neubig

prompt2model

prompt2model - Generate Deployable Models from Natural Language Instructions

sempre

Semantic Parser with Execution

zeno-build

Build, evaluate, understand, and fix LLM-based apps

ExplainaBoard

Interpretable Evaluation for AI Systems

datasets-CMU_Wilderness

CMU Wilderness Multilingual Speech Dataset

knn-transformers

PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT

xnmt

eXtensible Neural Machine Translation

pseudogen

A tool to automatically generate pseudo-code from source code.

LPAQA

Language model Prompt And Query Archive

visualwebarena

VisualWebArena is a benchmark for multimodal agents.

code-bert-score

CodeBERTScore: an automatic metric for code generation, based on BERTScore

echo-embeddings

MT-ComparEval

Tool for comparison and evaluation of machine translation.

coach

util-scripts

Various utility scripts useful for natural language processing, machine translation, etc.

cicada

cicada: a hypergraph-based toolkit for statistical machine translation based on {tree, string}-to-{tree, string} models

few-shot-clustering

ckylark

A latent-annotated probabilistic context-free grammar (LAPCFG) parser.

travatar

This is a repository for the Travatar forest-to-string translation decoder

text-generation-inference

An Apache 2.0 fork of HuggingFace's Large Language Model Text Generation Inference

DALM

An Efficient Language Model Using Double-Array Structures

trove

[preprint] TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks

lazy

A lazy decoder for syntax

LORG-Release

LORG is an accurate natural language parser developed in the NCLT at Dublin City University with support from Enterprise Ireland. The parser employs state-of-the-art statistical techniques and a flexible architecture to facilitate adaptation to new languages and new domains.

CommunityLM

[COLING 2022]: CommunityLM: Probing Partisan Worldviews from Language Models

egret

A fork of the Egret parser that fixes a few bugs

ganglist

CUI frontend of Ganglia

AlignmentTool

A tool for making alignments over bilingual text.

cdec

Decoder, aligner, and model optimizer for statistical machine translation and other structured prediction models based on (mostly) context-free formalisms

ducttape

A workflow management system for researchers who heart Unix.