相关论文: Dialog2Flow: Pre-training Soft-Contrastive Action-…

Sentence compression is the task of creating a shorter version of an input sentence while keeping important information. In this paper, we extend the task of compression by deletion with the use of contextual embeddings. Different from…

Video captioning aims to understand the spatio-temporal semantic concept of the video and generate descriptive sentences. The de-facto approach to this task dictates a text generator to learn from \textit{offline-extracted} motion or…

Accurate detection of disfluencies in spoken language is crucial for enhancing the performance of automatic speech and language processing systems, as well as fostering the development of more inclusive speech and language technologies.…

The increasing prevalence of Large Language Models (LMs) in critical applications highlights the need for controlled language generation strategies that are not only computationally efficient but that also enjoy performance guarantees. To…

Transformer-based language models (LMs) pretrained on large text collections are proven to store a wealth of semantic knowledge. However, 1) they are not effective as sentence encoders when used off-the-shelf, and 2) thus typically lag…

There have been many successful applications of sentence embedding methods. However, it has not been well understood what properties are captured in the resulting sentence embeddings depending on the supervision signals. In this paper, we…

Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers from sufficient token overhead and a fixed reasoning…

To ensure satisfactory user experience, dialog systems must be able to determine whether an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID sentences are available as training data because collecting enough…

Contextual adaptation in token embeddings plays a central role in determining how well language models maintain coherence and retain semantic relationships over extended text sequences. Static embeddings often impose constraints on lexical…

Continual learning requires balancing plasticity and stability while mitigating catastrophic forgetting. Inspired by human dreaming as a mechanism for internal simulation and knowledge restructuring, we introduce Dream2Learn (D2L), a…

Word embeddings have made enormous inroads in recent years in a wide variety of text mining applications. In this paper, we explore a word embedding-based architecture for predicting the relevance of a role between two financial entities…

We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled data. The approach distills reliable predictions from a teacher network, and uses these predictions as annotations to guide a student network…

Recent advances in generative machine learning models rekindled research interest in the area of password guessing. Data-driven password guessing approaches based on GANs, language models and deep latent variable models have shown…

Word embedding is a Natural Language Processing (NLP) technique that automatically maps words from a vocabulary to vectors of real numbers in an embedding space. It has been widely used in recent years to boost the performance of a vari-ety…

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for…

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…

Speech-driven facial animation methods usually contain two main classes, 3D and 2D talking face, both of which attract considerable research attention in recent years. However, to the best of our knowledge, the research on 3D talking face…

Learning sentence embeddings is a fundamental problem in natural language processing. While existing research primarily focuses on enhancing the quality of sentence embeddings, the exploration of sentence embedding dimensions is limited.…

Contrastive learning has shown promising potential for learning robust representations by utilizing unlabeled data. However, constructing effective positive-negative pairs for contrastive learning on facial behavior datasets remains…

Word embeddings are a fixed, distributional representation of the context of words in a corpus learned from word co-occurrences. Despite their proven utility in machine learning tasks, word embedding models may capture uneven semantic and…