Neural Attention-Aware Hierarchical Topic Model

• URL: http://arxiv.org/abs/2110.07161v1
• Date: Thu, 14 Oct 2021 05:42:32 GMT
• Title: Neural Attention-Aware Hierarchical Topic Model
• Authors: Yuan Jin, He Zhao, Ming Liu, Lan Du, Wray Buntine
• Abstract summary: We propose a variational autoencoder (VAE) NTM model that jointly reconstructs the sentence and document word counts. Our model also features hierarchical KL divergence to leverage embeddings of each document to regularize those of their sentences. Both quantitative and qualitative experiments have shown the efficacy of our model in 1) lowering the reconstruction errors at both the sentence and document levels, and 2) discovering more coherent topics from real-world datasets.
• Score: 25.721713066830404
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Neural topic models (NTMs) apply deep neural networks to topic modelling. Despite their success, NTMs generally ignore two important aspects: (1) only document-level word count information is utilized for the training, while more fine-grained sentence-level information is ignored, and (2) external semantic knowledge regarding documents, sentences and words are not exploited for the training. To address these issues, we propose a variational autoencoder (VAE) NTM model that jointly reconstructs the sentence and document word counts using combinations of bag-of-words (BoW) topical embeddings and pre-trained semantic embeddings. The pre-trained embeddings are first transformed into a common latent topical space to align their semantics with the BoW embeddings. Our model also features hierarchical KL divergence to leverage embeddings of each document to regularize those of their sentences, thereby paying more attention to semantically relevant sentences. Both quantitative and qualitative experiments have shown the efficacy of our model in 1) lowering the reconstruction errors at both the sentence and document levels, and 2) discovering more coherent topics from real-world datasets.

Related papers

• CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling [23.323587005085564]
  We introduce a novel neural topic model called the Contextlized Word Topic Model (CWTM) CWTM integrates contextualized word embeddings from BERT. It is capable of learning the topic vector of a document without BOW information. It can also derive the topic vectors for individual words within a document based on their contextualized word embeddings.
  arXiv  Detail & Related papers  (2023-05-16T10:07:33Z)
• Topics in the Haystack: Extracting and Evaluating Topics beyond Coherence [0.0]
  We propose a method that incorporates a deeper understanding of both sentence and document themes. This allows our model to detect latent topics that may include uncommon words or neologisms. We present correlation coefficients with human identification of intruder words and achieve near-human level results at the word-intrusion task.
  arXiv  Detail & Related papers  (2023-03-30T12:24:25Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)
• Multi-source Neural Topic Modeling in Multi-view Embedding Spaces [21.506835768643466]
  This work presents a novel neural topic modeling framework using multi-view embedding spaces. We first build respective pools of pretrained topic (i.e., TopicPool) and word embeddings (i.e., WordPool) We then identify one or more relevant source domain(s) and transfer knowledge to guide meaningful learning in the sparse target domain.
  arXiv  Detail & Related papers  (2021-04-17T14:08:00Z)
• Syntax-Enhanced Pre-trained Model [49.1659635460369]
  We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. We present a model that utilizes the syntax of text in both pre-training and fine-tuning stages.
  arXiv  Detail & Related papers  (2020-12-28T06:48:04Z)
• SLM: Learning a Discourse Language Representation with Sentence Unshuffling [53.42814722621715]
  We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation. We show that this feature of our model improves the performance of the original BERT by large margins.
  arXiv  Detail & Related papers  (2020-10-30T13:33:41Z)
• Abstractive Summarization of Spoken and Written Instructions with BERT [66.14755043607776]
  We present the first application of the BERTSum model to conversational language. We generate abstractive summaries of narrated instructional videos across a wide variety of topics. We envision this integrated as a feature in intelligent virtual assistants, enabling them to summarize both written and spoken instructional content upon request.
  arXiv  Detail & Related papers  (2020-08-21T20:59:34Z)
• A Neural Generative Model for Joint Learning Topics and Topic-Specific Word Embeddings [42.87769996249732]
  We propose a novel generative model to explore both local and global context for joint learning topics and topic-specific word embeddings. The trained model maps words to topic-dependent embeddings, which naturally addresses the issue of word polysemy.
  arXiv  Detail & Related papers  (2020-08-11T13:54:11Z)
• Context Reinforced Neural Topic Modeling over Short Texts [15.487822291146689]
  We propose a Context Reinforced Neural Topic Model (CRNTM) CRNTM infers the topic for each word in a narrow range by assuming that each short text covers only a few salient topics. Experiments on two benchmark datasets validate the effectiveness of the proposed model on both topic discovery and text classification.
  arXiv  Detail & Related papers  (2020-08-11T06:41:53Z)
• BURT: BERT-inspired Universal Representation from Twin Structure [89.82415322763475]
  BURT (BERT inspired Universal Representation from Twin Structure) is capable of generating universal, fixed-size representations for input sequences of any granularity. Our proposed BURT adopts the Siamese network, learning sentence-level representations from natural language inference dataset and word/phrase-level representations from paraphrasing dataset. We evaluate BURT across different granularities of text similarity tasks, including STS tasks, SemEval2013 Task 5(a) and some commonly used word similarity tasks.
  arXiv  Detail & Related papers  (2020-04-29T04:01:52Z)
• Towards Making the Most of Context in Neural Machine Translation [112.9845226123306]
  We argue that previous research did not make a clear use of the global context. We propose a new document-level NMT framework that deliberately models the local context of each sentence.
  arXiv  Detail & Related papers  (2020-02-19T03:30:00Z)

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.