Related papers: Task-Aware Specialization for Efficient and Robust…

This paper presents a novel open-domain dialogue generation model emphasizing the differentiation of speakers in multi-turn conversations. Differing from prior work that solely relies on the content of conversation history to generate a…

In this paper, we tackle the new Language-Based Audio Retrieval task proposed in DCASE 2022. Firstly, we introduce a simple, scalable architecture which ties both the audio and text encoder together. Secondly, we show that using this…

Attention-based recurrent neural encoder-decoder models present an elegant solution to the automatic speech recognition problem. This approach folds the acoustic model, pronunciation model, and language model into a single network and…

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory…

Dense embedding models are commonly deployed in commercial search engines, wherein all the document vectors are pre-computed, and near-neighbor search (NNS) is performed with the query vector to find relevant documents. However, the…

When translating natural language questions into SQL queries to answer questions from a database, we would like our methods to generalize to domains and database schemas outside of the training set. To handle complex questions and database…

Most existing deep multi-task learning models are based on parameter sharing, such as hard sharing, hierarchical sharing, and soft sharing. How choosing a suitable sharing mechanism depends on the relations among the tasks, which is not…

We introduce two pre-trained retrieval focused multilingual sentence encoding models, respectively based on the Transformer and CNN model architectures. The models embed text from 16 languages into a single semantic space using a multi-task…

This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner. Unlike conventional approaches of applying evolution or reinforcement learning over a discrete and non-differentiable…

Decoder-based transformers, while revolutionizing language modeling and scaling to immense sizes, have not completely overtaken encoder-heavy architectures in natural language processing. Specifically, encoder-only models remain dominant in…

There are two approaches for pairwise sentence scoring: Cross-encoders, which perform full-attention over the input pair, and Bi-encoders, which map each input independently to a dense vector space. While cross-encoders often achieve higher…

Auto Composing is an active and appealing research area in the past few years, and lots of efforts have been put into inventing more robust models to solve this problem. With the fast evolution of deep learning techniques, some deep neural…

The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer…

Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases.…

Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs). However, they typically rely on autoencoders constrained by some training-time regularization on…

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that…

Passage retrieval addresses the problem of locating relevant passages, usually from a large corpus, given a query. In practice, lexical term-matching algorithms like BM25 are popular choices for retrieval owing to their efficiency. However,…

Discrete diffusion models enable parallel token sampling for faster inference than autoregressive approaches. However, prior diffusion models use a decoder-only architecture, which requires sampling algorithms that invoke the full network…

Interactive speech recognition systems must generate words quickly while also producing accurate results. Two-pass models excel at these requirements by employing a first-pass decoder that quickly emits words, and a second-pass decoder that…

Recommendation model performance is intrinsically tied to the quality, volume, and relevance of their training data. To address common challenges like data sparsity and cold start, recent researchs have leveraged data from multiple…