Research of methods for injecting syntactic knowledge through linear types to the neural language modeling scheme

Open clone of OpenAI's unreleased WebText dataset scraper. This version uses pushshift.io files instead of the API for speed.

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

A library for building hierarchical text representation and corresponding downstream applications.

【2023年版】BERTによるテキスト分類

This repo contains a set of neural transducer, e.g. sequence-to-sequence model, focusing on character-level tasks.

Code for Pushdown Layers from our EMNLP 2023 paper

source code for {D}ocument-level {R}elation {E}xtraction with {E}vidence-guided {A}ttention {M}echanism

Data and software for building the ACL Anthology.

Lbl2Vec learns jointly embedded label, document and word vectors to retrieve documents with predefined topics from an unlabeled document corpus.

Learning from Neighbors: Unsupervised Text Classification

RAting VErbal Novelty

Session module for LINE Messaging API

A range of tools related to one-endpoint crossing graphs - parsing, format conversion, and evaluation

AI chat for every model.

Transformer-based language modeling with symbolic linguistic structure representations. Published at NAACL 2022.

English HPSG parser

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Source code for Twitter's Recommendation Algorithm

A sample of using docker to deploy a Python based app

Inference code for Llama models

azooKey: A Japanese Keyboard iOS Application Fully Developed in Swift

Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale, TACL (2022)

Parsing Data Generation for WSJ

Top2Vec learns jointly embedded topic, document and word vectors.

Clustering sentence embeddings to extract message intent