Related papers: I^3 Retriever: Incorporating Implicit Interaction …

Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…

Interactive and non-interactive model are the two de-facto standard frameworks in vector-based cross-lingual information retrieval (V-CLIR), which embed queries and documents in synchronous and asynchronous fashions, respectively. From the…

We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved items is a combinatorial optimization problem, generally…

Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers.…

Vector embeddings from pre-trained language models form a core component in Neural Information Retrieval systems across a multitude of knowledge extraction tasks. The paradigm of late interaction, introduced in ColBERT, demonstrates high…

Recent studies indicate that dense retrieval models struggle to perform well on a wide variety of retrieval tasks that lack dedicated training data, as different retrieval tasks often entail distinct search intents. To address this…

Transformer-based end-to-end speech recognition has achieved great success. However, the large footprint and computational overhead make it difficult to deploy these models in some real-world applications. Model compression techniques can…

Memory plays a key role in enhancing LLMs' performance when deployed to real-world applications. Existing solutions face trade-offs: explicit memory designs based on external storage require complex management and incur storage overhead,…

In-context Learning (ICL) is an emerging few-shot learning paradigm on Language Models (LMs) with inner mechanisms un-explored. There are already existing works describing the inner processing of ICL, while they struggle to capture all the…

Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks. While many neural IR methods encode queries and documents into single-vector representations, late interaction models produce…

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…

Current interactive systems with natural language interfaces lack the ability to understand a complex information-seeking request which expresses several implicit constraints at once, and there is no prior information about user preferences…

While in-context Learning (ICL) has proven to be an effective technique to improve the performance of Large Language Models (LLMs) in a variety of complex tasks, notably in translating natural language questions into Structured Query…

This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising…

Existing top-performance autonomous driving systems typically rely on the multi-modal fusion strategy for reliable scene understanding. This design is however fundamentally restricted due to overlooking the modality-specific strengths and…

Pre-trained language models are increasingly important components across multiple information retrieval (IR) paradigms. Late interaction, introduced with the ColBERT model and recently refined in ColBERTv2, is a popular paradigm that holds…

Recent progress in Natural Language Understanding (NLU) is driving fast-paced advances in Information Retrieval (IR), largely owed to fine-tuning deep language models (LMs) for document ranking. While remarkably effective, the ranking…

Ranker and retriever are two important components in dense passage retrieval. The retriever typically adopts a dual-encoder model, where queries and documents are separately input into two pre-trained models, and the vectors generated by…

Over the last few years, contextualized pre-trained transformer models such as BERT have provided substantial improvements on information retrieval tasks. Recent approaches based on pre-trained transformer models such as BERT, fine-tune…

Pre-trained Transformers (\eg BERT) have been commonly used in existing dense retrieval methods for parameter initialization, and recent studies are exploring more effective pre-training tasks for further improving the quality of dense…