41 citations · 96 across the 14 of their papers we have counts for
15 papers
Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM
Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal +2
Contrastive decoding (CD) (Li et al., 2023) improves the next-token distribution of a large expert language model (LM) using a small amateur LM. Although CD is applied to various L…
Grounded and Well-rounded: A Methodological Approach to the Study of Cross-modal and Cross-lingual Grounding
Timothee Mickus, Elaine Zosa, Denis Paperno
Grounding has been argued to be a crucial component towards the development of more complete and truly semantically competent artificial intelligence systems. Literature has divide…
Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations
Aleksey Tikhonov, Lisa Bylinina, Denis Paperno
Multimodal embeddings aim to enrich the semantic information in neural representations of language compared to text-only models. While different embeddings exhibit different applic…
Towards leveraging latent knowledge and Dialogue context for real-world conversational question answering
Shaomu Tan, Denis Paperno
In many real-world scenarios, the absence of external knowledge source like Wikipedia restricts question answering systems to rely on latent internal knowledge in limited dialogue…
Generating image captions with external encyclopedic knowledge
Sofia Nikiforova, Tejaswini Deoskar, Denis Paperno +1
Accurately reporting what objects are depicted in an image is largely a solved problem in automatic caption generation. The next big challenge on the way to truly humanlike caption…
How to Dissect a Muppet: The Structure of Transformer Embedding Spaces
Timothee Mickus, Denis Paperno, Mathieu Constant
Pretrained embeddings based on the Transformer architecture have taken the NLP community by storm. We show that they can mathematically be reframed as a sum of vector factors and s…
Semeval-2022 Task 1: CODWOE -- Comparing Dictionaries and Word Embeddings
Timothee Mickus, Kees van Deemter, Mathieu Constant +1
Word embeddings have advanced the state of the art in NLP across numerous tasks. Understanding the contents of dense neural representations is of utmost interest to the computation…
A Game Interface to Study Semantic Grounding in Text-Based Models
Timothee Mickus, Mathieu Constant, Denis Paperno
Can language models learn grounded representations from text distribution alone? This question is both central and recurrent in natural language processing; authors generally agree…
What Meaning-Form Correlation Has to Compose With
Timothee Mickus, Timothée Bernard, Denis Paperno
Compositionality is a widely discussed property of natural languages, although its exact definition has been elusive. We focus on the proposal that compositionality can be assessed…
Mark my Word: A Sequence-to-Sequence Approach to Definition Modeling
Timothee Mickus, Denis Paperno, Mathieu Constant
Defining words in a textual context is a useful task both for practical purposes and for gaining insight into distributed word representations. Building on the distributional hypot…
What do you mean, BERT? Assessing BERT as a Distributional Semantics Model
Timothee Mickus, Denis Paperno, Mathieu Constant +1
Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models. In th…
On learning an interpreted language with recurrent models
Denis Paperno
Can recurrent neural nets, inspired by human sequential data processing, learn to understand language? We construct simplified datasets reflecting core properties of natural langua…
RUSSE: The First Workshop on Russian Semantic Similarity
Alexander Panchenko, Natalia Loukachevitch, Dmitry Ustalov +3
The paper gives an overview of the Russian Semantic Similarity Evaluation (RUSSE) shared task held in conjunction with the Dialogue 2015 conference. There exist a lot of comparativ…
Human and Machine Judgements for Russian Semantic Relatedness
Alexander Panchenko, Dmitry Ustalov, Nikolay Arefyev +4
Semantic relatedness of terms represents similarity of meaning by a numerical score. On the one hand, humans easily make judgments about semantic relatedness. On the other hand, th…
The LAMBADA dataset: Word prediction requiring a broad discourse context
Denis Paperno, Germán Kruszewski, Angeliki Lazaridou +6
We introduce LAMBADA, a dataset to evaluate the capabilities of computational models for text understanding by means of a word prediction task. LAMBADA is a collection of narrative…