Lexicon expansion for latent variable grammars

Zeng, Xiaodong; Wong, Derek F.; Chao, Lidia S.; Trancoso, Isabel; He, Liangye; Huang, Qiuping

doi:10.1016/j.patrec.2014.01.010

Cited by 8 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of sentences in each dataset is shown in Table 1. On the English side, we used the constituent parser (Zeng et al, 2014(Zeng et al, , 2015 to produce a binary syntactic tree for each sentence, in constrast to the use of the HPSG parser by Eriguchi et al (2016). On the Chinese side, the sentences are segmented using the Chinese word segmentation toolkit of NiuTrans (Xiao et al, 2012).…”

Section: Datamentioning

confidence: 99%

Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation

Yang

Wong

Xiao

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

This paper proposes a hierarchical attentional neural translation model which focuses on enhancing source-side hierarchical representations by covering both local and global semantic information using a bidirectional tree-based encoder. To maximize the predictive likelihood of target words, a weighted variant of an attention mechanism is used to balance the attentive information between lexical and phrase vectors. Using a tree-based rare word encoding, the proposed model is extended to sub-word level to alleviate the out-of-vocabulary (OOV) problem. Empirical results reveal that the proposed model significantly outperforms sequence-to-sequence attention-based and tree-based neural translation models in English-Chinese translation tasks.

show abstract

Section: Datamentioning

confidence: 99%

Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation

Yang

Wong

Xiao

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since their inception, L-PCFGs have been used for syntactic parsing in multiple studies for a variety of languages such as English, French, German, Chinese, Arabic and other morphologically rich languages (Candito et al, 2010;Attia et al, 2010;Green and Manning, 2010;Goldberg and Elhadad, 2011;Dehdari et al, 2011;Björkelund et al, 2014;Zeng et al, 2014;Sun et al, 2014;Narayan and Cohen, 2016) …”

Section: Parsing With L-pcfgsmentioning

confidence: 99%

Latent-Variable PCFGs: Background and Applications

Cohen¹

2017

Proceedings of the 15th Meeting on the Mathematics of Language

View full text Add to dashboard Cite

Latent-variable probabilistic context-free grammars are latent-variable models that are based on context-free grammars. Nonterminals are associated with latent states that provide contextual information during the top-down rewriting process of the grammar. We survey a few of the techniques used to estimate such grammars and to parse text with them. We also give an overview of what the latent states represent for English Penn treebank parsing, and provide an overview of extensions and related models to these grammars.

show abstract

“…The task of sentence boundary detection or sentence boundary disambiguation (SBD) is to identify the sentence elements within a text. Many natural language processing (NLP) systems generally take a sentence as an input unit—part of speech (POS) tagging [ 1 ], chunking [ 2 ], and parsing [ 3 ], machine translation (MT) [ 4 ], information retrieval (IR) [ 5 ], and so forth. The SBD, acting as an initial processing step in most of the NLP applications, seems too simple to get the attention from the researchers.…”

Section: Introductionmentioning

confidence: 99%

iSentenizer-μ: Multilingual Sentence Boundary Detection Model

Wong

Chao

Zeng

2014

The Scientific World Journal

Self Cite

View full text Add to dashboard Cite

Sentence boundary detection (SBD) system is normally quite sensitive to genres of data that the system is trained on. The genres of data are often referred to the shifts of text topics and new languages domains. Although new detection models can be retrained for different languages or new text genres, previous model has to be thrown away and the creation process has to be restarted from scratch. In this paper, we present a multilingual sentence boundary detection system (iSentenizer-μ) for Danish, German, English, Spanish, Dutch, French, Italian, Portuguese, Greek, Finnish, and Swedish languages. The proposed system is able to detect the sentence boundaries of a mixture of different text genres and languages with high accuracy. We employ i +Learning algorithm, an incremental tree learning architecture, for constructing the system. iSentenizer-μ, under the incremental learning framework, is adaptable to text of different topics and Roman-alphabet languages, by merging new data into existing model to learn the new knowledge incrementally by revision instead of retraining. The system has been extensively evaluated on different languages and text genres and has been compared against two state-of-the-art SBD systems, Punkt and MaxEnt. The experimental results show that the proposed system outperforms the other systems on all datasets.

show abstract

Lexicon expansion for latent variable grammars

Cited by 8 publications

References 15 publications

Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation

Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation

Latent-Variable PCFGs: Background and Applications

iSentenizer-μ: Multilingual Sentence Boundary Detection Model

Contact Info

Product

Resources

About