Related papers: A Hierarchical Attention Based Seq2seq Model for C…
Rhetoric recognition is a critical component in automated essay scoring. By identifying rhetorical elements in student writing, AI systems can better assess linguistic and higher-order thinking skills, making it an essential task in the…
Recently, open-domain dialogue systems have attracted growing attention. Most of them use the sequence-to-sequence (Seq2Seq) architecture to generate responses. However, traditional Seq2Seq-based open-domain dialogue models tend to generate…
Recently, a variety of neural models have been proposed for lyrics generation. However, most previous work completes the generation process in a single pass with little human intervention. We believe that lyrics creation is a creative…
Researchers have recently started investigating deep neural networks for dialogue applications. In particular, generative sequence-to-sequence (Seq2Seq) models have shown promising results for unstructured tasks, such as word-level dialogue…
We study multi-turn response generation in chatbots where a response is generated according to a conversation context. Existing work has modeled the hierarchy of the context, but does not pay enough attention to the fact that words and…
Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…
The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval. Sequence-to-sequence (seq2seq) models, adopted from neural machine…
Outline generation aims to reveal the internal structure of a document by identifying underlying chapter relationships and generating corresponding chapter summaries. Although existing deep learning methods and large models perform well on…
Large language models (LLMs) have shown promise in formal theorem proving, but their token-level processing often fails to capture the inherent hierarchical nature of mathematical proofs. We introduce \textbf{Hierarchical Attention}, a…
The sequence-to-sequence (seq2seq) task aims at generating the target sequence based on the given input source sequence. Traditionally, most of the seq2seq task is resolved by the Encoder-Decoder framework which requires an encoder to…
Recently, symbolic music generation has become a focus of numerous deep learning research. Structure as an important part of music, contributes to improving the quality of music, and an increasing number of works start to study the…
We propose a novel model for multi-label text classification, which is based on sequence-to-sequence learning. The model generates higher-level semantic unit representations with multi-level dilated convolution as well as a corresponding…
Metaphors are common in everyday language, and the identification and understanding of metaphors are facilitated by models to achieve a better understanding of the text. Metaphors are mainly identified and generated by pre-trained models in…
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution. However, human learners readily…
Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models, a popular choice for set…
In this paper, we propose a technique to address the most challenging aspect of algorithmic songwriting process, which enables the human community to discover original lyrics, and melodies suitable for the generated lyrics. The proposed…
In this paper, we transform tag recommendation into a word-based text generation problem and introduce a sequence-to-sequence model. The model inherits the advantages of LSTM-based encoder for sequential modeling and attention-based decoder…
Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining…
Recent advances in text-to-speech have significantly improved the expressiveness of synthesized speech. However, it is still challenging to generate speech with contextually appropriate and coherent speaking style for multi-sentence text in…
Chinese Spelling Correction (CSC) aims to detect and correct spelling errors in Chinese sentences caused by phonetic or visual similarities. While current CSC models integrate pinyin or glyph features and have shown significant…