Search Results for author:
Found 24 papers, 15 papers with code
Discourse-Driven Integrated Dialogue Development Environment for Open-Domain Dialogue Systems
Development environments for spoken dialogue systems are popular today because they enable rapid creation of the dialogue systems in times when usage of the voice AI Assistants is constantly growing.
Uncertainty Estimation of Transformer Predictions for Misclassification Detection
Uncertainty estimation (UE) of model predictions is a crucial step for a variety of tasks such as active learning, misclassification detection, adversarial attack detection, out-of-distribution detection, etc.
Attention Understands Semantic Relations
Today, natural language processing heavily relies on pre-trained large language models.
In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss
This paper addresses the challenge of processing long documents using generative transformer models.
Uncertainty Guided Global Memory Improves Multi-Hop Question Answering
Conversely, the second group relies on the attention mechanism of the long input encoding model to facilitate multi-hop reasoning.
Better Together: Enhancing Generative Knowledge Graph Completion with Language Models and Neighborhood Information
In this study, we propose to include node neighborhoods as additional information to improve KGC methods based on language models.
Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification
This article investigates the knowledge transfer from the RuQTopics dataset.
Active Learning for Abstractive Text Summarization
Active Learning (AL) is a technique developed to reduce the amount of annotation required to achieve a certain level of machine learning model performance.
Collecting Interactive Multi-modal Datasets for Grounded Language Understanding
Human intelligence can remarkably adapt quickly to new tasks and environments.
Learning to Solve Voxel Building Embodied Tasks from Pixels and Natural Language Instructions
The adoption of pre-trained language models to generate action plans for embodied agents is a promising research strategy.
Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes
This requires to store prohibitively large intermediate data if a sequence consists of thousands or even millions elements, and as a result, makes learning of very long-term dependencies infeasible.
IGLU 2022: Interactive Grounded Language Understanding in a Collaborative Environment at NeurIPS 2022
Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions.
Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021
The primary goal of the competition is to approach the problem of how to build interactive agents that learn to solve a task while provided with grounded natural language instructions in a collaborative environment.
Knowledge Distillation of Russian Language Models with Reduction of Vocabulary
We propose two simple yet effective alignment techniques to make knowledge distillation to the students with reduced vocabulary.
NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions.
Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions
Enabling open-domain dialogue systems to ask clarifying questions when appropriate is an important direction for improving the quality of the system response.
Multi-Stream Transformers
Transformer-based encoder-decoder models produce a fused token-wise representation after every encoder layer.
Short Text Clustering with Transformers
Recent techniques for the task of short text clustering often rely on word embeddings as a transfer learning component.
Ranked #2 on
Short Text Clustering
on Stackoverflow
Memory Representation in Transformer
Adding trainable memory to selectively store local as well as global representations of a sequence is a promising direction to improve the Transformer model.
ConvAI3: Generating Clarifying Questions for Open-Domain Dialogue Systems (ClariQ)
The main aim of the conversational systems is to return an appropriate answer in response to the user requests.
Goal-Oriented Multi-Task BERT-Based Dialogue State Tracker
The organizers introduced the Schema-Guided Dialogue (SGD) dataset with multi-domain conversations and released a zero-shot dialogue state tracking model.
Loss Landscape Sightseeing with Multi-Point Optimization
We present multi-point optimization: an optimization technique that allows to train several models simultaneously without the need to keep the parameters of each one individually.
The Second Conversational Intelligence Challenge (ConvAI2)
We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots.
DeepPavlov: Open-Source Library for Dialogue Systems
It supports modular as well as end-to-end approaches to implementation of conversational agents.
