B. Chen

Publications
Influence

What do you learn from context? Probing for sentence structure in contextualized word representations

Ian Tenney, Patrick Xia, +8 authors Ellie Pavlick
Computer Science
ICLR
15 May 2019

We probe word-level contextual representations from four recent models and investigate how they encode sentence structure across a range of syntactic, semantic, local, and long-range phenomena. Expand

Generating phonetic cognates to handle named entities in English-Chinese cross-language spoken document retrieval

H. Meng, Wai-Kit Lo, B. Chen, K. Tang
Computer Science
IEEE Workshop on Automatic Speech Recognition and…
2001

We have developed a technique for automatic transliteration of named entities for English-Chinese cross-language spoken document retrieval (CL-SDR). Expand

Word Topic Models for Spoken Document Retrieval and Transcription

B. Chen
Computer Science
TALIP
1 March 2009

We propose a word topic model (WTM) to explore the co-occurrence relationship between words, as well as the long-span latent topical information, for language modeling in spoken document retrieval and transcription. Expand

Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling

Alex Wang, J. Hula, +13 authors Samuel R. Bowman
Computer Science
ACL
28 December 2018

We conduct the first large-scale systematic study of candidate pretraining tasks, comparing 19 different tasks both as alternatives and complements to language modeling. Expand

MATBN: A Mandarin Chinese Broadcast News Corpus

H. Wang, B. Chen, Jen-wei Kuo, Shih-Sian Cheng
Psychology, Computer Science
Int. J. Comput. Linguistics Chin. Lang. Process.
1 July 2005

The MATBN Mandarin Chinese broadcast news corpus contains 198 hours of broadcast news from the Public Television Service Foundation (Taiwan) with corresponding transcripts. Expand

Latent topic modeling of word vicinity information for speech recognition

Kuan-Yu Chen, Hsuan-Sheng Chiu, B. Chen
Computer Science
IEEE International Conference on Acoustics…
14 March 2010

A new topic language model, named word vicinity model (WVM), is proposed to explore the co-occurrence relationship between words, as well as the long-span latent topical information for language model adaptation. Expand

A discriminative HMM/N-gram-based retrieval approach for mandarin spoken documents

B. Chen, H. Wang, L. Lee
Computer Science
TALIP
1 June 2004

In recent years, statistical modeling approaches have steadily gained in popularity in the field of information retrieval. Expand

Improved spoken document retrieval by exploring extra acoustic and linguistic cues

B. Chen, H. Wang, L. Lee
Computer Science
INTERSPEECH
2001

In this paper, we explored the use of various extra information to improve the performance of spoken document retrieval (SDR). Expand

Extractive spoken document summarization for information retrieval

B. Chen, Y. Chen
Computer Science
Pattern Recognit. Lett.
1 March 2008

The purpose of extractive summarization is to automatically select a number of indicative sentences, passages, or paragraphs from the original document and then sequence them to form a concise summary. Expand

Mandarin-English Information (MEI): investigating translingual speech retrieval

H. Meng, B. Chen, +7 authors J. Wang
Computer Science
Comput. Speech Lang.
1 April 2004

This paper describes the Mandarin–English Information (MEI) project, where we investigated the problem of cross-language spoken document retrieval (CL-SDR), and developed one of the first English–Chinese CL- SDR systems. Expand

Recommended Authors