Related papers: Hierarchical Pre-training for Sequence Labelling i…

We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner. Recent pre-training methods in NLP focus on learning either bottom or top-level…

Recognizing emotions in conversations is a challenging task due to the presence of contextual dependencies governed by self- and inter-personal influences. Recent approaches have focused on modeling these dependencies primarily via…

Repository-level pretraining is commonly used to enable large language models for code to leverage codebase-wide context. This enhances their ability to generate accurate and context-aware code completions. In this work, we investigate how…

Dialogue act recognition is a fundamental task for an intelligent dialogue system. Previous work models the whole dialog to predict dialog acts, which may bring the noise from unrelated sentences. In this work, we design a hierarchical…

Large Language Models (LLMs) have made significant strides in handling long sequences. Some models like Gemini could even to be capable of dealing with millions of tokens. However, their performance evaluation has largely been confined to…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still…

Detecting emotion from dialogue is a challenge that has not yet been extensively surveyed. One could consider the emotion of each dialogue turn to be independent, but in this paper, we introduce a hierarchical approach to classify emotion,…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

We describe a neural transducer that maintains the flexibility of standard sequence-to-sequence (seq2seq) models while incorporating hierarchical phrases as a source of inductive bias during training and as explicit constraints during…

General scene perception has progressed from object recognition toward open-vocabulary grounding, part localization, and affordance prediction. Yet these capabilities are often realized as isolated predictions that localize objects, parts,…

Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representations to produce…

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…

In this paper, we propose Cross-Thought, a novel approach to pre-training sequence encoder, which is instrumental in building reusable sequence embeddings for large-scale NLP tasks such as question answering. Instead of using the original…

Dialogue disentanglement aims to detach the chronologically ordered utterances into several independent sessions. Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement…

Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization. In this work, we explore four different challenges of the task: handling and differentiating parts of the dialogue…

While existing hierarchical text classification (HTC) methods attempt to capture label hierarchies for model training, they either make local decisions regarding each label or completely ignore the hierarchy information during inference. To…

Different from the traditional classification tasks which assume mutual exclusion of labels, hierarchical multi-label classification (HMLC) aims to assign multiple labels to every instance with the labels organized under hierarchical…

We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource Speech Benchmark 2021: a suite of 4 black-box, zero-shot…

Emotion recognition in conversation, which aims to predict the emotion for all utterances, has attracted considerable research attention in recent years. It is a challenging task since the recognition of the emotion in one utterance…