A Study of MatchPyramid Models on Ad-hoc Retrieval
arXiv:1606.04648
Abstract
Deep neural networks have been successfully applied to many text matching tasks, such as paraphrase identification, question answering, and machine translation. Although ad-hoc retrieval can also be formalized as a text matching task, few deep models have been tested on it. In this paper, we study a state-of-the-art deep matching model, namely MatchPyramid, on the ad-hoc retrieval task. The MatchPyramid model employs a convolutional neural network over the interactions between query and document to produce the matching score. We conducted extensive experiments to study the impact of different pooling sizes, interaction functions and kernel sizes on the retrieval performance. Finally, we show that the MatchPyramid models can significantly outperform several recently introduced deep matching models on the retrieval task, but still cannot compete with the traditional retrieval models, such as BM25 and language models.
arXiv commentNeu-IR '16 SIGIR Workshop on Neural Information Retrieval
References in corpus (3)
Cited by in corpus (25)
- Information Retrieval: Recent Advances and Beyond
- Modeling Diverse Relevance Patterns in Ad-hoc Retrieval
- Pretrained Transformers for Text Ranking: BERT and Beyond
- Neural Models for Information Retrieval
- Neural Information Retrieval: A Literature Review
- Neural ranking models for document retrieval
- A Study of Neural Matching Models for Cross-lingual IR
- Content-Based Weak Supervision for Ad-Hoc Re-Ranking
- Lexically-Accelerated Dense Retrieval
- Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
- Match-Tensor: a Deep Relevance Model for Search
- DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval
- A Deep Look into Neural Ranking Models for Information Retrieval
- Learning to Match Using Local and Distributed Representations of Text for Web Search
- LexBoost: Improving Lexical Document Retrieval with Nearest Neighbors
- NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval
- Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
- Co-PACRR: A Context-Aware Neural IR Model for Ad-hoc Retrieval
- Overcoming low-utility facets for complex answer retrieval
- Beyond Lexical: A Semantic Retrieval Framework for Textual SearchEngine
- An In-depth Analysis of Passage-Level Label Transfer for Contextual Document Ranking
- DE-PACRR: Exploring Layers Inside the PACRR Model
- Attentive Long Short-Term Preference Modeling for Personalized Product Search
- Exploiting Sentence-Level Representations for Passage Ranking
- Searching Personal Collections