Search Results for author: Kenji Sagae

Found 19 papers, 5 papers with code

Towards Understanding What Code Language Models Learned

no code implementations20 Jun 2023 Toufique Ahmed, Dian Yu, Chengxuan Huang, Cathy Wang, Prem Devanbu, Kenji Sagae

To understand the extent to which language models can learn some form of meaning, we investigate their ability to capture semantics of code beyond superficial frequency and co-occurrence.

Automatically Exposing Problems with Neural Dialog Models

1 code implementation EMNLP 2021 Dian Yu, Kenji Sagae

Neural dialog models are known to suffer from problems such as generating unsafe and inconsistent responses.

reinforcement-learning Reinforcement Learning (RL)

Attribute Alignment: Controlling Text Generation from Pre-trained Language Models

1 code implementation Findings (EMNLP) 2021 Dian Yu, Zhou Yu, Kenji Sagae

Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities.

Attribute Language Modelling +1

Tracking the Evolution of Written Language Competence in L2 Spanish Learners

no code implementations WS 2020 Alessio Miaschi, Sam Davidson, Dominique Brunato, Felice Dell{'}Orletta, Kenji Sagae, Claudia Helena Sanchez-Gutierrez, Giulia Venturi

In this paper we present an NLP-based approach for tracking the evolution of written language competence in L2 Spanish learners using a wide range of linguistic features automatically extracted from students{'} written productions.

Studying the Difference Between Natural and Programming Language Corpora

no code implementations6 Jun 2018 Casey Casalnuovo, Kenji Sagae, Prem Devanbu

Code corpora, as observed in large software systems, are now known to be far more repetitive and predictable than natural language corpora.

Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States

1 code implementation TACL 2016 Ashish Vaswani, Kenji Sagae

Transition-based approaches based on local classification are attractive for dependency parsing due to their simplicity and speed, despite producing results slightly below the state-of-the-art.

Feature Engineering General Classification +3

Fast Rhetorical Structure Theory Discourse Parsing

4 code implementations10 May 2015 Michael Heilman, Kenji Sagae

In recent years, There has been a variety of research on discourse parsing, particularly RST discourse parsing.

Discourse Parsing

Practical Evaluation of Human and Synthesized Speech for Virtual Human Dialogue Systems

no code implementations LREC 2012 Kallirroi Georgila, Alan Black, Kenji Sagae, David Traum

To determine the best trade-off between performance and cost, we perform a systematic evaluation of human and synthesized voices with regard to naturalness, conversational aspect, and likability.

Speech Synthesis

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