Related papers: Learning Recurrent Span Representations for Extrac…

Owing to the rapidly growing multimedia content available on the Internet, extractive spoken document summarization, with the purpose of automatically selecting a set of representative sentences from a spoken document to concisely express…

A fundamental trade-off between effectiveness and efficiency needs to be balanced when designing an online question answering system. Effectiveness comes from sophisticated functions such as extractive machine reading comprehension (MRC),…

Why do modern language models, trained to do well on next-word prediction, appear to generate coherent documents and capture long-range structure? Here we show that next-token prediction is provably powerful for learning longer-range…

While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive. Natural…

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so…

Event Extraction bridges the gap between text and event signals. Based on the assumption of trigger-argument dependency, existing approaches have achieved state-of-the-art performance with expert-designed templates or complicated decoding…

Long document question answering is a challenging task due to its demands for complex reasoning over long text. Previous works usually take long documents as non-structured flat texts or only consider the local structure in long documents.…

Recursive neural networks (RvNN) have been shown useful for learning sentence representations and helped achieve competitive performance on several natural language inference tasks. However, recent RvNN-based models fail to learn simple…

Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…

Causal knowledge extraction is the task of extracting relevant causes and effects from text by detecting the causal relation. Although this task is important for language understanding and knowledge discovery, recent works in this domain…

Sentence scoring and sentence selection are two main steps in extractive document summarization systems. However, previous works treat them as two separated subtasks. In this paper, we present a novel end-to-end neural network framework for…

We propose a novel constituency parsing model that casts the parsing problem into a series of pointing tasks. Specifically, our model estimates the likelihood of a span being a legitimate tree constituent via the pointing score…

Reading comprehension models are based on recurrent neural networks that sequentially process the document tokens. As interest turns to answering more complex questions over longer documents, sequential reading of large portions of text…

Explanations in a recommender system assist users in making informed decisions among a set of recommended items. Great research attention has been devoted to generating natural language explanations to depict how the recommendations are…

Recently, strong results have been demonstrated by Deep Recurrent Neural Networks on natural language transduction problems. In this paper we explore the representational power of these models using synthetic grammars designed to exhibit…

How to learn highly compact yet effective sentence representation? Pre-trained language models have been effective in many NLP tasks. However, these models are often huge and produce large sentence embeddings. Moreover, there is a big…

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…

We address the problem of extractive question answering using document-level distant super-vision, pairing questions and relevant documents with answer strings. We compare previously used probability space and distant super-vision…

Reading comprehension models answer questions posed in natural language when provided with a short passage of text. They present an opportunity to address a long-standing challenge in data management: the extraction of structured data from…

Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams. We argue that the explainability of this task should place…