Related papers: Building an Efficient and Effective Retrieval-base…

Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is time to re-evaluate it.…

On a wide range of natural language processing and information retrieval tasks, transformer-based models, particularly pre-trained language models like BERT, have demonstrated tremendous effectiveness. Due to the quadratic complexity of the…

A BERT-based Neural Ranking Model (NRM) can be either a crossencoder or a bi-encoder. Between the two, bi-encoder is highly efficient because all the documents can be pre-processed before the actual query time. In this work, we show two…

We present an analysis of large-scale pretrained deep learning models used for cross-modal (text-to-audio) retrieval. We use embeddings extracted by these models in a metric learning framework to connect matching pairs of audio and text.…

Existing multilingual embedding models often encounter challenges in cross-lingual scenarios due to imbalanced linguistic resources and less consideration of cross-lingual alignment during training. Although standardized contrastive…

Long-form video understanding presents significant challenges for interactive retrieval systems, as conventional methods struggle to process extensive video content efficiently. Existing approaches often rely on single models, inefficient…

Modern search systems rely on a fast first stage retriever to fetch relevant items from a massive catalog of items. Deployed search systems often use user engagement signals to supervise bi-encoder retriever training at scale, because these…

We present a novel end-to-end language model for joint retrieval and classification, unifying the strengths of bi- and cross- encoders into a single language model via a coarse-to-fine memory matching search procedure for learning and…

Deep pre-trained language models (e,g. BERT) are effective at large-scale text retrieval task. Existing text retrieval systems with state-of-the-art performance usually adopt a retrieve-then-reranking architecture due to the high…

We present a multi-task learning framework to enable the training of one universal incremental dialogue processing model with four tasks of disfluency detection, language modelling, part-of-speech tagging, and utterance segmentation in a…

To better support information retrieval tasks such as web search and open-domain question answering, growing effort is made to develop retrieval-oriented language models, e.g., RetroMAE and many others. Most of the existing works focus on…

Recent research has shown that mixed-initiative conversational search, based on the interaction between users and computers to clarify and improve a query, provides enormous advantages. Nonetheless, incorporating additional information…

In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, there is no comparably principled basis to justify trust in the content of the text…

Open-retrieval question answering systems are generally trained and tested on large datasets in well-established domains. However, low-resource settings such as new and emerging domains would especially benefit from reliable question…

With the increasing research interest in dialogue response generation, there is an emerging branch formulating this task as selecting next sentences, where given the partial dialogue contexts, the goal is to determine the most probable next…

Large language models (LLMs) have demonstrated their ability to learn in-context, allowing them to perform various tasks based on a few input-output examples. However, the effectiveness of in-context learning is heavily reliant on the…

This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the…

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

Even though BERT achieves successful performance improvements in various supervised learning tasks, applying BERT for unsupervised tasks still holds a limitation that it requires repetitive inference for computing contextual language…

As an effective tool for eliciting the power of Large Language Models (LLMs), prompting has recently demonstrated unprecedented abilities across a variety of complex tasks. To further improve the performance, prompt ensemble has attracted…