Related papers: Adaptive Latent Entity Expansion for Document Retr…

Query expansion is a widely used technique to improve the recall of search systems. In this paper, we propose an approach to query expansion that leverages the generative abilities of Large Language Models (LLMs). Unlike traditional query…

Retrieval augmentation is critical when Language Models (LMs) exploit non-parametric knowledge related to the query through external knowledge bases before reasoning. The retrieved information is incorporated into LMs as context alongside…

Query categorization is an essential part of query intent understanding in e-commerce search. A common query categorization task is to select the relevant fine-grained product categories in a product taxonomy. For frequent queries, rich…

Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information. Existing approaches either rely on expensive supervised fine-tuning to generate…

Neural retrieval models (NRMs) have been shown to outperform their statistical counterparts owing to their ability to capture semantic meaning via dense document representations. These models, however, suffer from poor interpretability as…

LLM-based search agents are increasingly trained on entity-centric synthetic data to solve complex, knowledge-intensive tasks. However, prevailing training methods like Group Relative Policy Optimization (GRPO) discard this rich entity…

Learned Sparse Retrieval (LSR) such as SPLADE has growing interest for effective semantic 1st stage matching while enjoying the efficiency of inverted indices. A recent work on learning SPLADE models with expanded vocabularies (ESPLADE) was…

Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user's queries in natural language. From classic retrieval methods to learning-based ranking…

Injecting textual information into knowledge graph (KG) entity representations has been a worthwhile expedition in terms of improving performance in KG oriented tasks within the NLP community. External knowledge often adopted to enhance KG…

Learned Sparse Retrieval (LSR) models use vocabularies from pre-trained transformers, which often split entities into nonsensical fragments. Splitting entities can reduce retrieval accuracy and limits the model's ability to incorporate…

Compared with English, Chinese suffers from more grammatical ambiguities, like fuzzy word boundaries and polysemous words. In this case, contextual information is not sufficient to support Chinese named entity recognition (NER), especially…

We focus on two research issues in entity search: scoring a document or snippet that potentially supports a candidate entity, and aggregating scores from different snippets into an entity score. Proximity scoring has been studied in IR…

Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…

Developing a universal model that can efficiently and effectively respond to a wide range of information access requests -- from retrieval to recommendation to question answering -- has been a long-lasting goal in the information retrieval…

In enterprise settings, efficiently retrieving relevant information from large and complex knowledge bases is essential for operational productivity and informed decision-making. This research presents a systematic empirical framework for…

Dense retrievers encode queries and documents and map them in an embedding space using pre-trained language models. These embeddings need to be high-dimensional to fit training signals and guarantee the retrieval effectiveness of dense…

Long-tail question answering presents significant challenges for large language models (LLMs) due to their limited ability to acquire and accurately recall less common knowledge. Retrieval-augmented generation (RAG) systems have shown great…

Parameter Efficient Fine-Tuning (PEFT) methods have been extensively utilized in Large Language Models (LLMs) to improve the down-streaming tasks without the cost of fine-tuing the whole LLMs. Recent studies have shown how to effectively…

Query and product relevance prediction is a critical component for ensuring a smooth user experience in e-commerce search. Traditional studies mainly focus on BERT-based models to assess the semantic relevance between queries and products.…

Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. If the entities are entirely absent from the…