Related papers: Design Challenges for a Multi-Perspective Search E…
Users often have trouble formulating their information needs into words on the first try when searching online. This can lead to frustration, as they may have to reformulate their queries when retrieved information is not relevant. This can…
Our goal is to use formal methods to analyse normative documents written in English, such as privacy policies and service-level agreements. This requires the combination of a number of different elements, including information extraction…
Question answering (QA) systems for large document collections typically use pipelines that (i) retrieve possibly relevant documents, (ii) re-rank them, (iii) rank paragraphs or other snippets of the top-ranked documents, and (iv) select…
Large language models (LLMs) that have been trained on a corpus that includes large amount of code exhibit a remarkable ability to understand HTML code. As web interfaces are primarily constructed using HTML, we design an in-depth study to…
Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Existing work has combined these in simple "retrieve-then-read"…
Information Retriever (IR) aims to find the relevant documents (e.g. snippets, passages, and articles) to a given query at large scale. IR plays an important role in many tasks such as open domain question answering and dialogue systems,…
Information retrieval is a rapidly evolving field. However it still faces significant limitations in the scientific and industrial vast amounts of information, such as semantic divergence and vocabulary gaps in sparse retrieval, low…
Natural language understanding (NLU) of text is a fundamental challenge in AI, and it has received significant attention throughout the history of NLP research. This primary goal has been studied under different tasks, such as Question…
We are presenting a set of multilingual text analysis tools that can help analysts in any field to explore large document collections quickly in order to determine whether the documents contain information of interest, and to find the…
This paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can improve the overall performance. However, the pipeline system is…
Natural language provides a widely accessible and expressive interface for robotic agents. To understand language in complex environments, agents must reason about the full range of language inputs and their correspondence to the world.…
With the recent explosion in the size and complexity of source codebases and software projects, the need for efficient source code search engines has increased dramatically. Unfortunately, existing information retrieval-based methods fail…
The continued rise of neural networks and large language models in the more recent past has altered the natural language processing landscape, enabling new approaches towards typical language tasks and achieving mainstream success. Despite…
Existing methods for interactive image retrieval have demonstrated the merit of integrating user feedback, improving retrieval results. However, most current systems rely on restricted forms of user feedback, such as binary relevance…
Recent advances in large language models have enabled the development of viable generative retrieval systems. Instead of a traditional document ranking, generative retrieval systems often directly return a grounded generated text as a…
Many search systems work with large amounts of natural language data, e.g., search queries, user profiles, and documents. Building a successful search system requires a thorough understanding of textual data semantics, where deep learning…
Much has been discussed about how Large Language Models, Knowledge Graphs and Search Engines can be combined in a synergistic manner. A dimension largely absent from current academic discourse is the user perspective. In particular, there…
The goal of case-based retrieval is to assist physicians in the clinical decision making process, by finding relevant medical literature in large archives. We propose a research that aims at improving the effectiveness of case-based…
Query Understanding concerns about inferring the precise intent of search by the user with his formulated query, which is challenging because the queries are often very short and ambiguous. The report discusses the various kind of queries…
The rapid growth of web has resulted in vast volume of information. Information availability at a rapid speed to the user is vital. English language (or any for that matter) has lot of ambiguity in the usage of words. So there is no…