Последовательность в последовательность

In this paper, with the help of knowl- edge base, we build and formulate a se- mantic space to connect the source and target languages, and apply it to the …...

Most of the existing Neural Machine Translation (NMT) models focus on the conversion of sequential data and do not directly use syntactic information. We propose a novel end-to-end syntac- tic …...

AbstractWe interpret the predictions of any black-box structured input-structured output model around a specific input-output pair. Our method returns an “explanation” consisting of groups of input-output tokens that are causally …...

AbstractIn a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword …...

AbstractNeural attention models have achieved great success in different NLP tasks. However, they have not fulfilled their promise on the AMR parsing task due to the data sparsity issue. In …...

Following upon the last year’s CUNI sys- tem for automatic post-editing of machine translation output, we focus on exploit- ing the potential of sequence-to-sequence neural models for this task. In …...

AbstractSequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the response. Unlike translation, conversation responding …...

AbstractVideo captioning, the task of describing the content of a video, has seen some promising improvements in recent years with sequence-to-sequence models, but accurately learning the temporal and logical dynamics …...

AbstractWe propose a new sentence simplification task (Split-and-Rephrase) where the aim is to split a complex sentence into a meaning preserving sequence of shorter sentences. Like sentence simplification, splitting-and-rephrasing has …...

AbstractAlthough sequence-to-sequence (seq2seq) network has achieved significant success in many NLP tasks such as machine translation and text summarization, simply applying this approach to transition-based dependency parsing cannot yield a …...

AbstractThe study on human-computer conversation systems is a hot research topic nowadays. One of the prevailing methods to build the system is using the generative Sequence-to-Sequence (Seq2Seq) model through neural …...

AbstractIn the popular sequence to sequence (seq2seq) neural machine translation (NMT), there exist many weighted sum models (WSMs), each of which takes a set of input and generates one output. …...

Depending on the quality of the original document, Optical Character Recognition (OCR) can produce a range of errors – from erroneous letters to additional and spurious blank spaces. We applied …...

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 …...

Automatically generating video description is one of the approaches to enable computers to deeply understand videos, which can have a great impact and can be useful to many other applications. …...

AbstractWe present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers …...

AbstractAspect term extraction (ATE) aims at identifying all aspect terms in a sentence and is usually modeled as a sequence labeling problem. However, sequence labeling based methods cannot make full …...

AbstractSpoken language translation applications for speech suffer due to conversational speech phenomena, particularly the presence of disfluencies. With the rise of end-to-end speech translation models, processing steps such as disfluency …...

AbstractWe consider neural language generation under a novel problem setting: generating the words of a sentence according to the order of their first appearance in its lexicalized PCFG parse tree, …...

AbstractFor every patient’s visit to a clinician, a clinical note is generated documenting their medical conversation, including complaints discussed, treatments, and medical plans. Despite advances in natural language processing, automating …...

AbstractRecent 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 …...

We propose to study the automatic generation of descriptions from content editing activities in collaborative environments. We define such task as identifying the changes associated to two consecutive versions of …...

AbstractIn sequence-to-sequence models, classical optimal transport (OT) can be applied to semantically match generated sentences with target sentences. However, in non-parallel settings, target sentences are usually unavailable. To tackle this …...

AbstractEmbodied Vision and Language Task Completion requires an embodied agent to interpret natural language instructions and egocentric visual observations to navigate through and interact with environments. In this work, we …...

AbstractEven if recent Transformer-based architectures, such as BERT, achieved impressive results in semantic processing tasks, their fine-tuning stage still requires large scale training resources. Usually, Data Augmentation (DA) techniques can …...

AbstractSolving math word problems requires deductive reasoning over the quantities in the text. Various recent research efforts mostly relied on sequence-to-sequence or sequence-to-tree models to generate mathematical expressions without explicitly …...

AbstractThis paper presents MuCGEC, a multi-reference multi-source evaluation dataset for Chinese Grammatical Error Correction (CGEC), consisting of 7,063 sentences collected from three Chinese-as-a-Second-Language (CSL) learner sources. Each sentence is corrected …...

AbstractState-of-the-art data augmentation methods help improve the generalization of deep learning models. However, these methods often generate examples that contradict the preserving class labels. This is crucial for some natural …...

AbstractMost existing text generation models follow the sequence-to-sequence paradigm. Generative Grammar suggests that humans generate natural language texts by learning language grammar. We propose a syntax-guided generation schema, which generates …...

AbstractThis paper presents the extscMineTrans English-to-Chinese speech translation systems developed for two challenge tracks of IWSLT 2023, i.e., Offline Speech Translation (S2T) and Speech-to-Speech Translation (S2ST). For the S2T track, …...