Discriminative language modeling

Xem 1-20 trên 33 kết quả Discriminative language modeling
  • This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a method based on conditional random fields (CRFs). The models are encoded as deterministic weighted finite state automata, and are applied by intersecting the automata with word-lattices that are the output from a baseline recognizer. The perceptron algorithm has the benefit of automatically selecting a relatively small feature set in just a couple of passes over the training data. ...

    pdf8p bunbo_1 17-04-2013 31 2   Download

  • In this paper, we propose a novel discriminative language model, which can be applied quite generally. Compared to the well known N-gram language models, discriminative language models can achieve more accurate discrimination because they can employ overlapping features and nonlocal information. However, discriminative language models have been used only for re-ranking in specific applications because negative examples are not available.

    pdf8p hongvang_1 16-04-2013 26 1   Download

  • Language models based on word surface forms only are unable to benefit from available linguistic knowledge, and tend to suffer from poor estimates for rare features. We propose an approach to overcome these two limitations. We use factored features that can flexibly capture linguistic regularities, and we adopt confidence-weighted learning, a form of discriminative online learning that can better take advantage of a heavy tail of rare features.

    pdf6p hongdo_1 12-04-2013 33 2   Download

  • We describe a method for discriminative training of a language model that makes use of syntactic features. We follow a reranking approach, where a baseline recogniser is used to produce 1000-best output for each acoustic input, and a second “reranking” model is then used to choose an utterance from these 1000-best lists. The reranking model makes use of syntactic features together with a parameter estimation method that is based on the perceptron algorithm. We describe experiments on the Switchboard speech recognition task. ...

    pdf8p bunbo_1 17-04-2013 33 2   Download

  • This paper presents a discriminative pruning method of n-gram language model for Chinese word segmentation. To reduce the size of the language model that is used in a Chinese word segmentation system, importance of each bigram is computed in terms of discriminative pruning criterion that is related to the performance loss caused by pruning the bigram. Then we propose a step-by-step growing algorithm to build the language model of desired size.

    pdf8p hongvang_1 16-04-2013 29 1   Download

  • While OOV is always a problem for most languages in ASR, in the Chinese case the problem can be avoided by utilizing character n-grams and moderate performances can be obtained. However, character ngram has its own limitation and proper addition of new words can increase the ASR performance. Here we propose a discriminative lexicon adaptation approach for improved character accuracy, which not only adds new words but also deletes some words from the current lexicon.

    pdf9p hongphan_1 14-04-2013 40 2   Download

  • This paper presents a predicate-argument structure analysis that simultaneously conducts zero-anaphora resolution. By adding noun phrases as candidate arguments that are not only in the sentence of the target predicate but also outside of the sentence, our analyzer identifies arguments regardless of whether they appear in the sentence or not. Because we adopt discriminative models based on maximum entropy for argument identification, we can easily add new features. We add language model scores as well as contextual features.

    pdf4p hongphan_1 15-04-2013 37 1   Download

  • Chapters in the first part of the book cover all the essential speech processing techniques for building robust, automatic speech recognition systems: the representation for speech signals and the methods for speech-features extraction, acoustic and language modeling, efficient algorithms for searching the hypothesis space, and multimodal approaches to speech recognition.

    pdf576p kimngan_1 06-11-2012 36 6   Download

  • Most previous studies of morphological disambiguation and dependency parsing have been pursued independently. Morphological taggers operate on n-grams and do not take into account syntactic relations; parsers use the “pipeline” approach, assuming that morphological information has been separately obtained. However, in morphologically-rich languages, there is often considerable interaction between morphology and syntax, such that neither can be disambiguated without the other.

    pdf10p hongdo_1 12-04-2013 34 3   Download

  • The present paper describes a robust approach for abbreviating terms. First, in order to incorporate non-local information into abbreviation generation tasks, we present both implicit and explicit solutions: the latent variable model, or alternatively, the label encoding approach with global information. Although the two approaches compete with one another, we demonstrate that these approaches are also complementary. By combining these two approaches, experiments revealed that the proposed abbreviation generator achieved the best results for both the Chinese and English languages. ...

    pdf9p hongphan_1 14-04-2013 31 3   Download

  • Deterministic parsing guided by treebankinduced classifiers has emerged as a simple and efficient alternative to more complex models for data-driven parsing. We present a systematic comparison of memory-based learning (MBL) and support vector machines (SVM) for inducing classifiers for deterministic dependency parsing, using data from Chinese, English and Swedish, together with a variety of different feature models. The comparison shows that SVM gives higher accuracy for richly articulated feature models across all languages, albeit with considerably longer training times. ...

    pdf8p hongvang_1 16-04-2013 25 2   Download

  • Discriminative methods have shown significant improvements over traditional generative methods in many machine learning applications, but there has been difficulty in extending them to natural language parsing. One problem is that much of the work on discriminative methods conflates changes to the learning method with changes to the parameterization of the problem. We show how a parser can be trained with a discriminative learning method while still parameterizing the problem according to a generative probability model.

    pdf8p bunbo_1 17-04-2013 31 2   Download

  • We present a framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source-channel approach as a special case. All knowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and possible hidden variables. This approach allows a baseline machine translation system to be extended easily by adding new feature functions. We show that a baseline statistical machine translation system is significantly improved using this approach. ...

    pdf8p bunmoc_1 20-04-2013 26 2   Download

  • Concept taxonomies offer a powerful means for organizing knowledge, but this organization must allow for many overlapping and fine-grained perspectives if a general-purpose taxonomy is to reflect concepts as they are actually employed and reasoned about in everyday usage. We present here a means of bootstrapping finely-discriminating taxonomies from a variety of different starting points, or seeds, that are acquired from three different sources: WordNet, ConceptNet and the web at large.

    pdf8p bunthai_1 06-05-2013 44 2   Download

  • This paper studies the impact of written language variations and the way it affects the capitalization task over time. A discriminative approach, based on maximum entropy models, is proposed to perform capitalization, taking the language changes into consideration. The proposed method makes it possible to use large corpora for training. The evaluation is performed over newspaper corpora using different testing periods. The achieved results reveal a strong relation between the capitalization performance and the elapsed time between the training and testing data periods. ...

    pdf4p hongphan_1 15-04-2013 25 1   Download

  • AMBER is a model of first language acquisition that improves its performance through a process of error recovery. The model is implemented as an adaptive production system that introduces new condition-action rules on the basis of experience. AMBER starts with the ability to say only one word at a time, but adds rules for ordering goals and producing grammatical morphemes, based on comparisons between predicted and observed sentences.

    pdf7p bungio_1 03-05-2013 29 1   Download

  • We present a model for sentence compression that uses a discriminative largemargin learning framework coupled with a novel feature set defined on compressed bigrams as well as deep syntactic representations provided by auxiliary dependency and phrase-structure parsers. The parsers are trained out-of-domain and contain a significant amount of noise. We argue that the discriminative nature of the learning algorithm allows the model to learn weights relative to any noise in the feature set to optimize compression accuracy directly.

    pdf8p bunthai_1 06-05-2013 28 1   Download

  • Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task.

    pdf9p bunthai_1 06-05-2013 28 1   Download

  • An important part of question answering is ensuring a candidate answer is plausible as a response. We present a flexible approach based on discriminative preference ranking to determine which of a set of candidate answers are appropriate. Discriminative methods provide superior performance while at the same time allow the flexibility of adding new and diverse features. Experimental results on a set of focused What ...? and Which ...? questions show that our learned preference ranking methods perform better than alternative solutions to the task of answer typing. A gain of almost 0.

    pdf9p bunthai_1 06-05-2013 24 1   Download

  • Research on the discovery of terms from corpora has focused on word sequences whose recurrent occurrence in a corpus is indicative of their terminological status, and has not addressed the issue of discovering terms when data is sparse. This becomes apparent in the case of noun compounding, which is extremely productive: more than half of the candidate compounds extracted from a corpus are attested only once. We show how evidence about established (i.e.

    pdf8p bunthai_1 06-05-2013 31 3   Download



p_strKeyword=Discriminative language modeling

nocache searchPhinxDoc


Đồng bộ tài khoản