Related papers: Frustratingly Easy Natural Question Answering

Speech Emotion Recognition (SER) plays a key role in advancing human-computer interaction. Attention mechanisms have become the dominant approach for modeling emotional speech due to their ability to capture long-range dependencies and…

Many extractive question answering models are trained to predict start and end positions of answers. The choice of predicting answers as positions is mainly due to its simplicity and effectiveness. In this study, we hypothesize that when…

Conversational question answering (ConvQA) is a simplified but concrete setting of conversational search. One of its major challenges is to leverage the conversation history to understand and answer the current question. In this work, we…

The availability of large, high-quality datasets has been one of the main drivers of recent progress in question answering (QA). Such annotated datasets however are difficult and costly to collect, and rarely exist in languages other than…

Question answering (QA) is an important natural language processing (NLP) task and has received much attention in academic research and industry communities. Existing QA studies assume that questions are raised by humans and answers are…

BERT model has been successfully applied to open-domain QA tasks. However, previous work trains BERT by viewing passages corresponding to the same question as independent training instances, which may cause incomparable scores for answers…

The performance of Open-Domain Question Answering (ODQA) retrieval systems can exhibit sub-optimal behavior, providing text excerpts with varying degrees of irrelevance. Unfortunately, many existing ODQA datasets lack examples specifically…

Neural models that independently project questions and answers into a shared embedding space allow for efficient continuous space retrieval from large corpora. Independently computing embeddings for questions and answers results in late…

We build four new test sets for the Stanford Question Answering Dataset (SQuAD) and evaluate the ability of question-answering systems to generalize to new data. Our first test set is from the original Wikipedia domain and measures the…

Recent advances with language models (e.g. BERT, XLNet, ...), have allowed surpassing human performance on complex NLP tasks such as Reading Comprehension. However, labeled datasets for training are available mostly in English which makes…

Methods for Visual Question Anwering (VQA) are notorious for leveraging dataset biases rather than performing reasoning, hindering generalization. It has been recently shown that better reasoning patterns emerge in attention layers of a…

Machine reading comprehension has made great progress in recent years owing to large-scale annotated datasets. In the clinical domain, however, creating such datasets is quite difficult due to the domain expertise required for annotation.…

We investigate the self-attention mechanism of BERT in a fine-tuning scenario for the classification of scientific articles over a taxonomy of research disciplines. We observe how self-attention focuses on words that are highly related to…

A major challenge of research on non-English machine reading for question answering (QA) is the lack of annotated datasets. In this paper, we present GermanQuAD, a dataset of 13,722 extractive question/answer pairs. To improve the…

Question answering (QA) can only make progress if we know if an answer is correct, but current answer correctness (AC) metrics struggle with verbose, free-form answers from large language models (LLMs). There are two challenges with current…

A large number of reading comprehension (RC) datasets has been created recently, but little analysis has been done on whether they generalize to one another, and the extent to which existing datasets can be leveraged for improving…

A question answering (QA) system is a type of conversational AI that generates natural language answers to questions posed by human users. QA systems often form the backbone of interactive dialogue systems, and have been studied extensively…

Recent progress in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks. Whilst learning linguistic knowledge, these models may also be storing relational knowledge present in the…

There are several issues with the existing general machine translation or natural language generation evaluation metrics, and question-answering (QA) systems are indifferent in that context. To build robust QA systems, we need the ability…

Scholastic trivia competitions test knowledge and intelligence through mastery of question answering. Modern question answering benchmarks are one variant of the Turing test. Specifically, answering a set of questions as well as a human is…