Search Results for author: Simon Corston-Oliver

Found 7 papers, 0 papers with code

An Effective, Performant Named Entity Recognition System for Noisy Business Telephone Conversation Transcripts

no code implementations COLING (WNUT) 2022 Xue-Yong Fu, Cheng Chen, Md Tahmid Rahman Laskar, Shashi Bhushan TN, Simon Corston-Oliver

We present a simple yet effective method to train a named entity recognition (NER) model that operates on business telephone conversation transcripts that contain noise due to the nature of spoken conversation and artifacts of automatic speech recognition.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Extracting Similar Questions From Naturally-occurring Business Conversations

no code implementations3 Jun 2022 Xiliang Zhu, David Rossouw, Shayna Gardiner, Simon Corston-Oliver

Pre-trained contextualized embedding models such as BERT are a standard building block in many natural language processing systems.

Sentence

Developing a Production System for Purpose of Call Detection in Business Phone Conversations

no code implementations NAACL (ACL) 2022 Elena Khasanova, Pooja Hiranandani, Shayna Gardiner, Cheng Chen, Xue-Yong Fu, Simon Corston-Oliver

In this paper we describe our implementation of a commercial system to detect Purpose of Call statements in English business call transcripts in real time.

Improving Punctuation Restoration for Speech Transcripts via External Data

no code implementations WNUT (ACL) 2021 Xue-Yong Fu, Cheng Chen, Md Tahmid Rahman Laskar, Shashi Bhushan TN, Simon Corston-Oliver

To leverage the available written text datasets, we introduce a data sampling technique based on an n-gram language model to sample more training data that are similar to our in-domain data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Cannot find the paper you are looking for? You can Submit a new open access paper.