Page: 1 2 3 4 5 6 7 8... 72
61 |
UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
62 |
The Utility and Interplay of Gazetteers and Entity Segmentation for Named Entity Recognition in English ...
|
|
|
|
BASE
|
|
Show details
|
|
63 |
Situation-Based Multiparticipant Chat Summarization: a Concept, an Exploration-Annotation Tool and an Example Collection ...
|
|
|
|
BASE
|
|
Show details
|
|
64 |
Don't Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
65 |
Boundary Detection with BERT for Span-level Emotion Cause Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
66 |
TexSmart: A System for Enhanced Natural Language Understanding ...
|
|
The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing 2021; Jiang, Haiyun; Kang, Zhanhui; Li, Yangming; Liu, Lemao; Shi, Shuming; Song, Linfeng; Xu, Kun; Yu, Dong; Zhang, Haisong; Zhang, Feng; Zhao, Enbo; Zheng, Suncong; Zhou, Botong. - : Underline Science Inc., 2021
|
|
Abstract:
This talk introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. Compared to most previous publicly available text understanding systems and tools, TexSmart holds some unique features. First, the NER function of TexSmart supports over 1,000 entity types, while most other public tools typically support several to (at most) dozens of entity types. Second, TexSmart introduces new semantic analysis functions like semantic expansion and deep semantic representation, that are absent in most previous systems. Third, a spectrum of algorithms (from very fast algorithms to those that are relatively slow but more accurate) are implemented for one function in TexSmart, to fulfill the requirements of different academic and industrial applications. The adoption of unsupervised or weakly-supervised algorithms is especially emphasized, with the goal of easily updating our models to include fresh data with less human ...
|
|
Keyword:
Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
|
|
URL: https://dx.doi.org/10.48448/y4nv-3c37 https://underline.io/lecture/28623-texsmart-a-system-for-enhanced-natural-language-understanding
|
|
BASE
|
|
Hide details
|
|
67 |
AND does not mean OR: Using Formal Languages to Study Language Models’ Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
68 |
Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images ...
|
|
|
|
BASE
|
|
Show details
|
|
69 |
Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach ...
|
|
|
|
BASE
|
|
Show details
|
|
70 |
Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search ...
|
|
|
|
BASE
|
|
Show details
|
|
72 |
Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
73 |
Document-level Event Extraction via Parallel Prediction Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
74 |
VL-BERT+: Detecting Protected Groups in Hateful Multimodal Memes ...
|
|
|
|
BASE
|
|
Show details
|
|
75 |
Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
76 |
Best of Both Worlds: Making High Accuracy Non-incremental Transformer-based Disfluency Detection Incremental ...
|
|
|
|
BASE
|
|
Show details
|
|
77 |
Attention-based Contextual Language Model Adaptation for Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
78 |
Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech ...
|
|
|
|
BASE
|
|
Show details
|
|
79 |
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
80 |
LUX (Linguistic aspects Under eXamination): Discourse Analysis for Automatic Fake News Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8... 72
|
|