Related papers: Select, Answer and Explain: Interpretable Multi-ho…
Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are…
Since real-world ubiquitous documents (e.g., invoices, tickets, resumes and leaflets) contain rich information, automatic document image understanding has become a hot topic. Most existing works decouple the problem into two separate tasks,…
Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…
Multiple-choice reading comprehension (MCRC) is the task of selecting the correct answer from multiple options given a question and an article. Existing MCRC models typically either read each option independently or compute a fixed-length…
Text entailment, the task of determining whether a piece of text logically follows from another piece of text, is a key component in NLP, providing input for many semantic applications such as question answering, text summarization,…
This paper presents a novel method to generate answers for non-extraction machine reading comprehension (MRC) tasks whose answers cannot be simply extracted as one span from the given passages. Using a pointer network-style extractive…
Document-level relation extraction (DocRE) attracts more research interest recently. While models achieve consistent performance gains in DocRE, their underlying decision rules are still understudied: Do they make the right predictions…
Multi-choice reading comprehension is a challenging task that requires complex reasoning procedure. Given passage and question, a correct answer need to be selected from a set of candidate answers. In this paper, we propose \textbf{D}ual…
Multi-hop question answering requires models to gather information from different parts of a text to answer a question. Most current approaches learn to address this task in an end-to-end way with neural networks, without maintaining an…
Interpretability is a pressing issue for machine learning. Common approaches to interpretable machine learning constrain interactions between features of the input, rendering the effects of those features on a model's output comprehensible…
Language-enabled AI systems can answer complex, multi-hop questions to high accuracy, but supporting answers with evidence is a more challenging task which is important for the transparency and trustworthiness to users. Prior work in this…
Multi-hop reasoning, which requires multi-step reasoning based on the supporting documents within a given context, remains challenging for large language models (LLMs). LLMs often struggle to filter out irrelevant documents within the…
Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition(QASC), that requires retrieving facts from a large…
Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic…
This paper is concerned with the task of multi-hop open-domain Question Answering (QA). This task is particularly challenging since it requires the simultaneous performance of textual reasoning and efficient searching. We present a method…
We propose a new CogQA framework for multi-hop question answering in web-scale documents. Inspired by the dual process theory in cognitive science, the framework gradually builds a \textit{cognitive graph} in an iterative process by…
We propose a simple yet robust stochastic answer network (SAN) that simulates multi-step reasoning in machine reading comprehension. Compared to previous work such as ReasoNet which used reinforcement learning to determine the number of…
Explaining automatically generated recommendations allows users to make more informed and accurate decisions about which results to utilize, and therefore improves their satisfaction. In this work, we develop a multi-task learning solution…
Effective multi-hop question answering (QA) requires reasoning over multiple scattered paragraphs and providing explanations for answers. Most existing approaches cannot provide an interpretable reasoning process to illustrate how these…
Multimedia or spoken content presents more attractive information than plain text content, but the former is more difficult to display on a screen and be selected by a user. As a result, accessing large collections of the former is much…