1 |
A Sentence Meaning Based Alignment Method for Parallel Text Corpora Preparation ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
News Across Languages - Cross-Lingual Document Similarity and Event Tracking ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Building Subject-aligned Comparable Corpora and Mining it for Truly Parallel Sentence Pairs ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Leveraging Textual Features for Best Answer Prediction in Community-based Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Applying deep learning techniques on medical corpora from the World Wide Web: a prototypical system and evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Editorial for the First Workshop on Mining Scientific Papers: Computational Linguistics and Bibliometrics ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
A fully data-driven method to identify (correlated) changes in diachronic corpora ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Color Aesthetics and Social Networks in Complete Tang Poems: Explorations and Discoveries ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Aspect-based Opinion Summarization with Convolutional Neural Networks ...
|
|
|
|
Abstract:
This paper considers Aspect-based Opinion Summarization (AOS) of reviews on particular products. To enable real applications, an AOS system needs to address two core subtasks, aspect extraction and sentiment classification. Most existing approaches to aspect extraction, which use linguistic analysis or topic modeling, are general across different products but not precise enough or suitable for particular products. Instead we take a less general but more precise scheme, directly mapping each review sentence into pre-defined aspects. To tackle aspect mapping and sentiment classification, we propose two Convolutional Neural Network (CNN) based methods, cascaded CNN and multitask CNN. Cascaded CNN contains two levels of convolutional networks. Multiple CNNs at level 1 deal with aspect mapping task, and a single CNN at level 2 deals with sentiment classification. Multitask CNN also contains multiple aspect CNNs and a sentiment CNN, but different networks share the same word embeddings. Experimental results ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Information Retrieval cs.IR; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.1511.09128 https://arxiv.org/abs/1511.09128
|
|
BASE
|
|
Hide details
|
|
12 |
amLite: Amharic Transliteration Using Key Map Dictionary ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Approaches for Sentiment Analysis on Twitter: A State-of-Art study ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Selecting Relevant Web Trained Concepts for Automated Event Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Better Summarization Evaluation with Word Embeddings for ROUGE ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Extending a Single-Document Summarizer to Multi-Document: a Hierarchical Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Visual Affect Around the World: A Large-scale Multilingual Visual Sentiment Ontology ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Towards Evaluation of Cultural-scale Claims in Light of Topic Model Sampling Effects ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Twitter Sentiment Analysis: Lexicon Method, Machine Learning Method and Their Combination ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|