Search Results for author:
Found 24 papers, 6 papers with code
CoDi: Conversational Distillation for Grounded Question Answering
This is a typical on-device scenario for specialist SLMs, allowing for open-domain model responses, without requiring the model to "memorize" world knowledge in its limited weights.
MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts
Under a 1-trillion-token training budget, the MoMa 1. 4B model, featuring 4 text experts and 4 image experts, achieves impressive FLOPs savings: 3. 7x overall, with 2. 6x for text and 5. 2x for image processing compared to a compute-equivalent dense baseline, measured by pre-training loss.
PRoDeliberation: Parallel Robust Deliberation for End-to-End Spoken Language Understanding
Spoken Language Understanding (SLU) is a critical component of voice assistants; it consists of converting speech to semantic parses for task execution.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
Altogether, these results suggest that training on DP synthetic data can be a better option than training a model on-device on private distributed data.
Small But Funny: A Feedback-Driven Approach to Humor Distillation
The emergence of Large Language Models (LLMs) has brought to light promising language generation capabilities, particularly in performing tasks like complex reasoning and creative writing.
Augmenting text for spoken language understanding with Large Language Models
Using the generated text with JAT and TTS for spoken semantic parsing improves EM on STOP by 1. 4% and 2. 6% absolute for existing and new domains respectively.
Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding
End-to-end (E2E) spoken language understanding (SLU) systems that generate a semantic parse from speech have become more promising recently.
TreePiece: Faster Semantic Parsing via Tree Tokenization
Autoregressive (AR) encoder-decoder neural networks have proved successful in many NLP problems, including Semantic Parsing -- a task that translates natural language to machine-readable parse trees.
Privately Customizing Prefinetuning to Better Match User Data in Federated Learning
To this end, we propose FreD (Federated Private Fr\'echet Distance) -- a privately computed distance between a prefinetuning dataset and federated datasets.
Introducing Semantics into Speech Encoders
Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+11
Data-Efficiency with a Single GPU: An Exploration of Transfer Methods for Small Language Models
Multi-task learning (MTL), instruction tuning, and prompting have recently been shown to improve the generalizability of large language models to new tasks.
STOP: A dataset for Spoken Task Oriented Semantic Parsing
Furthermore, in addition to the human-recorded audio, we are releasing a TTS-generated version to benchmark the performance for low-resource domain adaptation of end-to-end SLU systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Deliberation Model for On-Device Spoken Language Understanding
We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language understanding (NLU) component generates the semantic parse by conditioning on both ASR's text and audio embeddings.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Retrieve-and-Fill for Scenario-based Task-Oriented Semantic Parsing
We tackle this problem by introducing scenario-based semantic parsing: a variant of the original task which first requires disambiguating an utterance's "scenario" (an intent-slot template with variable leaf spans) before generating its frame, complete with ontology and utterance tokens.
RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing
While large pre-trained language models accumulate a lot of knowledge in their parameters, it has been demonstrated that augmenting it with non-parametric retrieval-based memory has a number of benefits from accuracy improvements to data efficiency for knowledge-focused tasks, such as question answering.
Assessing Data Efficiency in Task-Oriented Semantic Parsing
Data efficiency, despite being an attractive characteristic, is often challenging to measure and optimize for in task-oriented semantic parsing; unlike exact match, it can require both model- and domain-specific setups, which have, historically, varied widely across experiments.
Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
When tuning the architecture and hyperparameters of large machine learning models for on-device deployment, it is desirable to understand the optimal trade-offs between on-device latency and model accuracy.
Low-Resource Task-Oriented Semantic Parsing via Intrinsic Modeling
Task-oriented semantic parsing models typically have high resource requirements: to support new ontologies (i. e., intents and slots), practitioners crowdsource thousands of samples for supervised fine-tuning.
Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing
An effective recipe for building seq2seq, non-autoregressive, task-oriented parsers to map utterances to semantic frames proceeds in three steps: encoding an utterance $x$, predicting a frame's length |y|, and decoding a |y|-sized frame with utterance and ontology tokens.
Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog
Semantic parsing using sequence-to-sequence models allows parsing of deeper representations compared to traditional word tagging based models.
Muppet: Massive Multi-task Representations with Pre-Finetuning
We propose pre-finetuning, an additional large-scale learning stage between language model pre-training and fine-tuning.
Ranked #3 on
Text Summarization
on GigaWord
(using extra training data)
Conversational Semantic Parsing
In this paper, we propose a semantic representation for such task-oriented conversational systems that can represent concepts such as co-reference and context carryover, enabling comprehensive understanding of queries in a session.
Better Fine-Tuning by Reducing Representational Collapse
Although widely adopted, existing approaches for fine-tuning pre-trained language models have been shown to be unstable across hyper-parameter settings, motivating recent work on trust region methods.
Abstractive Text Summarization
Cross-Lingual Natural Language Inference
