Related papers: Constrained Decoding for Neural NLG from Compositi…

This thesis advances semantic representation learning to render language representations or models more semantically and geometrically interpretable, and to enable localised, quasi-symbolic, compositional control through deliberate shaping…

Recent progress on parse tree encoder for sentence representation learning is notable. However, these works mainly encode tree structures recursively, which is not conducive to parallelization. On the other hand, these works rarely take…

Analysis methods which enable us to better understand the representations and functioning of neural models of language are increasingly needed as deep learning becomes the dominant approach in NLP. Here we present two methods based on…

Processing long contexts is increasingly important for Large Language Models (LLMs) in tasks like multi-turn dialogues, code generation, and document summarization. This paper addresses the challenges of achieving high long-context…

The goal of text generation is to make machines express in human language. It is one of the most important yet challenging tasks in natural language processing (NLP). Since 2014, various neural encoder-decoder models pioneered by Seq2Seq…

Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to…

Forecasting Electroncephalography (EEG) signals during cognitive events remains a fundamental challenge in neuroscience and Brain-Computer Interfaces (BCIs), as existing methods struggle to capture both the stochastic nature of neural…

Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the…

The use of knowledge graphs (KGs) enhances the accuracy and comprehensiveness of the responses provided by a conversational agent. While generating answers during conversations consists in generating text from these KGs, it is still…

Neural generation methods for task-oriented dialogue typically generate from a meaning representation that is populated using a database of domain information, such as a table of data describing a restaurant. While earlier work focused…

In Natural Language Processing (NLP), we often need to extract information from tree topology. Sentence structure can be represented via a dependency tree or a constituency tree structure. For this reason, a variant of LSTMs, named…

Generating semantic layout from scene graph is a crucial intermediate task connecting text to image. We present a conceptually simple, flexible and general framework using sequence to sequence (seq-to-seq) learning for this task. The…

We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts, and we use it to directly compare…

Learning distributed sentence representations remains an interesting problem in the field of Natural Language Processing (NLP). We want to learn a model that approximates the conditional latent space over the representations of a logical…

Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is particularly challenging to generate both human-like and…

Decoding visual experience from brain signals offers exciting possibilities for neuroscience and interpretable AI. While EEG is accessible and temporally precise, its limitations in spatial detail hinder image reconstruction. Our model…

A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across…

The meaning of a sentence is a function of the relations that hold between its words. We instantiate this relational view of semantics in a series of neural models based on variants of relation networks (RNs) which represent a set of…

Many neural network models nowadays have achieved promising performances in Chit-chat settings. The majority of them rely on an encoder for understanding the post and a decoder for generating the response. Without given assigned semantics,…

Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedness which is not…