Related papers: Saying Hello World with GROOVE - A Solution to the…
The HLTCOE team applied PLAID, an mT5 reranker, GPT-4 reranker, score fusion, and document translation to the TREC 2024 NeuCLIR track. For PLAID we included a variety of models and training techniques -- Translate Distill (TD), Generate…
This paper explores the instruction fine-tuning technique for speech-to-semantic tasks by introducing a unified end-to-end (E2E) framework that generates target text conditioned on a task-related prompt for audio data. We pre-train the…
Deployed language models decay over time due to shifting inputs, changing user needs, or emergent world-knowledge gaps. When such problems are identified, we want to make targeted edits while avoiding expensive retraining. However, current…
We introduce a new framework that leverages machine learning models known as generative models to solve optimization problems. Our Generator-Enhanced Optimization (GEO) strategy is flexible to adopt any generative model, from quantum to…
This paper presents a solution for the Flow Graphs case of the Transformation Tool Contest 2013, using the Eclectic model transformation tool. The solution makes use of several languages of Eclectic, showing how it is possible to combine…
GeoGebra is an open source mathematics education software tool being used in thousands of schools worldwide. Since version 4.2 (December 2012) it supports symbolic computation of locus equations as a result of joint effort of mathematicians…
We investigate the problem of learning XML queries, path queries and tree pattern queries, from examples given by the user. A learning algorithm takes on the input a set of XML documents with nodes annotated by the user and returns a query…
Many language generation models are now available for a wide range of generation tasks, including machine translation and summarization. Combining such diverse models may lead to further progress, but ensembling generation models is…
The authors' "metatools" are a collection of tools for generic programming. This includes generating Java sources from mathematically well-founded specifications, as well as the creation of strictly typed document object models for XML…
Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield black-box models that are difficult to interpret and debug. In this work, we introduce GRACE (Generating Rewards As…
In this paper we describe our experiences with a tool for the development and testing of natural language grammars called GTU (German: Grammatik-Testumgebumg; grammar test environment). GTU supports four grammar formalisms under a…
The ubiquity of complex machine learning has raised the importance of model-agnostic explanation algorithms. These methods create artificial instances by slightly perturbing real instances, capturing shifts in model decisions. However, such…
The utility of collocating robots largely depends on the easy and intuitive interaction mechanism with the human. If a robot accepts task instruction in natural language, first, it has to understand the user's intention by decoding the…
Large language models exhibit complementary reasoning errors: on the same instance, one model may succeed with a particular decomposition while another fails. We propose Collaborative Reasoning (CORE), a training-time collaboration…
This report is meant to be used as auxiliary material for the guided grammar convergence technique proposed earlier as problem-specific improvement in the topic of convergence of grammars. It contains a narrated MegaL megamodel, as well as…
Counterfactual explanations, and their associated algorithmic recourse, are typically leveraged to understand, explain, and potentially alter a prediction coming from a black-box classifier. In this paper, we propose to extend the use of…
Large Language Models have revolutionized natural language processing, achieving unprecedented success across a vast range of tasks. However, their practical application in long-context scenarios is severely hampered by the formidable…
Video annotation and analysis is an important activity for teaching with and about audiovisual media artifacts because it helps students to learn how to identify textual and formal connections in media products. But school teachers lack…
Counterfactual examples are an appealing class of post-hoc explanations for machine learning models. Given input $x$ of class $y_1$, its counterfactual is a contrastive example $x^\prime$ of another class $y_0$. Current approaches primarily…
This report documents, describes, and evaluates new 2024 English GloVe (Global Vectors for Word Representation) models. While the original GloVe models built in 2014 have been widely used and found useful, languages and the world continue…