Search Results for author:
Found 22 papers, 1 papers with code
PerKGQA: Question Answering over Personalized Knowledge Graphs
The above concerns motivate our question answer- ing setting over personalized knowledge graphs (PERKGQA) where each user has restricted access to their KG.
Evaluating the Practical Utility of Confidence-score based Techniques for Unsupervised Open-world Classification
Open-world classification in dialog systems require models to detect open intents, while ensuring the quality of in-domain (ID) intent classification.
What Do Users Care About? Detecting Actionable Insights from User Feedback
Users often leave feedback on a myriad of aspects of a product which, if leveraged successfully, can help yield useful insights that can lead to further improvements down the line.
Constrained Decoding with Speculative Lookaheads
We propose constrained decoding with speculative lookaheads (CDSL), a technique that significantly improves upon the inference efficiency of CDLH without experiencing the drastic performance reduction seen with greedy decoding.
User Persona Identification and New Service Adaptation Recommendation
Providing a personalized user experience on information dense webpages helps users in reaching their end-goals sooner.
Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA
We present BYOKG, a universal question-answering (QA) system that can operate on any knowledge graph (KG), requires no human-annotated training data, and can be ready to use within a day -- attributes that are out-of-scope for current KGQA systems.
Document-Level Supervision for Multi-Aspect Sentiment Analysis Without Fine-grained Labels
Aspect-based sentiment analysis (ABSA) is a widely studied topic, most often trained through supervision from human annotations of opinionated texts.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems
Specifically, we propose an approach that performs contextual dynamic prompting where the prompts are learnt from dialog contexts.
Privacy Adhering Machine Un-learning in NLP
In several real world industry applications that use Machine Learning to build models on user data, such mandates require significant effort both in terms of data cleansing as well as model retraining while ensuring the models do not deteriorate in prediction quality due to removal of data.
Zero-Shot Learning for Joint Intent and Slot Labeling
It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Language Understanding (NLU) components of task-oriented dialog systems, especially for the many real world tasks that have a large and growing number of intents and slot types.
Unsupervised Neural Stylistic Text Generation using Transfer learning and Adapters
Research has shown that personality is a key driver to improve engagement and user experience in conversational systems.
Recursive Template-based Frame Generation for Task Oriented Dialog
The Natural Language Understanding (NLU) component in task oriented dialog systems processes a user{'}s request and converts it into structured information that can be consumed by downstream components such as the Dialog State Tracker (DST).
Joint Multiple Intent Detection and Slot Labeling for Goal-Oriented Dialog
Neural network models have recently gained traction for sentence-level intent classification and token-based slot-label identification.
What we need to learn if we want to do and not just talk
In task-oriented dialog, agents need to generate both fluent natural language responses and correct external actions like database queries and updates.
Achieving Fluency and Coherency in Task-oriented Dialog
We show how to combine nearest neighbor and Seq2Seq methods in a hybrid model, where nearest neighbor is used to generate fluent responses and Seq2Seq type models ensure dialog coherency and generate accurate external actions.
Exploring the Role of Logically Related Non-Question Phrases for Answering Why-Questions
Next, we apply an improved version of ranking with a prior-based approach, which ranks all words in the candidate document with respect to a set of root words (i. e. non-stopwords present in the question and in the candidate document).
