paper-with-me

Papers

A Dual Embedding Space Model for Document Ranking

2016-02-02 · Bhaskar Mitra, Eric Nalisnick, Nick Craswell, Rich Caruana

A fundamental goal of search engines is to identify, given a query, documents that have relevant text. This is intrinsically difficult because the query and the document may use different vocabulary, or the document may contain query words without being relevant. We investigate neural word embeddings as a source of evidence in document ranking. We train a word2vec embedding model on a large unlabelled query corpus, but in contrast to how the model is commonly used, we retain both the input and the output projections, allowing us to leverage both the embedding spaces to derive richer distributional relationships. During ranking we map the query words into the input space and the document words into the output space, and compute a query-document relevance score by aggregating the cosine similarities across all the query-document word pairs. We postulate that the proposed Dual Embedding Space Model (DESM) captures evidence on whether a document is about a query term in addition to what is modelled by traditional term-frequency based approaches. Our experiments show that the DESM can re-rank top documents returned by a commercial Web search engine, like Bing, better than a term-matching based signal like TF-IDF. However, when ranking a larger set of candidate documents, we find the embeddings-based approach is prone to false positives, retrieving documents that are only loosely related to the query. We demonstrate that this problem can be solved effectively by ranking based on a linear mixture of the DESM and the word counting features.

📄 PDF Abstract BibTeX arXiv:1602.01137

Code (0)

등록된 구현이 없습니다.

Tasks

Document RankingmodelWord Embeddings

Similar Papers 제목 키워드 기반

More Robust Dense Retrieval with Contrastive Dual Learning

2021-07-16 · Yizhi Li, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu

Dense retrieval conducts text retrieval in the embedding space and has shown many advantages compared to sparse retrieval. Existing dense retrievers optimize representations of queries and documents with contrastive trai…

Contrastive LearningInformation RetrievalRetrievalText Retrieval

Consistency and Variation in Kernel Neural Ranking Model

2018-09-27 · Mary Arpita Pyreddy, Varshini Ramaseshan, Narendra Nath Joshi, Zhuyun Dai 외

This paper studies the consistency of the kernel-based neural ranking model K-NRM, a recent state-of-the-art neural IR model, which is important for reproducible research and deployment in the industry. We find that K-NR…

modelWord Embeddings

Efficient Document Ranking with Learnable Late Interactions

2024-06-25 · Ziwei Ji, Himanshu Jain, Andreas Veit, Sashank J. Reddi 외

Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models m…

Document RankingInformation RetrievalPassage Re-RankingRe-Ranking

Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking

2022-03-29 · ACL 2022 5 · Yingrui Yang, Yifan Qiao, Tao Yang

Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopted…

QuantizationRe-Ranking

Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopte…

QuantizationRe-Ranking