The web provides a huge collection of web pages for researchers to study natural languages. However, processing web scale texts is not an easy task and needs many computational and linguistic resources. In this paper, we introduce two Chinese parts-of-speech tagged web-scale datasets and describe tools that make them easy to use for NLP applications. The first is a Chinese segmented and POS-tag...

This paper proposes a model to learn word embeddings with weighted contexts based on part-of-speech (POS) relevance weights. POS is a fundamental element in natural language. However, state-of-the-art word embedding models fail to consider it. This paper proposes to use position-dependent POS relevance weighting matrices to model the inherent syntactic relationship among words within a context ...

We present a HMM part-of-speech tagging method which is particularly suited for POS tagsets with a large number of fine-grained tags. It is based on three ideas: (1) splitting of the POS tags into attribute vectors and decomposition of the contextual POS probabilities of the HMM into a product of attribute probabilities, (2) estimation of the contextual probabilities with decision trees, and (3...

TCOF-POS : A Freely Available POS-Tagged Corpus of Spoken French This article details the creation of TCOF-POS, the first freely available corpus of spontaneous spoken French. We present here the methodology that was followed in order to obtain the best possible quality in the final resource. This corpus already is freely available and can be used as a training/validation corpus for NLP tools, ...

Adoptive immunotherapy with antitumor T cells is a promising novel approach for the treatment of cancer. However, T-cell therapy may be limited by the cotransfer of regulatory T cells (T(reg)). Here, we explored this hypothesis by using 2 cell surface markers, CD44 and CD137, to isolate antitumor CD4 T cells while excluding T(regs). In a murine model of B-cell lymphoma, only CD137(neg)CD44(hi) ...

This paper presents an application of a Dynamic Bayesian Network (DBN) to the task of assigning Part-of-Speech (PoS) tags to novel text. This task is particularly challenging for non-standard corpora, such as Internet lingo, where a large proportion of words are unknown. Previous work reveals that PoS tags depend on a variety of morphological and contextual features. Representing these dependen...

Text normalization and part-of-speech (POS) tagging for social media data have been investigated recently, however, prior work has treated them separately. In this paper, we propose a joint Viterbi decoding process to determine each token’s POS tag and non-standard token’s correct form at the same time. In order to evaluate our approach, we create two new data sets with POS tag labels and non-s...

New and emerging collaborative responses to sex offender management are challenging traditional notions about how treatment providers and probation and parole officers (POs) deliver services to this difficult population. Typically, sex offender treatment professionals provide community-based services to offenders who are supervised by POs. Yet, no comprehensive survey has investigated how treat...

Part of speech taggers generally perform well on homogeneous data sets, but their performance often varies considerably across different genres. In this paper we investigate the adaptation of POS taggers to individual genres by creating POS tagging experts. We use topic modeling to determine genres automatically and then build a tagging expert for each genre. We use Latent Dirichlet Allocation ...

BACKGROUND Point-of-sale (POS) tobacco advertising has been linked to youth smoking susceptibility and experimental smoking. However, there is limited evidence of the association between POS advertising bans and youth smoking participation. This study aims to examine how such bans are associated with current smoking, daily smoking, and regular smoking (≥ 1 cigarettes per day) participation amon...