Related papers: A Divide-and-Conquer Strategy for Parsing
It is a challenging task to accurately perform semantic segmentation due to the complexity of real picture scenes. Many semantic segmentation methods based on traditional deep learning insufficiently captured the semantic and appearance…
The automation of document processing is gaining recent attention due to the great potential to reduce manual work through improved methods and hardware. Neural networks have been successfully applied before - even though they have been…
Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success relies on augmenting…
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…
Recent years the task of incomplete utterance rewriting has raised a large attention. Previous works usually shape it as a machine translation task and employ sequence to sequence based architecture with copy mechanism. In this paper, we…
Past work on unsupervised parsing is constrained to written form. In this paper, we present the first study on unsupervised spoken constituency parsing given unlabeled spoken sentences and unpaired textual data. The goal is to determine the…
We present a simple document alignment method that incorporates sentence order information in both candidate generation and candidate re-scoring. Our method results in 61% relative reduction in error compared to the best previously…
Sentence embedding methods offer a powerful approach for working with short textual constructs or sequences of words. By representing sentences as dense numerical vectors, many natural language processing (NLP) applications have improved…
We address the text-to-text generation problem of sentence-level paraphrasing -- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach applies multiple-sequence alignment to sentences gathered…
Breaking long documents into smaller segments is a fundamental challenge in information retrieval. Whether for search engines, question-answering systems, or retrieval-augmented generation (RAG), effective segmentation determines how well…
Sentence simplification reduces semantic complexity to benefit people with language impairments. Previous simplification studies on the sentence level and word level have achieved promising results but also meet great challenges. For…
Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…
Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, search, and dialogue. In this…
Sequential sentence classification deals with the categorisation of sentences based on their content and context. Applied to scientific texts, it enables the automatic structuring of research papers and the improvement of academic search…
This paper proposes some modest improvements to Extractor, a state-of-the-art keyphrase extraction system, by using a terabyte-sized corpus to estimate the informativeness and semantic similarity of keyphrases. We present two techniques to…
Text segmentation, the task of dividing a document into sections, is often a prerequisite for performing additional natural language processing tasks. Existing text segmentation methods have typically been developed and tested using clean,…
The capacitated arc routing problem is a very important problem with many practical applications. This paper focuses on the large scale capacitated arc routing problem. Traditional solution optimization approaches usually fail because of…
We introduce and asses several Divide \& Conquer heuristic strategies aimed to solve large instances of the 0-1 Minimization Knapsack Problem. The method subdivides a large problem in two smaller ones (or recursive iterations of the same…
Both bottom-up and top-down strategies have been used for neural transition-based constituent parsing. The parsing strategies differ in terms of the order in which they recognize productions in the derivation tree, where bottom-up…
Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype learning paradigm to…