Frédéric Béchet

Predicting Links on Wikipedia with Anchor Text Information

Wikipedia, the largest open-collaborative online encyclopedia, is a corpus of documents bound together by internal hyperlinks. These links form the building blocks of a large network whose...

Mining Spoken Dialogue Corpora for System Evaluation and Modelin

Part-Of-Speech Sensitivity of Routers in Mixture of Experts Models

Factual Knowledge Assessment of Language Models Using Distractors

Tagging with Hidden Markov Models Using Ambiguous Tags

WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models

Joint Syntactic and Semantic Analysis with a Multitask Deep Learning Framework for Spoken Language Understanding

Applying multiview learning algorithms to human-human conversation classification

A language model combining n-grams and stochastic finite state automata

Large Span statistical language models: application to homophone disambiguation for large vocabulary speech recognition in French

Conceptual decoding for spoken dialog systems

PERCOLI: A Person Identification System for the 2013 REPERE Challenge

Automatic assignment of part-of-speech to out-of-vocabulary words for text-to-speech processing

Multi-channel sentence classification for spoken dialogue language modeling

Person name recognition and linking from overlay text in TV broadcast shows

Conceptual decoding from word lattices: application to the spoken dialogue corpus MEDIA

Evaluating the pronunciation of proper names by four French grapheme-to-phoneme converters

Integrating MAP and linear transformation for language model adaptation