• Publications
  • Influence
Neural Ranking Models with Weak Supervision
TLDR
This paper proposes to train a neural ranking model using weak supervision, where labels are obtained automatically without human annotators or any external resources, and suggests that supervised neural ranking models can greatly benefit from pre-training on large amounts of weakly labeled data that can be easily obtained from unsupervised IR models. Expand
Embedding-based Query Language Models
TLDR
This paper proposes to use word embeddings to incorporate and weight terms that do not occur in the query, but are semantically related to the query terms, and develops an embedding-based relevance model, an extension of the effective and robust relevance model approach. Expand
From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing
TLDR
The results demonstrate the importance of sparsity in neural IR models and show that dense representations can be pruned effectively, giving new insights about essential semantic features and their distributions. Expand
A Deep Look into Neural Ranking Models for Information Retrieval
TLDR
A deep look into the neural ranking models from different dimensions is taken to analyze their underlying assumptions, major design principles, and learning strategies to obtain a comprehensive empirical understanding of the existing techniques. Expand
Current challenges and visions in music recommender systems research
TLDR
This article identifies and shed light on what it believes are the most pressing challenges MRS research is facing, from both academic and industry perspectives and details possible future directions and visions for the further evolution of the field. Expand
ANTIQUE: A Non-factoid Question Answering Benchmark
TLDR
This paper develops and releases a collection of 2,626 open-domain non-factoid questions from a diverse set of categories, and includes a brief analysis of the data as well as baseline results on both classical and neural IR models. Expand
Relevance-based Word Embedding
TLDR
Both query expansion experiments on four TREC collections and query classification experiments on the KDD Cup 2005 dataset suggest that the relevance-based word embedding models significantly outperform state-of-the-art proximity-based embedding model, such as word2vec and GloVe. Expand
Estimating Embedding Vectors for Queries
TLDR
A theoretical framework for estimating query embedding vectors based on the individual embedding vector of vocabulary terms is proposed and a number of different implementations of this framework are provided and it is shown that the AWE method is a special case of the proposed framework. Expand
Generating Clarifying Questions for Information Retrieval
TLDR
A taxonomy of clarification for open-domain search queries is identified by analyzing large-scale query reformulation data sampled from Bing search logs, and supervised and reinforcement learning models for generating clarifying questions learned from weak supervision data are proposed. Expand
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
TLDR
This paper formulate the task of asking clarifying questions in open-domain information-seeking conversational systems, propose an offline evaluation methodology for the task, and collect a dataset, called Qulac, through crowdsourcing, which significantly outperforms competitive baselines. Expand
...
1
2
3
4
5
...