Query Understanding through Knowledge-Based Conceptualization
Authors: Zhongyuan Wang, Kejun Zhao, Haixun Wang, Xiaofeng Meng, Ji-Rong Wen
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we examine our method on real data and compare it to representative previous methods. The experimental results show that our method achieves higher accuracy and efficiency in query conceptualization. |
| Researcher Affiliation | Collaboration | Zhongyuan Wang, Kejun Zhao Renmin University of China Beijing, China {kejunzhao, mengxf}@ruc.edu.cn; Haixun Wang Microsoft Research Beijing, China zhy.wang@microsoft.com; Xiaofeng Meng, Ji-Rong Wen Google Research Mountain View, CA, USA haixun@google.com jirong.wen@gmail.com |
| Pseudocode | No | The paper describes its algorithm in Section 4 'Understanding Queries' and its subsections, including formulas like Eq 14, but it does not include a formally labeled 'Algorithm' or 'Pseudocode' block. |
| Open Source Code | No | The paper states 'Probase data is available at http://probase.msra.cn/dataset.aspx' but does not provide a link or explicit statement about the availability of the source code for the methodology described in the paper. |
| Open Datasets | Yes | In our work, we use a probabilistic lexical knowledge base known as Probase2 [Wu et al., 2012], but our techniques can be applied to other knowledge bases such as Yago. Probase data is available at http://probase.msra.cn/dataset.aspx |
| Dataset Splits | No | The paper states 'We create two labeled datasets out of randomly selected search queries. The first consists of 600 queries... The second also consists of 600 queries...', but it does not provide specific details on how these datasets were split into training, validation, or test sets for their experiments (e.g., percentages, sample counts, or methodology for creating splits). |
| Hardware Specification | No | The paper does not provide any specific details regarding the hardware (e.g., GPU models, CPU types, memory) used to conduct the experiments. |
| Software Dependencies | No | The paper mentions using the 'Stanford Parser' to process a web corpus, but it does not provide specific version numbers for the Stanford Parser or any other software libraries or dependencies used in their experiments. |
| Experiment Setup | No | The paper describes the general approach and algorithm for query understanding but does not provide specific experimental setup details such as hyperparameter values (e.g., learning rates, batch sizes, number of epochs) or other detailed training configurations. |