Topic Memory Networks for Short Text Classification

Zeng, Jichuan; Li, Jing; Yan, Shuicheng; Gao, Cuiyun; Lyu, Michael R.; King, Irwin

doi:10.18653/v1/d18-1351

Cited by 124 publications

(87 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To alleviate this issue, Bahdanau et al [28] proposed the attention mechanism to focus on relevant parts of the source sequence during decoding. We use the attention mechanism in our work because previous studies [35]- [37] prove that attention-based models can better capture the key information (e.g., topical or emotional tokens) in the source sequence. Fig.…”

Section: Attention Mechanismmentioning

confidence: 99%

Automating App Review Response Generation

Gao

Zeng

Xia

et al. 2019

2019 34th IEEE/ACM International Conference on Automated Software Engineering (ASE)

Self Cite

View full text Add to dashboard Cite

Previous studies showed that replying to a user review usually has a positive effect on the rating that is given by the user to the app. For example, Hassan et al. found that responding to a review increases the chances of a user updating their given rating by up to six times compared to not responding. To alleviate the labor burden in replying to the bulk of user reviews, developers usually adopt a template-based strategy where the templates can express appreciation for using the app or mention the company email address for users to follow up. However, reading a large number of user reviews every day is not an easy task for developers. Thus, there is a need for more automation to help developers respond to user reviews.Addressing the aforementioned need, in this work we propose a novel approach RRGen that automatically generates review responses by learning knowledge relations between reviews and their responses. RRGen explicitly incorporates review attributes, such as user rating and review length, and learns the relations between reviews and corresponding responses in a supervised way from the available training data. Experiments on 58 apps and 309,246 review-response pairs highlight that RRGen outperforms the baselines by at least 67.4% in terms of BLEU-4 (an accuracy measure that is widely used to evaluate dialogue response generation systems). Qualitative analysis also confirms the effectiveness of RRGen in generating relevant and accurate responses.

show abstract

Section: Attention Mechanismmentioning

confidence: 99%

Automating App Review Response Generation

Gao

Zeng

Xia

et al. 2019

2019 34th IEEE/ACM International Conference on Automated Software Engineering (ASE)

Self Cite

View full text Add to dashboard Cite

show abstract

“…We implement our model based on the pytorch framework in Paszke et al (2017). For NTM, we implement it following the design 10 in Zeng et al (2018) and set topic number K to 50. The KG model is set up mostly based on Meng et al (2017).…”

Section: Jointly Learning Topics and Keyphrasesmentioning

confidence: 99%

Topic-Aware Neural Keyphrase Generation for Social Media Language

Wang¹,

Li²,

Chan³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

A huge volume of user-generated content is daily produced on social media. To facilitate automatic language understanding, we study keyphrase prediction, distilling salient information from massive posts. While most existing methods extract words from source posts to form keyphrases, we propose a sequence-to-sequence (seq2seq) based neural keyphrase generation framework, enabling absent keyphrases to be created. Moreover, our model, being topic-aware, allows joint modeling of corpus-level latent topic representations, which helps alleviate the data sparsity that widely exhibited in social media language. Experiments on three datasets collected from English and Chinese social media platforms show that our model significantly outperforms both extraction and generation models that do not exploit latent topics. 1 Further discussions show that our model learns meaningful topics, which interprets its superiority in social media keyphrase generation.

show abstract

“…Recently, several works are proposed to utilize neural networks for short text classification. Zeng et al proposed a novel topic memory network to encode category relevant representation (Zeng et al, 2018). The topic inference and document classification are jointly performed in their model.…”

Section: Related Workmentioning

confidence: 99%

Filtering and Classifying Relevant Short Text with a Few Seed Words

Chen

Yan

2019

Data and Information Management

View full text Add to dashboard Cite

Filtering out irrelevant documents and classifying the relevant ones into topical categories is a de facto task in many applications. However, supervised learning solutions require extravagant human efforts on document labeling. In this paper, we propose a novel seed-guided topic model for dataless short text classification and filtering, named SSCF. Without using any labeled documents, SSCF takes a few “seed words” for each category of interest, and conducts short text filtering and classification in a weakly supervised manner. To overcome the issues of data sparsity and imbalance, the short text collection is mapped to a collection of pseudodocuments, one for each word. SSCF infers two kinds of topics on pseudo-documents: category-topics and general-topics. Each category-topic is associated with one category of interest, covering the meaning of the latter. In SSCF, we devise a novel word relevance estimation process based on the seed words, for hidden topic inference. The dominating topic of a short text is identified through post inference and then used for filtering and classification. On two real-world datasets in two languages, experimental results show that our proposed SSCF consistently achieves better classification accuracy than state-of-the-art baselines. We also observe that SSCF can even achieve superior performance than the supervised classifiers supervised latent dirichlet allocation (sLDA) and support vector machine (SVM) on some testing tasks.

show abstract

Topic Memory Networks for Short Text Classification

Cited by 124 publications

References 35 publications

Automating App Review Response Generation

Automating App Review Response Generation

Topic-Aware Neural Keyphrase Generation for Social Media Language

Filtering and Classifying Relevant Short Text with a Few Seed Words

Contact Info

Product

Resources

About