Neural Methods

AbstractNeural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence …...

AbstractMultimodal semantic models that extend linguistic representations with additional perceptual input have proved successful in a range of natural language processing (NLP) tasks. Recent research has successfully used neural methods …...

AbstractUnsupervised constituency parsing aims to learn a constituency parser from a training corpus without parse tree annotations. While many methods have been proposed to tackle the problem, including statistical and …...

AbstractThe successful application of neural methods to machine translation has realized huge quality advances for the community. With these improvements, many have noted outstanding challenges, including the modeling and treatment …...

AbstractBooks are typically segmented into chapters and sections, representing coherent sub-narratives and topics. We investigate the task of predicting chapter boundaries, as a proxy for the general task of segmenting …...

AbstractNeural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always available across languages. …...

AbstractLemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Most prior work on ML based lemmatization has focused on …...

AbstractThis paper focuses on paraphrase generation,which is a widely studied natural language generation task in NLP. With the development of neural models, paraphrase generation research has exhibited a gradual shift …...

AbstractNamed entity recognition has become an increasingly useful tool for digital humanities research, specially when it comes to historical texts. However, historical texts pose a wide range of challenges to …...

AbstractWhile neural methods for text-to-speech (TTS) have shown great advances in modeling multiple speakers, even in zero-shot settings, the amount of data needed for those approaches is generally not feasible …...