Related papers: DiscoFuse: A Large-Scale Dataset for Discourse-Bas…

The body movements accompanying speech aid speakers in expressing their ideas. Co-speech motion generation is one of the important approaches for synthesizing realistic avatars. Due to the intricate correspondence between speech and motion,…

With the further development of informatization, more and more data is stored in the form of text. There are some loss of text during their generation and transmission. The paper aims to establish a language model based on the large-scale…

While state-of-the-art Text-to-Speech systems can generate natural speech of very high quality at sentence level, they still meet great challenges in speech generation for paragraph / long-form reading. Such deficiencies are due to i)…

Spoken language translation applications for speech suffer due to conversational speech phenomena, particularly the presence of disfluencies. With the rise of end-to-end speech translation models, processing steps such as disfluency removal…

Automated multi-document extractive text summarization is a widely studied research problem in the field of natural language understanding. Such extractive mechanisms compute in some form the worthiness of a sentence to be included into the…

Contextual commonsense inference is the task of generating various types of explanations around the events in a dyadic dialogue, including cause, motivation, emotional reaction, and others. Producing a coherent and non-trivial explanation…

Academic writing should be concise as concise sentences better keep the readers' attention and convey meaning clearly. Writing concisely is challenging, for writers often struggle to revise their drafts. We introduce and formulate revising…

We compiled a new sentence splitting corpus that is composed of 203K pairs of aligned complex source and simplified target sentences. Contrary to previously proposed text simplification corpora, which contain only a small number of split…

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these capabilities without…

Extracting summaries from long documents can be regarded as sentence classification using the structural information of the documents. How to use such structural information to summarize a document is challenging. In this paper, we propose…

Record fusion is the task of aggregating multiple records that correspond to the same real-world entity in a database. We can view record fusion as a machine learning problem where the goal is to predict the "correct" value for each…

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to…

Open-domain question answering can be reformulated as a phrase retrieval problem, without the need for processing documents on-demand during inference (Seo et al., 2019). However, current phrase retrieval models heavily depend on sparse…

Deep neural networks have achieved great successes on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire. In this paper, we make the first…

Distant supervision (DS) is a well established technique for creating large-scale datasets for relation extraction (RE) without using human annotations. However, research in DS-RE has been mostly limited to the English language.…

Phrases are essential to understand the core concepts in conversations. However, due to their rare occurrence in training data, correct translation of phrases is challenging in speech translation tasks. In this paper, we propose a phrase…

Sequence-to-sequence (Seq2Seq) models with attention have excelled at tasks which involve generating natural language sentences such as machine translation, image captioning and speech recognition. Performance has further been improved by…

Recent advances in text-to-vision generation excel in visual fidelity but struggle with compositional generalization and semantic alignment. Existing datasets are noisy and weakly compositional, limiting models' understanding of complex…

Sentences that present a complex syntax act as a major stumbling block for downstream Natural Language Processing applications whose predictive quality deteriorates with sentence length and complexity. The task of Text Simplification (TS)…

In this paper, we focus on training and evaluating effective word embeddings with both text and visual information. More specifically, we introduce a large-scale dataset with 300 million sentences describing over 40 million images crawled…