Modeling Fuzzy Cluster Transitions for Topic Tracing
- URL: http://arxiv.org/abs/2104.08258v1
- Date: Fri, 16 Apr 2021 17:41:16 GMT
- Title: Modeling Fuzzy Cluster Transitions for Topic Tracing
- Authors: Xiaonan Jing, Yi Zhang, Qingyuan Hu, Julia Taylor Rayz
- Abstract summary: Twitter can be viewed as a data source for Natural Language Processing (NLP) tasks.
We propose a framework for modeling fuzzy transitions of topic clusters.
- Score: 4.901193306593378
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Twitter can be viewed as a data source for Natural Language Processing (NLP)
tasks. The continuously updating data streams on Twitter make it challenging to
trace real-time topic evolution. In this paper, we propose a framework for
modeling fuzzy transitions of topic clusters. We extend our previous work on
crisp cluster transitions by incorporating fuzzy logic in order to enrich the
underlying structures identified by the framework. We apply the methodology to
both computer generated clusters of nouns from tweets and human tweet
annotations. The obtained fuzzy transitions are compared with the crisp
transitions, on both computer generated clusters and human labeled topic sets.
Related papers
- Pushdown Layers: Encoding Recursive Structure in Transformer Language
Models [86.75729087623259]
Recursion is a prominent feature of human language, and fundamentally challenging for self-attention.
This work introduces Pushdown Layers, a new self-attention layer.
Transformers equipped with Pushdown Layers achieve dramatically better and 3-5x more sample-efficient syntactic generalization.
arXiv Detail & Related papers (2023-10-29T17:27:18Z) - Graph Decision Transformer [83.76329715043205]
Graph Decision Transformer (GDT) is a novel offline reinforcement learning approach.
GDT models the input sequence into a causal graph to capture potential dependencies between fundamentally different concepts.
Our experiments show that GDT matches or surpasses the performance of state-of-the-art offline RL methods on image-based Atari and OpenAI Gym.
arXiv Detail & Related papers (2023-03-07T09:10:34Z) - How Well Do Sparse Imagenet Models Transfer? [75.98123173154605]
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" datasets.
In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset.
We show that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities.
arXiv Detail & Related papers (2021-11-26T11:58:51Z) - Towards Tokenized Human Dynamics Representation [41.75534387530019]
We study how to segment and cluster videos into recurring temporal patterns in a self-supervised way.
We evaluate the frame-wise representation learning step by Kendall's Tau and the lexicon building step by normalized mutual information and language entropy.
On the AIST++ and PKU-MMD datasets, actons bring significant performance improvements compared to several baselines.
arXiv Detail & Related papers (2021-11-22T18:59:58Z) - R2D2: Relational Text Decoding with Transformers [18.137828323277347]
We propose a novel framework for modeling the interaction between graphical structures and the natural language text associated with their nodes and edges.
Our proposed method utilizes both the graphical structure as well as the sequential nature of the texts.
While the proposed model has wide applications, we demonstrate its capabilities on data-to-text generation tasks.
arXiv Detail & Related papers (2021-05-10T19:59:11Z) - Tracing Topic Transitions with Temporal Graph Clusters [4.901193306593378]
Twitter serves as a data source for many Natural Language Processing (NLP) tasks.
It can be challenging to identify topics on Twitter due to continuous updating data stream.
We present an unsupervised graph based framework to identify the evolution of sub-topics within two weeks of real-world Twitter data.
arXiv Detail & Related papers (2021-04-16T00:55:31Z) - End-to-end Semantic Role Labeling with Neural Transition-based Model [25.921541005563856]
End-to-end semantic role labeling (SRL) has been received increasing interest.
Recent work is mostly focused on graph-based neural models.
We present the first work of transition-based neural models for end-to-end SRL.
arXiv Detail & Related papers (2021-01-02T07:35:54Z) - Unsupervised Paraphrasing with Pretrained Language Models [85.03373221588707]
We propose a training pipeline that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting.
Our recipe consists of task-adaptation, self-supervision, and a novel decoding algorithm named Dynamic Blocking.
We show with automatic and human evaluations that our approach achieves state-of-the-art performance on both the Quora Question Pair and the ParaNMT datasets.
arXiv Detail & Related papers (2020-10-24T11:55:28Z) - Cluster-Former: Clustering-based Sparse Transformer for Long-Range
Dependency Encoding [90.77031668988661]
Cluster-Former is a novel clustering-based sparse Transformer to perform attention across chunked sequences.
The proposed framework is pivoted on two unique types of Transformer layer: Sliding-Window Layer and Cluster-Former Layer.
Experiments show that Cluster-Former achieves state-of-the-art performance on several major QA benchmarks.
arXiv Detail & Related papers (2020-09-13T22:09:30Z) - Transition-based Semantic Dependency Parsing with Pointer Networks [0.34376560669160383]
We propose a transition system that can straightforwardly produce labelled directed acyclic graphs and perform semantic dependency parsing.
We enhance our approach with deep contextualized word embeddings extracted from BERT.
The resulting system not only outperforms all existing transition-based models, but also matches the best fully-supervised accuracy to date on SemEval 2015 18 English datasets.
arXiv Detail & Related papers (2020-05-27T13:18:27Z) - Tree-structured Attention with Hierarchical Accumulation [103.47584968330325]
"Hierarchical Accumulation" encodes parse tree structures into self-attention at constant time complexity.
Our approach outperforms SOTA methods in four IWSLT translation tasks and the WMT'14 English-German translation task.
arXiv Detail & Related papers (2020-02-19T08:17:00Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.