Search results

This project provides the source to reproduce the main methods of the paper "Attention-based contextual language model adaptation for speech recognition", submitted to ACL 2021. This codebase also implements additional functionality that was not explicitly described in the paper, such as experimental methods for combining multiple types of non-linguistic context together (e.g. geo-location, and datetime

We propose gender-filtered self-training (GFST) to improve gender translation accuracy on unambiguously gendered inputs. Our GFST approach uses a source monolingual corpus and an initial model to generate gender-specific pseudo-parallel corpora which are then filtered and added to the training data. We evaluate GFST on translation from English into five languages, finding that it improves gender accuracy

This paper proposes FeatGraph to accelerate GNN workloads by co-optimizing graph traversal and feature dimension computation. FeatGraph provides a flexible programming interface to express diverse GNN models by composing coarse-grained sparse templates with fine-grained user-defined functions (UDFs) on each vertex/edge. FeatGraph incorporates optimizations for graph traversal into the sparse templates and

Developing Text Normalization (TN) systems for Text-to-Speech (TTS) on new languages is hard. We propose a novel architecture to facilitate it for multiple languages while using data less than 3% of the size of the data used by the state of the art results on English. We treat TN as a sequence classification problem and propose a granular tokenization mechanism that enables the system to learn majority

Luminous is a framework for testing the performance of embodied AI (EAI) models in indoor tasks. Generally, we integrate different kind of functionalities into this repository that are related to evaluate EAI performance for indoor tasks. The Indoor Scene Synthesis module provides different methods for synthesize randomized indoor scenes that be visualized in Unity Engine. The Luminous for Alfred offers

We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification, semantic role labeling, event extraction, coreference resolution, and dialogue state tracking. Instead of tackling the problem by training task-specific discriminative

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without exploiting its full potential. In particular, previous losses do not take the intra-modality similarities into account, which leads to inefficient embeddings, as the same content

Episodic training is a core ingredient of few-shot learning to train models on tasks with limited labelled data. Despite its success, episodic training remains largely understudied, prompting us to ask the question: what is the best way to sample episodes? In this paper, we first propose a method to approximate episode sampling distributions based on their difficulty. Building on this method, we perform

DenseClus is a Python module for clustering mixed type data using UMAP and HDBSCAN. Allowing for both categorical and numerical data, DenseClus makes it possible to incorporate all features in clustering.

A lot of recent work in dialogue modeling has been on written conversations, partly because of available data sets. However, written dialogues are not sufficient to fully capture the nature of spoken conversations as well as the potential effect of speech recognition errors on practical spoken dialogue systems. This challenge track aims to provide a new benchmark on spoken task-oriented conversations. We

GuessWhat?! is a visual dialog guessing game which incorporates a Questioner agent that generates a sequence of questions, while an Oracle agent answers the respective questions about a target object in an image. Based on this dialog history between the Questioner and the Oracle, a Guesser agent makes a final guess of the target object. While previous work has focused on dialogue policy optimization and

This repository contains the ListQA datasets described in the paper - Question Answering using Web Lists. Datasets, NQWebList and GQWebList, use a subset of questions from Natural Questions and GooAQ respectively. To build these datasets, each annotator was shown a question and a relevant URL from the web and was asked to annotate the list answer on the URL, if it exists. For annotating a list, the annotators

The MAX Toolkit provides software which aims to accelerate the development of devices which integrate multiple voice agents. The Toolkit provides guidance to both device makers and agent developers towards this goal.

Coala is a python package for Contextual Answer Sentence Selection. Answer Sentence Selection (AS2) is a sub-task of question answering, and it aims at finding the sentence containing the answer for a given input question from a pool of possible candidate sentences (e.g. retrieved from a search engine). In our contextual AS2 task, we provide models that leverage contextual information coming from the documents

Automatic unreliable news detection is a research problem with great potential impact. Recently, several papers have shown promising results on large-scale news datasets with models that only use the article itself without resorting to any fact-checking mechanism or retrieving any supporting evidence. In this work, we take a closer look at these datasets. The code is tested on Python 3.7 and PyTorch 1.6.0

Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research. The existing literature on open-domain knowledge selection is limited and makes certain brittle assumptions on knowledge sources to simplify the overall task (Dinan et al., 2019), such as the existence of a single relevant knowledge sentence per context. In this work, we evaluate

Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underlying vision-and-language navigation (VLN). In this paper, we present VISITRON, a multi-modal Transformer-based navigator better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN). VISITRON

GRAVL-BERT is a unified multimodal coreference resolution (MCR) framework which combines visual relationships between objects, background scenes, dialogue, and metadata by integrating graph neural networks with VL-BERT.

We introduce a human annotated dataset for factual consistency. Annotations are done on generated responses from different configurations of neural response generators, knowledge snippets, and decoding strategies. In addition, to facilitate the development of a factual consistency detector, we automatically create a new corpus called Conv FEVER that is adapted from the Wizard of Wkipedia dataset and includes

Fact verification has attracted a lot of attention in the machine learning and natural language processing communities, as it is one of the key methods for detecting misinformation. Existing large-scale benchmarks for this task have focused mostly on textual sources, i.e. unstructured information, and thus ignored the wealth of information available in structured formats, such as tables. In this paper we