Related papers: Looking Under the Hood : Tools for Diagnosing your…

In multilingual question answering, either the question needs to be translated into the document language, or vice versa. In addition to direction, there are multiple methods to perform the translation, four of which we explore in this…

Prior work in standardized science exams requires support from large text corpus, such as targeted science corpus fromWikipedia or SimpleWikipedia. However, retrieving knowledge from the large corpus is time-consuming and questions embedded…

Transformer based architectures have shown notable results on many down streaming tasks including question answering. The availability of data, on the other hand, impedes obtaining legitimate performance for low-resource languages. In this…

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…

In knowledge graph construction, a challenging issue is how to extract complex (e.g., overlapping) entities and relationships from a small amount of unstructured historical data. The traditional pipeline methods are to divide the extraction…

Answer selection and knowledge base question answering (KBQA) are two important tasks of question answering (QA) systems. Existing methods solve these two tasks separately, which requires large number of repetitive work and neglects the…

Cross-lingual Machine Reading Comprehension (xMRC) is challenging due to the lack of training data in low-resource languages. The recent approaches use training data only in a resource-rich language like English to fine-tune large-scale…

In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks. We propose a framework for multi-task learn- ing that enables one to selectively share the information…

In several question answering benchmarks, pretrained models have reached human parity through fine-tuning on an order of 100,000 annotated questions and answers. We explore the more realistic few-shot setting, where only a few hundred…

We consider the problem of adapting neural paragraph-level question answering models to the case where entire documents are given as input. Our proposed solution trains models to produce well calibrated confidence scores for their results…

Text-based Question Answering (QA) is a challenging task which aims at finding short concrete answers for users' questions. This line of research has been widely studied with information retrieval techniques and has received increasing…

A trending paradigm for multiple-choice question answering (MCQA) is using a text-to-text framework. By unifying data in different tasks into a single text-to-text format, it trains a generative encoder-decoder model which is both powerful…

Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. "Downstream" tasks, often based on sentence classification, are commonly used to…

We propose a new test to measure a text model's multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. To attain high accuracy on this test, models must possess extensive…

Answering multi-hop questions over hybrid factual knowledge from the given text and table (TextTableQA) is a challenging task. Existing models mainly adopt a retriever-reader framework, which have several deficiencies, such as noisy…

Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers…

This study proposes a new way of using WordNet for Query Expansion (QE). We choose candidate expansion terms, as usual, from a set of pseudo relevant documents; however, the usefulness of these terms is measured based on their definitions…

Question Answering (QA) is the task of automatically answering questions posed by humans in natural languages. There are different settings to answer a question, such as abstractive, extractive, boolean, and multiple-choice QA. As a popular…

The task of multiple choice question answering (MCQA) refers to identifying a suitable answer from multiple candidates, by estimating the matching score among the triple of the passage, question and answer. Despite the general research…

Embodied Question Answering (EQA) requires agents to explore 3D environments to obtain observations and answer questions related to the scene. Existing methods leverage VLMs to directly explore the environment and answer questions without…