相关论文: Unifying Question Answering, Text Classification, …

Information Extraction refers to a collection of tasks within Natural Language Processing (NLP) that identifies sub-sequences within text and their labels. These tasks have been used for many years to link extract relevant information and…

Models for reading comprehension (RC) commonly restrict their output space to the set of all single contiguous spans from the input, in order to alleviate the learning problem and avoid the need for a model that generates text explicitly.…

This paper introduces a new information extraction model for business documents. Different from prior studies which only base on span extraction or sequence labeling, the model takes into account advantage of both span extraction and…

The reading comprehension task, that asks questions about a given evidence document, is a central problem in natural language understanding. Recent formulations of this task have typically focused on answer selection from a set of…

Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…

Span extraction, aiming to extract text spans (such as words or phrases) from plain texts, is a fundamental process in Information Extraction. Recent works introduce the label knowledge to enhance the text representation by formalizing the…

Text compression has diverse applications such as Summarization, Reading Comprehension and Text Editing. However, almost all existing approaches require either hand-crafted features, syntactic labels or parallel data. Even for one that…

We analyze various methods for single-label and multi-label text classification across well-known datasets, categorizing them into bag-of-words, sequence-based, graph-based, and hierarchical approaches. Despite the surge in methods like…

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…

Joint extraction of entities and relations aims to detect entity pairs along with their relations using a single model. Prior work typically solves this task in the extract-then-classify or unified labeling manner. However, these methods…

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple…

We introduce SpERT, an attention model for span-based joint entity and relation extraction. Our key contribution is a light-weight reasoning on BERT embeddings, which features entity recognition and filtering, as well as relation…

We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random tokens, and (2) training the span boundary…

Estimation of semantic similarity is an important research problem both in natural language processing and the natural language understanding, and that has tremendous application on various downstream tasks such as question answering,…

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Extracting entities and relations is an essential task of information extraction. Triplets extracted from a sentence might overlap with each other. Previous methods either did not address the overlapping issues or solved overlapping issues…

Existing techniques for text detection can be broadly classified into two primary groups: segmentation-based and regression-based methods. Segmentation models offer enhanced robustness to font variations but require intricate…

Dense retrieval has shown promising results in many information retrieval (IR) related tasks, whose foundation is high-quality text representation learning for effective search. Some recent studies have shown that autoencoder-based language…

Dense vector representations for sentences made significant progress in recent years as can be seen on sentence similarity tasks. Real-world phrase retrieval applications, on the other hand, still encounter challenges for effective use of…

A health outcome is a measurement or an observation used to capture and assess the effect of a treatment. Automatic detection of health outcomes from text would undoubtedly speed up access to evidence necessary in healthcare decision…