Related papers: Syntactic representation learning for neural netwo…

We propose a novel training strategy for Tacotron-based text-to-speech (TTS) system to improve the expressiveness of speech. One of the key challenges in prosody modeling is the lack of reference that makes explicit modeling difficult. The…

We use reinforcement learning to learn tree-structured neural networks for computing representations of natural language sentences. In contrast with prior work on tree-structured models in which the trees are either provided as input or…

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…

In this paper, we investigate to which extent contextual neural language models (LMs) implicitly learn syntactic structure. More concretely, we focus on constituent structure as represented in the Penn Treebank (PTB). Using standard probing…

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…

Parsing sentences into syntax trees can benefit downstream applications in NLP. Transition-based parsers build trees by executing actions in a state transition system. They are computationally efficient, and can leverage machine learning to…

People exploit the predictability of lexical structures during text comprehension. Though predictable structure is also present in speech, the degree to which prosody, e.g. intonation, tempo, and loudness, contributes to such structure…

Prosody is essential for speech technology, shaping comprehension, naturalness, and expressiveness. However, current text-to-speech (TTS) systems still struggle to accurately capture human-like prosodic variation, in part because existing…

Syntax has been shown to benefit Coreference Resolution from incorporating long-range dependencies and structured information captured by syntax trees, either in traditional statistical machine learning based systems or recently proposed…

For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) plays an important role in producing natural and intelligible speech. Although inter-utterance linguistic information can influence the speech interpretation of the…

Syntactic language models (SLMs) enhance Transformers by incorporating syntactic biases through the modeling of linearized syntactic parse trees alongside surface sentences. This paper focuses on compositional SLMs that are based on…

Although text-to-speech (TTS) systems have significantly improved, most TTS systems still have limitations in synthesizing speech with appropriate phrasing. For natural speech synthesis, it is important to synthesize the speech with a…

Existing neural semantic parsers mainly utilize a sequence encoder, i.e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees. In this paper,…

Writing style is a combination of consistent decisions at different levels of language production including lexical, syntactic, and structural associated to a specific author (or author groups). While lexical-based models have been widely…

Neural sequence-to-sequence text-to-speech synthesis (TTS), such as Tacotron-2, transforms text into high-quality speech. However, generating speech with natural prosody still remains a challenge. Yasuda et. al. show that unlike natural…

Tacotron-based end-to-end speech synthesis has shown remarkable voice quality. However, the rendering of prosody in the synthesized speech remains to be improved, especially for long sentences, where prosodic phrasing errors can occur…

In this work, we propose a novel constituency parsing scheme. The model predicts a vector of real-valued scalars, named syntactic distances, for each split position in the input sentence. The syntactic distances specify the order in which…

In this paper, we propose a feature reinforcement method under the sequence-to-sequence neural text-to-speech (TTS) synthesis framework. The proposed method utilizes the multiple input encoder to take three levels of text information, i.e.,…

In recent times, it has been shown that one can use code as data to aid various applications such as automatic commit message generation, automatic generation of pull request descriptions and automatic program repair. Take for instance the…

Neural network architectures have been augmented with differentiable stacks in order to introduce a bias toward learning hierarchy-sensitive regularities. It has, however, proven difficult to assess the degree to which such a bias is…