no code implementations • 21 Mar 2024 • Maxime Peyrard, Martin Josifoski, Robert West
We refer to these orchestrated interactions among semantic processors, optimizing and searching in semantic space, as semantic decoding algorithms.
no code implementations • 16 Feb 2024 • Mohammad Hossein Amani, Nicolas Mario Baldwin, Amin Mansouri, Martin Josifoski, Maxime Peyrard, Robert West
Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel data is scarce.
1 code implementation • 9 Jan 2024 • Tim R. Davidson, Veniamin Veselovsky, Martin Josifoski, Maxime Peyrard, Antoine Bosselut, Michal Kosinski, Robert West
We introduce an approach to evaluate language model (LM) agency using negotiation games.
1 code implementation • 4 Dec 2023 • Giovanni Monea, Maxime Peyrard, Martin Josifoski, Vishrav Chaudhary, Jason Eisner, Emre Kiciman, Hamid Palangi, Barun Patra, Robert West
Yet the mechanisms underlying this contextual grounding remain unknown, especially in situations where contextual information contradicts factual knowledge stored in the parameters, which LLMs also excel at recalling.
2 code implementations • 11 Aug 2023 • Marija Šakota, Maxime Peyrard, Robert West
For a wide variety of tasks, inputs can be phrased as natural language prompts for an LM, from whose output the solution can then be extracted.
2 code implementations • 2 Aug 2023 • Martin Josifoski, Lars Klein, Maxime Peyrard, Nicolas Baldwin, Yifei Li, Saibo Geng, Julian Paul Schnitzler, Yuxing Yao, Jiheng Wei, Debjit Paul, Robert West
To support rapid and rigorous research, we introduce the aiFlows library embodying Flows.
2 code implementations • 23 May 2023 • Saibo Geng, Martin Josifoski, Maxime Peyrard, Robert West
In this work, we demonstrate that formal grammars can describe the output space for a much wider range of tasks and argue that GCD can serve as a unified framework for structured NLP tasks in general.
1 code implementation • 4 Apr 2023 • Debjit Paul, Mete Ismayilzada, Maxime Peyrard, Beatriz Borges, Antoine Bosselut, Robert West, Boi Faltings
Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e. g., chain-of-thought prompting.
1 code implementation • 7 Mar 2023 • Martin Josifoski, Marija Sakota, Maxime Peyrard, Robert West
This work shows that useful data can be synthetically generated even for tasks that cannot be solved directly by LLMs: for problems with structured outputs, it is possible to prompt an LLM to perform the task in the reverse direction, by generating plausible input text for a target output structure.
1 code implementation • 13 Oct 2022 • Martin Josifoski, Maxime Peyrard, Frano Rajic, Jiheng Wei, Debjit Paul, Valentin Hartmann, Barun Patra, Vishrav Chaudhary, Emre Kiciman, Boi Faltings, Robert West
Specifically, by analyzing the correlation between the likelihood and the utility of predictions across a diverse set of tasks, we provide empirical evidence supporting the proposed taxonomy and a set of principles to structure reasoning when choosing a decoding algorithm.
2 code implementations • 18 Sep 2022 • Valentin Hartmann, Léo Meynent, Maxime Peyrard, Dimitrios Dimitriadis, Shruti Tople, Robert West
We identify three sources of leakage: (1) memorizing specific information about the $\mathbb{E}[Y|X]$ (expected label given the feature values) of interest to the adversary, (2) wrong inductive bias of the model, and (3) finiteness of the training data.
no code implementations • 31 Aug 2022 • Pierre Colombo, Maxime Peyrard, Nathan Noiry, Robert West, Pablo Piantanida
Automatic evaluation metrics capable of replacing human judgments are critical to allowing fast development of new methods.
no code implementations • 6 Jul 2022 • Damien Teney, Maxime Peyrard, Ehsan Abbasnejad
Underspecification refers to the existence of multiple models that are indistinguishable in their in-domain accuracy, even though they differ in other desirable properties such as out-of-distribution (OOD) performance.
1 code implementation • 20 May 2022 • Marija Sakota, Maxime Peyrard, Robert West
Wikipedia is one of the richest knowledge sources on the Web today.
1 code implementation • 17 Jan 2022 • Justyna Czestochowska, Kristina Gligoric, Maxime Peyrard, Yann Mentha, Michal Bien, Andrea Grutter, Anita Auer, Aris Xanthos, Robert West
We find that with 30 annotations per emoji, 16 emojis (1. 2%) are completely unambiguous, whereas 55 emojis (4. 3%) are so ambiguous that their descriptions are indistinguishable from randomly chosen descriptions.
1 code implementation • NAACL 2022 • Martin Josifoski, Nicola De Cao, Maxime Peyrard, Fabio Petroni, Robert West
Structured and grounded representation of text is typically formalized by closed information extraction, the problem of extracting an exhaustive set of (subject, relation, object) triplets that are consistent with a predefined set of entities and relations from a knowledge base schema.
1 code implementation • ACL 2021 • Maxime Peyrard, Wei Zhao, Steffen Eger, Robert West
Evaluation in NLP is usually done by comparing the scores of competing systems independently averaged over a common set of test instances.
1 code implementation • 16 Oct 2021 • Maxime Peyrard, Sarvjeet Singh Ghotra, Martin Josifoski, Vidhan Agarwal, Barun Patra, Dean Carignan, Emre Kiciman, Robert West
In particular, we adapt a game-theoretic formulation of IRM (IRM-games) to language models, where the invariance emerges from a specific training schedule in which all the environments compete to optimize their own environment-specific loss by updating subsets of the model in a round-robin fashion.
1 code implementation • 19 May 2021 • Maxime Peyrard, Beatriz Borges, Kristina Gligorić, Robert West
We make progress in both respects by training and analyzing transformer-based humor recognition models on a recently introduced dataset consisting of minimal pairs of aligned sentences, one serious, the other humorous.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Maxime Peyrard, Robert West
The goal of text summarization is to compress documents to the relevant information while excluding background information already known to the receiver.
1 code implementation • 19 Aug 2020 • Kristina Gligorić, Manoel Horta Ribeiro, Martin Müller, Olesia Altunina, Maxime Peyrard, Marcel Salathé, Giovanni Colavizza, Robert West
Timely access to accurate information is crucial during the COVID-19 pandemic.
Social and Information Networks
1 code implementation • 5 May 2020 • Maxime Peyrard, Robert West
Causal discovery, the task of automatically constructing a causal model from data, is of major significance across the sciences.
1 code implementation • ACL 2020 • Wei Zhao, Goran Glavaš, Maxime Peyrard, Yang Gao, Robert West, Steffen Eger
We systematically investigate a range of metrics based on state-of-the-art cross-lingual semantic representations obtained with pretrained M-BERT and LASER.
4 code implementations • IJCNLP 2019 • Wei Zhao, Maxime Peyrard, Fei Liu, Yang Gao, Christian M. Meyer, Steffen Eger
A robust evaluation metric has a profound impact on the development of text generation systems.
1 code implementation • ACL 2019 • Maxime Peyrard
In summarization, automatic evaluation metrics are usually compared based on their ability to correlate with human judgments.
no code implementations • NAACL 2018 • Maxime Peyrard, Iryna Gurevych
Supervised summarization systems usually rely on supervision at the sentence or n-gram level provided by automatic metrics like ROUGE, which act as noisy proxies for human judgments.
1 code implementation • 4 Mar 2018 • Andreas Rücklé, Steffen Eger, Maxime Peyrard, Iryna Gurevych
Here, we generalize the concept of average word embeddings to power mean word embeddings.
1 code implementation • LREC 2018 • Avinesh P. V. S., Maxime Peyrard, Christian M. Meyer
Live blogs are an increasingly popular news format to cover breaking news and live events in online journalism.
no code implementations • ACL 2019 • Maxime Peyrard
Research on summarization has mainly been driven by empirical approaches, crafting systems to perform well on standard datasets with the notion of information Importance remaining latent.
no code implementations • WS 2017 • Maxime Peyrard, Teresa Botschen, Iryna Gurevych
The evaluation of summaries is a challenging but crucial task of the summarization field.
no code implementations • ACL 2017 • Maxime Peyrard, Judith Eckle-Kohler
We present a new supervised framework that learns to estimate automatic Pyramid scores and uses them for optimization-based extractive multi-document summarization.
1 code implementation • ACL 2017 • Maxime Peyrard, Judith Eckle-Kohler
We present a new framework for evaluating extractive summarizers, which is based on a principled representation as optimization problem.
1 code implementation • WS 2017 • Michael Bugert, Yevgeniy Puzikov, Andreas R{\"u}ckl{\'e}, Judith Eckle-Kohler, Teresa Martin, Eugenio Mart{\'\i}nez-C{\'a}mara, Daniil Sorokin, Maxime Peyrard, Iryna Gurevych
The Story Cloze test is a recent effort in providing a common test scenario for text understanding systems.
1 code implementation • COLING 2016 • Markus Zopf, Maxime Peyrard, Judith Eckle-Kohler
In a detailed analysis, we show that our new corpus is significantly different from the homogeneous corpora commonly used, and that it is heterogeneous along several dimensions.
1 code implementation • COLING 2016 • Maxime Peyrard, Judith Eckle-Kohler
Extracting summaries via integer linear programming and submodularity are popular and successful techniques in extractive multi-document summarization.