Search Results for author:
Found 19 papers, 6 papers with code
Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs.
CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs
We apply CESAR on InstructDial, a benchmark for instruction-based dialog tasks.
Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language
Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations.
"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge
We hope this task and dataset can promote further research on TOD and subjective content understanding.
KILM: Knowledge Injection into Encoder-Decoder Language Models
Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters.
Role of Bias Terms in Dot-Product Attention
Moreover, we argue that the bias term of the value linear transformation has a more prominent role than that of the bias term of the query linear transformation.
Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
This work focuses on in-context data augmentation for intent detection.
Ranked #1 on
Intent Detection
on BANKING77 10-shot
Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning
Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning.
Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging.
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks.
Zero-Shot Controlled Generation with Encoder-Decoder Transformers
In this work, we propose novel approaches for controlling encoder-decoder transformer-based NLG models in zero-shot.
Correcting Automated and Manual Speech Transcription Errors using Warped Language Models
Masked language models have revolutionized natural language processing systems in the past few years.
Language Model is All You Need: Natural Language Understanding as Question Answering
Different flavors of transfer learning have shown tremendous impact in advancing research and applications of machine learning.
Warped Language Models for Noise Robust Language Understanding
The insertion and drop modification of the input text during training of WLM resemble the types of noise due to Automatic Speech Recognition (ASR) errors, and as a result WLMs are likely to be more robust to ASR noise.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Joint Contextual Modeling for ASR Correction and Language Understanding
As a baseline approach, we trained task-specific Statistical Language Models (SLM) and fine-tuned state-of-the-art Generalized Pre-training (GPT) Language Model to re-rank the n-best ASR hypotheses, followed by a model to identify the dialog act and slots.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Exploration Based Language Learning for Text-Based Games
In this work, we propose to use the exploration approach of Go-Explore for solving text-based games.
Plato Dialogue System: A Flexible Conversational AI Research Platform
Plato has been designed to be easy to understand and debug and is agnostic to the underlying learning frameworks that train each component.
Flexibly-Structured Model for Task-Oriented Dialogues
It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot.
Named Entity Sequence Classification
We frame NESC as a binary classification problem and we use NER as well as recurrent neural networks to find the probability of candidate named entity is a real named entity.
