1 |
Enhancing Cross-lingual Prompting with Mask Token Augmentation ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Cross-lingual Aspect-based Sentiment Analysis with Aspect Term Code-Switching ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Multilingual AMR Parsing with Noisy Knowledge Distillation ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Multi-perspective Coherent Reasoning for Helpfulness Prediction of Multimodal Reviews ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Argument Pair Extraction via Attention-guided Multi-Layer Multi-Cross Encoding ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyond ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning ...
|
|
|
|
Abstract:
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence data in many domains. To address this issue, we firstly explore an unsupervised domain adaptation setting for this task. Prior work can only use common syntactic relations between aspect and opinion words to bridge the domain gaps, which highly relies on external linguistic resources. To resolve it, we propose a novel Selective Adversarial Learning (SAL) method to align the inferred correlation vectors that automatically capture their latent relations. The SAL method can dynamically learn an alignment weight for each word such that more important words can possess higher alignment weights to achieve fine-grained (word-level) adaptation. Empirically, extensive experiments demonstrate the effectiveness of the proposed SAL method. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1910.14192 https://arxiv.org/abs/1910.14192
|
|
BASE
|
|
Hide details
|
|
17 |
A knowledge regularized hierarchical approach for emotion cause analysis
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Neural Rating Regression with Abstractive Tips Generation for Recommendation ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Reader-Aware Multi-Document Summarization via Sparse Coding ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Abstractive Multi-Document Summarization via Phrase Selection and Merging ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|