A Short Introduction to Learning to Rank

Li, Hang

doi:10.1587/transinf.e94.d.1854

Cited by 251 publications

(141 citation statements)

References 16 publications

Supporting

Mentioning

137

Contrasting

Unclassified

Order By: Relevance

“…4). In two-dimensional space, f (s) is proved to be increasing along each coordinate if control points are restricted in the interior of the hypercube [0, 1] d [14]. Thus, a proposition can be deduced by Lemma 1.…”

Section: Rpc Formulation With Bézier Curvesmentioning

confidence: 98%

Unsupervised ranking of multi-attribute objects based on principal curves

Liu

Mei

2016

2016 IEEE 32nd International Conference on Data Engineering (ICDE)

View full text Add to dashboard Cite

Abstract-Unsupervised ranking faces one critical challenge in evaluation applications, that is, no ground truth is available. When PageRank and its variants show a good solution in related subjects, they are applicable only for ranking from link-structure data. In this work, we focus on unsupervised ranking from multi-attribute data which is also common in evaluation tasks. To overcome the challenge, we propose five essential meta-rules for the design and assessment of unsupervised ranking approaches: scale and translation invariance, strict monotonicity, linear/nonlinear capacities, smoothness, and explicitness of parameter size. These metarules are regarded as high level knowledge for unsupervised ranking tasks. Inspired by the works in [8] and [14], we propose a ranking principal curve (RPC) model, which learns a one-dimensional manifold function to perform unsupervised ranking tasks on multi-attribute observations. Furthermore, the RPC is modeled to be a cubic Bézier curve with control points restricted in the interior of a hypercube, thereby complying with all the five meta-rules to infer a reasonable ranking list. With control points as the model parameters, one is able to understand the learned manifold and to interpret the ranking list semantically. Numerical experiments of the presented RPC model are conducted on two open datasets of different ranking applications. In comparison with the state-of-the-art approaches, the new model is able to show more reasonable ranking lists.

show abstract

Section: Rpc Formulation With Bézier Curvesmentioning

confidence: 98%

Unsupervised ranking of multi-attribute objects based on principal curves

Liu

Mei

2016

2016 IEEE 32nd International Conference on Data Engineering (ICDE)

View full text Add to dashboard Cite

show abstract

“…There are generally three formulations (Li, 2011): pointwise ranking, pairwise ranking, and listwise ranking. The goal is to learn a ranking function f (w, tp i ) → y i where tp i denotes a text pair <s1,s2>.…”

Section: Learning To Rank Semantic Coherencementioning

confidence: 99%

Learning to Rank Semantic Coherence for Topic Segmentation

Wang

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Topic segmentation plays an important role for discourse parsing and information retrieval. Due to the absence of training data, previous work mainly adopts unsupervised methods to rank semantic coherence between paragraphs for topic segmentation. In this paper, we present an intuitive and simple idea to automatically create a "quasi" training dataset, which includes a large amount of text pairs from the same or different documents with different semantic coherence. With the training corpus, we design a symmetric CNN neural network to model text pairs and rank the semantic coherence within the learning to rank framework. Experiments show that our algorithm is able to achieve competitive performance over strong baselines on several real-world datasets.

show abstract

“…This approach typically views the entire ranked list of documents as a learning instance while optimizing some objective function defined over all of the documents, such as, normalized discounted cumulative gain (NDCG) [2]. We refer the readers who are interested in more details of LTR to [4,17,14] for more comprehensive reviews.…”

Section: Learning To Rankmentioning

confidence: 99%

“…Coordinate Ascent algorithm has also been shown to be effective for learning linear ranking functions in some other search domains [19]. One key benefit of listwise learning-to-rank approach over pointwise and pairwise ones is that the listwise approach can optimize ranking-based metrics directly [14,17]. The objective function we optimize in the learning process is normalized discounted cumulative gain (NDCG@K) defined on the graded relevance labels as described above.…”

Section: Existing Features and Learning Algorithmmentioning

confidence: 99%

From Query-By-Keyword to Query-By-Example

Ha-Thuc

Yan

et al. 2017

Proceedings of the 2017 ACM on Conference on Information and Knowledge Management

View full text Add to dashboard Cite

One key challenge in talent search is to translate complex criteria of a hiring position into a search query, while it is relatively easy for a searcher to list examples of suitable candidates for a given position. To improve search efficiency, we propose the next generation of talent search at LinkedIn, also referred to as Search By Ideal Candidates. In this system, a searcher provides one or several ideal candidates as the input to hire for a given position. The system then generates a query based on the ideal candidates and uses it to retrieve and rank results. Shifting from the traditional QueryBy-Keyword to this new Query-By-Example system poses a number of challenges: How to generate a query that best describes the candidates? When moving to a completely different paradigm, how does one leverage previous product logs to learn ranking models and/or evaluate the new system with no existing usage logs? Finally, given the different nature between the two search paradigms, the ranking features typically used for Query-By-Keyword systems might not be optimal for Query-By-Example. This paper describes our approach to solving these challenges. We present experimental results confirming the effectiveness of the proposed solution, particularly on query building and search ranking tasks. As of writing this paper, the new system has been available to all LinkedIn members.

show abstract

A Short Introduction to Learning to Rank

Cited by 251 publications

References 16 publications

Unsupervised ranking of multi-attribute objects based on principal curves

Unsupervised ranking of multi-attribute objects based on principal curves

Learning to Rank Semantic Coherence for Topic Segmentation

From Query-By-Keyword to Query-By-Example

Contact Info

Product

Resources

About