Titlebook: Computational Linguistics; 15th International C K?iti Hasida,Win Pa Pa Conference proceedings 2018 Springer Nature Singapore Pte Ltd. 2018

CAND

Semantic Refinement GRU-Based Neural Language Generation for Spoken Dialogue Systemsl networks (RNN), in which a gating mechanism is applied before RNN computation. This allows the proposed model to generate appropriate sentences. The RNN-based generator can be learned from unaligned data by jointly training sentence planning and surface realization to produce natural language resp

大廳

Discovering Representative Space for Relational Similarity Measurementional similarity is important for various natural language processing tasks such as, relational search, noun-modifier classification, and analogy detection. Despite this need, the features that accurately express the relational similarity between two word pairs remain largely unknown. So far, method

insurgent

sacrum

Integrating Specialized Bilingual Lexicons of Multiword Expressions for Domain Adaptation in Statistaracterize specific-domains vocabularies. Translating multiword expressions is a challenge for current Statistical Machine Translation (SMT) systems because corpus-based approaches are effective only when large amounts of parallel corpora are available. However, parallel corpora are only available f

Lacerate

Logical Parsing from Natural Language Based on a Neural Translation Modelemantic parser rely on high-quality lexicons, hand-crafted grammars and linguistic features which are limited by applied domain or representation. In this paper, we propose an approach to learn from denotations based on the Seq2Seq model augmented with attention mechanism. We encode input sequence i

向下

憤慨一下

NUL

Khmer POS Tagging Using Conditional Random Fieldsstudy, in order to further explore this topic, we present an alternative approach to Khmer POS tagging using Conditional Random Fields (CRFs). Since the features greatly affect the tagging accuracy, we investigate five groups of features and use them with the CRF model. First, we study different con

gusher

Statistical Khmer Name Romanizationethods are applied prevalently in practice. These are inconsistent and complicated in some cases, due to unstable phonemic, orthographic, and etymological principles. Consequently, statistical approaches are required for the task. We collect and manually align 7,?658 Khmer name Romanization instance

是比賽