Search Results for author:
Found 32 papers, 7 papers with code
The Social Dynamics of Language Change in Online Networks
Language change is a complex social phenomenon, revealing pathways of communication and sociocultural influence.
On Evaluating and Comparing Open Domain Dialog Systems
In this paper, we propose a comprehensive evaluation strategy with multiple metrics designed to reduce subjectivity by selecting metrics which correlate well with human judgement.
Contextual Topic Modeling For Dialog Systems
On annotated data, we show that incorporating context and dialog acts leads to relative gains in topic classification accuracy by 35% and on unsupervised keyword detection recall by 11% for conversational interactions where topics frequently span multiple utterances.
Parsing Coordination for Spoken Language Understanding
Typical spoken language understanding systems provide narrow semantic parses using a domain-specific ontology.
Online Embedding Compression for Text Classification using Low Rank Matrix Factorization
Empirically, we show that the proposed method can achieve 90% compression with minimal impact in accuracy for sentence classification tasks, and outperforms alternative methods like fixed-point quantization or offline word embedding compression.
Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems
This limits such systems in two different ways: If there is an update in the task domain, the dialogue system usually needs to be updated or completely re-trained.
Detecting Offensive Content in Open-domain Conversations using Two Stage Semi-supervision
We train models using publicly available annotated datasets as well as using the proposed large-scale semi-supervised datasets.
Practical Semantic Parsing for Spoken Language Understanding
Executable semantic parsing is the task of converting natural language utterances into logical forms that can be directly used as queries to get a response.
Natural Language Generation at Scale: A Case Study for Open Domain Question Answering
Our experiments show the feasibility of learning statistical NLG models for open-domain QA with larger ontologies.
Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators
Having explicit feedback on the relevance and interestingness of a system response at each turn can be a useful signal for mitigating such issues and improving system quality by selecting responses from different approaches.
HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking
In this work, we analyze the performance of these two alternative dialogue state tracking methods, and present a hybrid approach (HyST) which learns the appropriate method for each slot type.
Ranked #18 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Dialogue State Tracking
Multi-domain Dialogue State Tracking
MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines
To fix the noisy state annotations, we use crowdsourced workers to re-annotate state and utterances based on the original utterances in the dataset.
Ranked #16 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Dialogue State Tracking
Multi-domain Dialogue State Tracking
Towards Universal Dialogue Act Tagging for Task-Oriented Dialogues
In unsupervised learning experiments we achieve an F1 score of 54. 1% on system turns in human-human dialogues.
Update Frequently, Update Fast: Retraining Semantic Parsing Systems in a Fraction of Time
To reduce training time, one can fine-tune the previously trained model on each patch, but naive fine-tuning exhibits catastrophic forgetting - degradation of the model performance on the data not represented in the data patch.
Linear Predictive Coding for Acute Stress Prediction from Computer Mouse Movements
This work demonstrates that the damping frequency and damping ratio from LPC are significantly correlated with those from an MSD model, thus confirming the validity of using LPC to infer muscle stiffness and damping.
COVID-19 and the stock market: evidence from Twitter
COVID-19 has had a much larger impact on the financial markets compared to previous epidemics because the news information is transferred over the social networks at a speed of light.
Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems
Finally, we evaluate our system using a typical movie ticket booking task and show that the dialogue simulator is an essential component of the system that leads to over $50\%$ improvement in turn-level action signature prediction accuracy.
Misinformation Detection on YouTube Using Video Captions
Using caption dataset, the proposed models can classify videos among three classes (Misinformation, Debunking Misinformation, and Neutral) with 0. 85 to 0. 90 F1-score.
Pre-Trained Language Transformers are Universal Image Classifiers
The pretrained transformer of GPT-2 is trained to generate text and then fine-tuned to classify facial images.
TableFormer: Robust Transformer Modeling for Table-Text Encoding
Existing models for table understanding require linearization of the table structure, where row or column order is encoded as an unwanted bias.
Reducing Model Jitter: Stable Re-training of Semantic Parsers in Production Environments
Lastly, we discuss practical trade-offs between such techniques and show that co-distillation provides a sweet spot in terms of jitter reduction for semantic parsing systems with only a modest increase in resource usage.
Improving Top-K Decoding for Non-Autoregressive Semantic Parsing via Intent Conditioning
As the top-level intent largely governs the syntax and semantics of a parse, the intent conditioning allows the model to better control beam search and improves the quality and diversity of top-k outputs.
CST5: Data Augmentation for Code-Switched Semantic Parsing
To aid further research in this area, we are also releasing (a) Hinglish-TOP, the largest human annotated code-switched semantic parsing dataset to date, containing 10k human annotated Hindi-English (Hinglish) code-switched utterances, and (b) Over 170K CST5 generated code-switched utterances from the TOPv2 dataset.
DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue
Modern virtual assistants use internal semantic parsing engines to convert user utterances to actionable commands.
StyleTRF: Stylizing Tensorial Radiance Fields
In this work, we present StyleTRF, a compact, quick-to-optimize strategy for stylized view generation using TensoRF.
Interactive Segmentation of Radiance Fields
Radiance Fields (RF) are popular to represent casually-captured scenes for new view synthesis and several applications beyond it.
Predicting Socio-Economic Well-being Using Mobile Apps Data: A Case Study of France
Nonetheless, alternative data sources, such as call data records (CDR) and mobile app usage, can serve as cost-effective and up-to-date sources for identifying socio-economic indicators.
PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs
Research interest in task-oriented dialogs has increased as systems such as Google Assistant, Alexa and Siri have become ubiquitous in everyday life.
FusedRF: Fusing Multiple Radiance Fields
The fused RF has the same render times and memory utilizations as a single RF.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Multi-task Language Understanding
on MMLU
(using extra training data)
GSN: Generalisable Segmentation in Neural Radiance Field
Our GSN representation generates new views of unseen scenes on the fly along with consistent, per-pixel semantic features.
Reducing Model Churn: Stable Re-training of Conversational Agents
Lastly, we discuss practical trade-offs between such techniques and show that co-distillation provides a sweet spot in terms of churn reduction with only a modest increase in resource usage.
