندگان
چکیده
We investigate the task of punctuation prediction in English sentences without prosodic information. In our approach, stochastic gradient ascent (SGA) is used to maximize log conditional likelihood when learning the parameters of linear-chain conditional random fields. For SGA, two different approximation techniques, namely Collins perceptron and contrastive divergence, are used to estimate the update step size. We construct 672 feature functions for our punctuation prediction model on a dataset with 70, 115 training examples and 28, 027 test examples. Experimental results show that SGA with Collins perceptron and SGA with contrastive divergence yield 7.11% and 13.89% word level error rate, respectively.
منابع مشابه
Better Punctuation Prediction with Dynamic Conditional Random Fields
This paper focuses on the task of inserting punctuation symbols into transcribed conversational speech texts, without relying on prosodic cues. We investigate limitations associated with previous methods, and propose a novel approach based on dynamic conditional random fields. Different from previous work, our proposed approach is designed to jointly perform both sentence boundary and sentence ...
متن کاملDynamic Conditional Random Fields for Joint Sentence Boundary and Punctuation Prediction
The use of dynamic conditional random fields (DCRF) has been shown to outperform linear-chain conditional random fields (LCRF) for punctuation prediction on conversational speech texts [1]. In this paper, we combine lexical, prosodic, and modified n-gram score features into the DCRF framework for a joint sentence boundary and punctuation prediction task on TDT3 English broadcast news. We show t...
متن کاملA CRF Sequence Labeling Approach to Chinese Punctuation Prediction
This paper presents a conditional random fields based labeling approach to Chinese punctuation prediction. To this end, we first reformulate Chinese punctuation prediction as a multiple-pass labeling task on a sequence of words, and then explore various features from three linguistic levels, namely words, phrase and functional chunks for punctuation prediction under the framework of conditional...
متن کاملCombining Punctuation and Disfluency Prediction: An Empirical Study
Punctuation prediction and disfluency prediction can improve downstream natural language processing tasks such as machine translation and information extraction. Combining the two tasks can potentially improve the efficiency of the overall pipeline system and reduce error propagation. In this work1, we compare various methods for combining punctuation prediction (PU) and disfluency prediction (...
متن کاملImproved models for automatic punctuation prediction for spoken and written text
This paper presents improved models for the automatic prediction of punctuation marks in written or spoken text. Various kinds of textual features are combined using Conditional Random Fields. These features include language model scores, token n-grams, sentence length, and syntactic information extracted from parse trees. The resulting models are evaluated on several different tasks, ranging f...
متن کامل