Related papers: Building a Test Collection for Speech-Driven Web R…
Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet. However, existing models focus only on optimizing…
BERT-based re-ranking and dense retrieval (DR) systems have been shown to improve search effectiveness for spoken content retrieval (SCR). However, both methods can still show a reduction in effectiveness when using ASR transcripts in…
Search typically relies on keyword queries, but these are often semantically ambiguous. We propose to overcome this by offering users natural language questions, based on their keyword queries, to disambiguate their intent. This…
Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…
Spontaneous conversations in real-world settings such as those found in child-centered recordings have been shown to be amongst the most challenging audio files to process. Nevertheless, building speech processing models handling such a…
Conversational search is one of the ultimate goals of information retrieval. Recent research approaches conversational search by simplified settings of response ranking and conversational question answering, where an answer is either…
We describe Microsoft's conversational speech recognition system, in which we combine recent developments in neural-network-based acoustic and language modeling to advance the state of the art on the Switchboard recognition task. Inspired…
Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…
Despite the effectiveness of sequence-to-sequence framework on the task of Short-Text Conversation (STC), the issue of under-exploitation of training data (i.e., the supervision signals from query text is \textit{ignored}) still remains…
This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for…
Retrieval augmented language models have recently become the standard for knowledge intensive tasks. Rather than relying purely on latent semantics within the parameters of large neural models, these methods enlist a semi-parametric memory…
Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate…
Developing an efficient retriever to retrieve knowledge from a large-scale knowledge base (KB) is critical for task-oriented dialogue systems to effectively handle localized and specialized tasks. However, widely used generative models such…
For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…
Contextual retrieval is a critical technique for today's search engines in terms of facilitating queries and returning relevant information. This paper reports on the development and evaluation of a system designed to tackle some of the…
Recent advances in spoken language technologies and the introduction of many customer facing products, have given rise to a wide customer reliance on smart personal assistants for many of their daily tasks. In this paper, we present a…
A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…
This paper describes the approach of the THUIR team at the WSDM Cup 2023 Pre-training for Web Search task. This task requires the participant to rank the relevant documents for each query. We propose a new data pre-processing method and…
Task-oriented conversational modeling with unstructured knowledge access, as track 1 of the 9th Dialogue System Technology Challenges (DSTC 9), requests to build a system to generate response given dialogue history and knowledge access.…
We present a system, Spoke, for creating and searching internal knowledge base (KB) articles for organizations. Spoke is available as a SaaS (Software-as-a-Service) product deployed across hundreds of organizations with a diverse set of…