Related papers: Latent Retrieval for Weakly Supervised Open Domain…

Knowledge-based question answering relies on the availability of facts, the majority of which cannot be found in structured sources (e.g. Wikipedia info-boxes, Wikidata). One of the major components of extracting facts from unstructured…

Conversational search is one of the ultimate goals of information retrieval. Recent research approaches conversational search by simplified settings of response ranking and conversational question answering, where an answer is either…

The information retrieval community has recently witnessed a revolution due to large pretrained transformer models. Another key ingredient for this revolution was the MS MARCO dataset, whose scale and diversity has enabled zero-shot…

A compelling approach to complex question answering is to convert the question to a sequence of actions, which can then be executed on the knowledge base to yield the answer, aka the programmer-interpreter approach. Use similar training…

Open-domain Question Answering (ODQA) has achieved significant results in terms of supervised learning manner. However, data annotation cannot also be irresistible for its huge demand in an open domain. Though unsupervised QA or…

Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to logical forms or database queries. Such…

Video question answering that requires external knowledge beyond the visual content remains a significant challenge in AI systems. While models can effectively answer questions based on direct visual observations, they often falter when…

The task of Information Retrieval (IR) requires a system to identify relevant documents based on users' information needs. In real-world scenarios, retrievers are expected to not only rely on the semantic relevance between the documents and…

Automatic relation extraction (RE) for types of interest is of great importance for interpreting massive text corpora in an efficient manner. Traditional RE models have heavily relied on human-annotated corpus for training, which can be…

Dense retrieval (DR) approaches based on powerful pre-trained language models (PLMs) achieved significant advances and have become a key component for modern open-domain question-answering systems. However, they require large amounts of…

Training and refreshing a web-scale Question Answering (QA) system for a multi-lingual commercial search engine often requires a huge amount of training examples. One principled idea is to mine implicit relevance feedback from user behavior…

Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge. While promising, this approach requires to use models with billions of parameters, which are expensive to train and…

Large Language Models~(LLMs) are prone to hallucinations, and Retrieval-Augmented Generation (RAG) helps mitigate this, but at a high computational cost while risking misinformation. Adaptive retrieval aims to retrieve only when necessary,…

Despite limited success, information retrieval (IR) systems today are not intelligent or reliable. IR systems return poor search results when users formulate their information needs into incomplete or ambiguous queries (i.e., weak queries).…

Retrieval-augmented models have proven to be effective in natural language processing tasks, yet there remains a lack of research on their optimization using variational inference. We introduce the Variational Open-Domain (VOD) framework…

Open-retrieval question answering systems are generally trained and tested on large datasets in well-established domains. However, low-resource settings such as new and emerging domains would especially benefit from reliable question…

A popular recent approach to answering open-domain questions is to first search for question-related passages and then apply reading comprehension models to extract answers. Existing methods usually extract answers from single passages…

Despite extensive research on a wide range of question answering (QA) systems, most existing work focuses on answer containment-i.e., assuming that answers can be directly extracted and/or generated from documents in the corpus. However,…

Multilingual information retrieval (IR) is challenging since annotated training data is costly to obtain in many languages. We present an effective method to train multilingual IR systems when only English IR training data and some parallel…

In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop…