Learning Context-Sensitive Word Embeddings with Neural Tensor Skip-Gram Model
Authors: Pengfei Liu, Xipeng Qiu, Xuanjing Huang
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments show qualitative improvements of our model over single-sense Skip-Gram on word neighbors. We also perform empirical comparisons on two tasks, contextual word similarity and text classification, which demonstrate the effectiveness of our model over the other state-of-the-art multi-prototype models. |
| Researcher Affiliation | Academia | Pengfei Liu, Xipeng Qiu and Xuanjing Huang Shanghai Key Laboratory of Data Science, Fudan University School of Computer Science, Fudan University 825 Zhangheng Road, Shanghai, China {pfliu14,xpqiu,xjhuang}@fudan.edu.cn |
| Pseudocode | No | The paper describes the model mathematically and textually but does not include any explicit pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code or links to a code repository. |
| Open Datasets | Yes | We evaluate our embeddings on Stanford s Contextual Word Similarities (SCWS) dataset, developed by Huang et al.[2012]. ... We select Wikipedia, the largest online knowledge base, to learn topical word embeddings for this task. We adopt the April 2010 dump, which is also used by [Huang et al., 2012]. ... We use the popular dataset 20News Group, which consists of about 20,000 documents from 20 different newsgroups. |
| Dataset Splits | No | The paper mentions using a 'training set D' and training on the 'training set' for 20News Group, but does not specify explicit numerical splits (e.g., percentages or counts) for training, validation, and test sets. It refers to standard datasets but doesn't detail how they were partitioned for their specific experiments. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU or CPU models, or memory specifications used for running the experiments. |
| Software Dependencies | No | The paper mentions using tools like LDA and Liblinear, but it does not specify any version numbers for these or any other software dependencies, which is required for reproducible software description. |
| Experiment Setup | Yes | When learning Skip-Gram and our models, we set window size as 5 and the dimensionality of both word embeddings and topic embeddings as K = 400. We set the number of topic T = 400 and iteration number I = 50. ... For our model, we first learn topic models using LDA on the training and test set by setting the number of topics T = 80, ... and topic embeddings d = 400. |