Related papers: CIKMar: A Dual-Encoder Approach to Prompt-Based Re…

Intelligent personal assistant systems with either text-based or voice-based conversational interfaces are becoming increasingly popular around the world. Retrieval-based conversation models have the advantages of returning fluent and…

In this work, we address the challenge of multilingual category relevance judgment in e-commerce search, where traditional ensemble-based systems improve accuracy but at the cost of heavy training, inference, and maintenance complexity. To…

For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence…

With the rapid advancement of multimodal information retrieval, increasingly complex retrieval tasks have emerged. Existing methods predominately rely on task-specific fine-tuning of vision-language models, often those trained with…

Large language models (LLMs) are trained on text-only data that go far beyond the languages with paired speech and text data. At the same time, Dual Encoder (DE) based retrieval systems project queries and documents into the same embedding…

Multi-modal retrieval-augmented Question Answering (MRAQA), integrating text and images, has gained significant attention in information retrieval (IR) and natural language processing (NLP). Traditional ranking methods rely on small…

This paper investigates how to effectively incorporate a pre-trained masked language model (MLM), such as BERT, into an encoder-decoder (EncDec) model for grammatical error correction (GEC). The answer to this question is not as…

As the use of interactive machines grow, the task of Emotion Recognition in Conversation (ERC) became more important. If the machine-generated sentences reflect emotion, more human-like sympathetic conversations are possible. Since emotion…

We present BgGPT-Gemma-2-27B-Instruct and BgGPT-Gemma-2-9B-Instruct: continually pretrained and fine-tuned versions of Google's Gemma-2 models, specifically optimized for Bulgarian language understanding and generation. Leveraging Gemma-2's…

We present BERT-CTC-Transducer (BECTRA), a novel end-to-end automatic speech recognition (E2E-ASR) model formulated by the transducer with a BERT-enhanced encoder. Integrating a large-scale pre-trained language model (LM) into E2E-ASR has…

Text ranking is a critical task in information retrieval. Recent advances in pre-trained language models (PLMs), especially large language models (LLMs), present new opportunities for applying them to text ranking. While supervised…

Using large language models (LLMs) to predict relevance judgments has shown promising results. Most studies treat this task as a distinct research line, e.g., focusing on prompt design for predicting relevance labels given a query and…

We present CID-GraphRAG (Conversational Intent-Driven Graph Retrieval-Augmented Generation), a novel framework that addresses the limitations of existing dialogue systems in maintaining both contextual coherence and goal-oriented…

Current speech enhancement (SE) research has largely neglected channel attention and spatial attention, and encoder-decoder architecture-based networks have not adequately considered how to provide efficient inputs to the intermediate…

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…

Interactive search can provide a better experience by incorporating interaction feedback from the users. This can significantly improve search accuracy as it helps avoid irrelevant information and captures the users' search intents.…

Large Language Models (LLMs) have shown impressive capabilities in complex reasoning tasks. However, current approaches employ uniform language density for both intermediate reasoning and final answers, leading to computational…

We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a…

This study explores the application of Large Language Models (LLMs), specifically GPT-4, in the analysis of classroom dialogue, a crucial research task for both teaching diagnosis and quality improvement. Recognizing the knowledge-intensive…

We propose a neural language modeling system based on low-rank adaptation (LoRA) for speech recognition output rescoring. Although pretrained language models (LMs) like BERT have shown superior performance in second-pass rescoring, the high…