Search Results for author:
Found 19 papers, 6 papers with code
CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device
While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also introduces unique challenges for accuracy and memory.
UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity
Notably, UI-JEPA accomplishes the performance with a 50. 5x reduction in computational cost and a 6. 6x improvement in latency in the IIW dataset.
LUCID: LLM-Generated Utterances for Complex and Interesting Dialogues
Spurred by recent advances in Large Language Models (LLMs), virtual assistants are poised to take a leap forward in terms of their dialogue capabilities.
Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries
To address this problem, we handle the task of conversation retrieval based on text summaries of the conversations.
Intelligent Assistant Language Understanding On Device
It has recently become feasible to run personal digital assistants on phones and other personal devices.
Conversational Semantic Parsing for Dialog State Tracking
We consider a new perspective on dialog state tracking (DST), the task of estimating a user's goal through the course of a dialog.
A Generative Model for Joint Natural Language Understanding and Generation
This approach allows us to explore both spaces of natural language and formal representations, and facilitates information sharing through the latent space to eventually benefit NLU and NLG.
Natural Language Understanding
Task-Oriented Dialogue Systems
+1
Building a Neural Semantic Parser from a Domain Ontology
We address these challenges with a framework which allows to elicit training data from a domain ontology and bootstrap a neural parser which recursively builds derivations of logical forms.
Dependency Grammar Induction with a Neural Variational Transition-based Parser
Transition-based models enable faster inference with $O(n)$ time complexity, but their performance still lags behind.
Weakly-supervised Neural Semantic Parsing with a Generative Ranker
Weakly-supervised semantic parsers are trained on utterance-denotation pairs, treating logical forms as latent.
Learning an Executable Neural Semantic Parser
This paper describes a neural semantic parser that maps natural language utterances onto logical forms which can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response.
Edina: Building an Open Domain Socialbot with Self-dialogues
We present Edina, the University of Edinburgh's social bot for the Amazon Alexa Prize competition.
A Generative Parser with a Discriminative Recognition Algorithm
Generative models defining joint distributions over parse trees and sentences are useful for parsing and language modeling, but impose restrictions on the scope of features and are often outperformed by discriminative models.
Learning Structured Natural Language Representations for Semantic Parsing
We introduce a neural semantic parser that converts natural language utterances to intermediate representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target domains.
Dependency Parsing as Head Selection
Conventional graph-based dependency parsers guarantee a tree structure both during training and inference.
Neural Summarization by Extracting Sentences and Words
Traditional approaches to extractive summarization rely heavily on human-engineered features.
Long Short-Term Memory-Networks for Machine Reading
In this paper we address the question of how to render sequence-level networks better at handling structured input.
Ranked #56 on
Natural Language Inference
on SNLI
Syntax-Aware Multi-Sense Word Embeddings for Deep Compositional Models of Meaning
We detail a compositional distributional framework based on a rich form of word embeddings that aims at facilitating the interactions between words in the context of a sentence.
Investigating the Role of Prior Disambiguation in Deep-learning Compositional Models of Meaning
This paper aims to explore the effect of prior disambiguation on neural network- based compositional models, with the hope that better semantic representations for text compounds can be produced.
