Related papers: Towards Inference-Oriented Reading Comprehension: …
We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data. PMR can resolve the discrepancy…
Machine Reading Comprehension (MRC) is an active field in natural language processing with many successful developed models in recent years. Despite their high in-distribution accuracy, these models suffer from two issues: high training…
Recent studies have explored integrating large language models (LLMs) into recommendation systems but face several challenges, including training-induced bias and bottlenecks from serialized architecture. To effectively address these…
We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, which is difficult to solve with existing QA methods due…
Machine Reading Comprehension (MRC) models tend to take advantage of spurious correlations (also known as dataset bias or annotation artifacts in the research community). Consequently, these models may perform the MRC task without fully…
Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so by sharpening the distribution over full generated outputs, favoring completions that are…
Conversational Machine Reading (CMR) requires answering a user's initial question through multi-turn dialogue interactions based on a given document. Although there exist many effective methods, they largely neglected the alignment between…
This study aims at solving the Machine Reading Comprehension problem where questions have to be answered given a context passage. The challenge is to develop a computationally faster model which will have improved inference time. State of…
When humans learn to perform a difficult task (say, reading comprehension (RC) over longer passages), it is typically the case that their performance improves significantly on an easier version of this task (say, RC over shorter passages).…
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…
While neural networks with attention mechanisms have achieved superior performance on many natural language processing tasks, it remains unclear to which extent learned attention resembles human visual attention. In this paper, we propose a…
As a broad and major category in machine reading comprehension (MRC), the generalized goal of discriminative MRC is answer prediction from the given materials. However, the focuses of various discriminative MRC tasks may be diverse enough:…
Recent works using artificial neural networks based on distributed word representation greatly boost performance on various natural language processing tasks, especially the answer selection problem. Nevertheless, most of the previous works…
Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understandable way, the relationship between the input and output of…
We propose MRU (Multi-Range Reasoning Units), a new fast compositional encoder for machine comprehension (MC). Our proposed MRU encoders are characterized by multi-ranged gating, executing a series of parameterized contract-and-expand…
Machine reading comprehension (MRC) is a challenging task in natural language processing that makes computers understanding natural language texts and answer questions based on those texts. There are many techniques for solving this…
The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA). In this paper, we approach the problems by closely modelling questions in a neural…
Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear. We study this question in a controlled cellular-automata (1dCA) framework that excludes memorisation by using…
In spite of great advancements of machine reading comprehension (RC), existing RC models are still vulnerable and not robust to different types of adversarial examples. Neural models over-confidently predict wrong answers to semantic…
A challenge in creating a dataset for machine reading comprehension (MRC) is to collect questions that require a sophisticated understanding of language to answer beyond using superficial cues. In this work, we investigate what makes…