MIPA: Mutual Information Based Paraphrase Acquisition via Bilingual Pivoting

1 code implementation • IJCNLP 2017 • Tomoyuki Kajiwara, Mamoru Komachi, Daichi Mochihashi

We present a pointwise mutual information (PMI)-based approach to formalize paraphrasability and propose a variant of PMI, called MIPA, for the paraphrase acquisition.

Learning Word Embeddings Semantic Textual Similarity +1

Nonparametric Bayesian Semi-supervised Word Segmentation

no code implementations • TACL 2017 • Ryo Fujii, Ryo Domoto, Daichi Mochihashi

This paper presents a novel hybrid generative/discriminative model of word segmentation based on nonparametric Bayesian methods.

Language Modelling Machine Translation +2

Suggesting Sentences for ESL using Kernel Embeddings

no code implementations • WS 2017 • Kent Shioda, Mamoru Komachi, Rue Ikeya, Daichi Mochihashi

This method implicitly models latent intent of query and sentences, and alleviates the problem of noisy alignment.

Retrieval Semantic Textual Similarity +1

Human-like Natural Language Generation Using Monte Carlo Tree Search

no code implementations • WS 2016 • Kaori Kumagai, Ichiro Kobayashi, Daichi Mochihashi, Hideki Asoh, Tomoaki Nakamura, Takayuki Nagai

Language Modelling Text Generation

Inducing Word and Part-of-Speech with Pitman-Yor Hidden Semi-Markov Models

no code implementations • IJCNLP 2015 • Kei Uchiumi, Hiroshi Tsukahara, Daichi Mochihashi

Chinese Word Segmentation Language Modelling +2

Learning Word Meanings and Grammar for Describing Everyday Activities in Smart Environments

no code implementations • EMNLP 2015 • Muhammad Attamimi, Yuji Ando, Tomoaki Nakamura, Takayuki Nagai, Daichi Mochihashi, Ichiro Kobayashi, Hideki Asoh

Language Modelling

Improvements to the Bayesian Topic N-Gram Models

no code implementations • EMNLP 2013 • Hiroshi Noji, Daichi Mochihashi, Yusuke Miyao

Language Modelling

Predicting Word Fixations in Text with a CRF Model for Capturing General Reading Strategies among Readers

no code implementations • WS 2012 • Tadayoshi Hara, Daichi Mochihashi, Yoshinobu Kano, Akiko Aizawa

How LSTM Encodes Syntax: Exploring Context Vectors and Semi-Quantization on Natural Text

no code implementations • COLING 2020 • Chihiro Shibata, Kei Uchiumi, Daichi Mochihashi

For some dimensions in the context vector, we show that their activations are highly correlated with the depth of phrase structures, such as VP and NP.

Language Modelling Quantization