Topical Word Embeddings
Authors: Yang Liu, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In the experiments, we evaluate the TWE models on two tasks, contextual word similarity and text classification. The experimental results show that our models outperform typical word embedding models including the multi-prototype version on contextual word similarity, and also exceed latent topic models and other representative document models on text classification. |
| Researcher Affiliation | Academia | 1 Department of Computer Science and Technology, State Key Lab on Intelligent Technology and Systems, National Lab for Information Science and Technology, Tsinghua University, Beijing 100084, China 2 School of Computing, National University of Singapore, Singapore 3 Jiangsu Collaborative Innovation Center for Language Competence, Jiangsu 221009, China |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The source code of this paper can be obtained from https://github.com/largelymfs/ topical word embeddings. |
| Open Datasets | Yes | We use the dataset released by (Huang et al. 2012) for evaluation, named as SCWS in this paper following (Luong, Socher, and Manning 2013). (...) We adopt the April 2010 dump also used by (Huang et al. 2012) 1. The dataset and the vocabulary file can be downloaded from http://www.socher.org/. (...) Here we run the experiments on the dataset 20News Group 2. 20News Group consists of about 20, 000 documents from 20 different newsgroups. http://qwone.com/~jason/20Newsgroups/. |
| Dataset Splits | No | The paper mentions training and test sets for 20News Group but does not specify the exact percentages, sample counts, or explicit methodology for these splits, nor does it explicitly mention a validation set with details. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions using Liblinear but does not provide specific version numbers for any software libraries, packages, or programming languages used in the experiments. |
| Experiment Setup | Yes | When learning topic assignments with LDA, we set T = 400 and I = 50. When learning Skip-Gram and TWE models, we set window size as 5 and the dimensions of both word embeddings and topic embeddings as K = 400. (...) For TWE models, we learn topic models using LDA on the training set by setting the number of topics T = 80. |