Related papers: Faster Shift-Reduce Constituent Parsing with a Non…

We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation. Existing approaches to this problem use recurrent structures, which not only suffer from the long-term dependency problem…

The addition of syntax-aware decoding in Neural Machine Translation (NMT) systems requires an effective tree-structured neural network, a syntax-aware attention model and a language generation model that is sensitive to sentence structure.…

The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…

Processing sentence constituency trees in binarised form is a common and popular approach in literature. However, constituency trees are non-binary by nature. The binarisation procedure changes deeply the structure, furthering constituents…

Deep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees. In this paper, we…

In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent words. Byte-pair encoding (BPE) and its variants are the predominant approach…

The latest advancements in unsupervised learning of sentence embeddings predominantly involve employing contrastive learning-based (CL-based) fine-tuning over pre-trained language models. In this study, we analyze the latest sentence…

Neural semantic parsers usually fail to parse long and complex utterances into correct meaning representations, due to the lack of exploiting the principle of compositionality. To address this issue, we present a novel framework for…

In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models. Specifically, we achieve dynamic latency with only one model by using arbitrary right context during…

Models need appropriate inductive biases to effectively learn from small amounts of data and generalize systematically outside of the training distribution. While Transformers are highly versatile and powerful, they can still benefit from…

Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work proposes automatic methods…

Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers.…

In this paper, we study representation learning for multi-task decision-making in non-stationary environments. We consider the framework of sequential linear bandits, where the agent performs a series of tasks drawn from distinct sets…

This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive…

Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised…

We propose a method for non-projective dependency parsing by incrementally predicting a set of edges. Since the edges do not have a pre-specified order, we propose a set-based learning method. Our method blends graph, transition, and…

In hierarchical text classification, we perform a sequence of inference steps to predict the category of a document from top to bottom of a given class taxonomy. Most of the studies have focused on developing novels neural network…

Dependency parsing is the task of inferring natural language structure, often approached by modeling word interactions via attention through biaffine scoring. This mechanism works like self-attention in Transformers, where scores are…

In this paper, we propose a novel BTG-forest-based alignment method. Based on a fast unsupervised initialization of parameters using variational IBM models, we synchronously parse parallel sentences top-down and align hierarchically under…

We propose a soft gradient boosting framework for sequential regression that embeds a learnable linear feature transform within the boosting procedure. At each boosting iteration, we train a soft decision tree and learn a linear input…