Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen components. Motivated by trad
itional semantic parsing where compositionality is explicitly accounted for by symbolic grammars, we propose a new decoding framework that preserves the expressivity and generality of sequence-to-sequence models while featuring lexicon-style alignments and disentangled information processing. Specifically, we decompose decoding into two phases where an input utterance is first tagged with semantic symbols representing the meaning of individual words, and then a sequence-to-sequence model is used to predict the final meaning representation conditioning on the utterance and the predicted tag sequence. Experimental results on three semantic parsing datasets show that the proposed approach consistently improves compositional generalization across model architectures, domains, and semantic formalisms.
Domain adaption for word segmentation and POS tagging is a challenging problem for Chinese lexical processing. Self-training is one promising solution for it, which struggles to construct a set of high-quality pseudo training instances for the target
domain. Previous work usually assumes a universal source-to-target adaption to collect such pseudo corpus, ignoring the different gaps from the target sentences to the source domain. In this work, we start from joint word segmentation and POS tagging, presenting a fine-grained domain adaption method to model the gaps accurately. We measure the gaps by one simple and intuitive metric, and adopt it to develop a pseudo target domain corpus based on fine-grained subdomains incrementally. A novel domain-mixed representation learning model is proposed accordingly to encode the multiple subdomains effectively. The whole process is performed progressively for both corpus construction and model training. Experimental results on a benchmark dataset show that our method can gain significant improvements over a vary of baselines. Extensive analyses are performed to show the advantages of our final domain adaption model as well.
Tag recommendation relies on either a ranking function for top-k tags or an autoregressive generation method. However, the previous methods neglect one of two seemingly conflicting yet desirable characteristics of a tag set: orderlessness and inter-d
ependency. While the ranking approach fails to address the inter-dependency among tags when they are ranked, the autoregressive approach fails to take orderlessness into account because it is designed to utilize sequential relations among tokens. We propose a sequence-oblivious generation method for tag recommendation, in which the next tag to be generated is independent of the order of the generated tags and the order of the ground truth tags occurring in training data. Empirical results on two different domains, Instagram and Stack Overflow, show that our method is significantly superior to the previous approaches.
The research aimed to study the role of content marketing in improving the mental image of the brand, by studying the role of content marketing elements (attractiveness, relevance, value) in improving the mental image. The researcher relied on the de
scriptive analytical method as a general approach to the research, where a questionnaire was designed and distributed to the research sample consisting of 318 individuals from the consumers of Seronex screens in Lattakia governorate (rural and city), and the researcher also used the statistical program spss to analyze the answers of the research sample. The researcher concluded that there is a positive, significant effect of content marketing on the mental image of Syronex, and the dimensions of content marketing were arranged in terms of this degree of influence in the following order: relevance, value, attractiveness
We implemented a neural machine translation system that uses automatic sequence tagging to improve the quality of translation. Instead of operating on unannotated sentence pairs, our system uses pre-trained tagging systems to add linguistic features
to source and target sentences. Our proposed neural architecture learns a combined embedding of tokens and tags in the encoder, and simultaneous token and tag prediction in the decoder. Compared to a baseline with unannotated training, this architecture increased the BLEU score of German to English film subtitle translation outputs by 1.61 points using named entity tags; however, the BLEU score decreased by 0.38 points using part-of-speech tags. This demonstrates that certain token-level tag outputs from off-the-shelf tagging systems can improve the output of neural translation systems using our combined embedding and simultaneous decoding extensions.
Given the clinical notes written in electronic health records (EHRs), it is challenging to predict the diagnostic codes which is formulated as a multi-label classification task. The large set of labels, the hierarchical dependency, and the imbalanced
data make this prediction task extremely hard. Most existing work built a binary prediction for each label independently, ignoring the dependencies between labels. To address this problem, we propose a two-stage framework to improve automatic ICD coding by capturing the label correlation. Specifically, we train a label set distribution estimator to rescore the probability of each label set candidate generated by a base predictor. This paper is the first attempt at learning the label set distribution as a reranking module for ICD coding. In the experiments, our proposed framework is able to improve upon best-performing predictors for medical code prediction on the benchmark MIMIC datasets.
Tree-adjoining grammar (TAG) and combinatory categorial grammar (CCG) are two well-established mildly context-sensitive grammar formalisms that are known to have the same expressive power on strings (i.e., generate the same class of string languages)
. It is demonstrated that their expressive power on trees also essentially coincides. In fact, CCG without lexicon entries for the empty string and only first-order rules of degree at most 2 are sufficient for its full expressive power.
This research handles the Semiotic Features in the Augustian's text an attempt to
discover its nature and implication. It tackies the Semiotic theme, its concepts and relation
to the Sociological Cultural realities of modern semitians. then it disc
usses the concept of
sign and its relation to interpretation in this text showing its distinct features, Symbolic
language which makes us delve deep into this text trying to open broaden horiozons via
searching deep into existence to decipher hidden meanings of symbos in the external
existence of things. It also deals with the speciality of sign to Augustein in which the
theological perspective played the major role. It also aims at specifying the differences and
similarities with some modern semitics to talk eventually about kinds of sign trying to end
up with some results that help us comprehend the Augustian's text.
The objective of this field study was to examine the effect of brand
name dimensions, namely; brand perceived price, brand perceived
quality on purchase decision. The field research was carried out
on university youth in Syria. Aimed the research
was to
understand the most influential brand name dimensions on
purchase decision. Based on brand name literature, previous
empirical and conceptual studies, a self-administered
questionnaire was developed as a primary data collection method.
The questionnaire instrument was distributed and delivered to a
convenience sample (800 students) of Al-Furat university.
Descriptive statistics, simple and multiple regression analysis
techniques were employed to test the research model and
hypotheses. Empirical findings revealed a positive and significant
impact of brand name dimensions (brand perceived price, brand
perceived quality) on purchase decision of youth university.
