• Publications
  • Influence
Multi-Domain Joint Semantic Frame Parsing Using Bi-Directional RNN-LSTM
TLDR
Experimental results show the power of a holistic multi-domain, multi-task modeling approach to estimate complete semantic frames for all user utterances addressed to a conversational system over alternative methods based on single domain/task deep learning.
Using Recurrent Neural Networks for Slot Filling in Spoken Language Understanding
TLDR
This paper implemented and compared several important RNN architectures, including Elman, Jordan, and hybrid variants, and implemented these networks with the publicly available Theano neural network toolkit and completed experiments on the well-known airline travel information system (ATIS) benchmark.
Prosody-based automatic segmentation of speech into sentences and topics
TLDR
This work combines prosodic cues with word-based approaches, and evaluates performance on two speech corpora, Broadcast News and Switchboard, finding that the prosodic model achieves comparable performance with significantly less training data, and requires no hand-labeling of prosodic events.
Building a Turkish Treebank
TLDR
This work involves refining a set of treebank annotation guidelines and developing a sophisticated annotation tool with an extendable plug-in architecture for morphological analysis, morphological disambigsuation and syntactic annotation disambiguation.
MultiWOZ 2.1: Multi-Domain Dialogue State Corrections and State Tracking Baselines
TLDR
This work uses crowdsourced workers to fix the state annotations and utterances in the original version of the MultiWOZ data, hoping that this dataset resource will allow for more effective dialogue state tracking models to be built in the future.
Building a Conversational Agent Overnight with Dialogue Self-Play
TLDR
A new corpus of 3,000 dialogues spanning 2 domains collected with M2M is proposed, and comparisons with popular dialogue datasets on the quality and diversity of the surface forms and dialogue flows are presented.
Dialog State Tracking: A Neural Reading Comprehension Approach
TLDR
This work forms dialog state tracking as a reading comprehension task to answer the question what is the state of the current belief state of a dialog after reading conversational context, and uses a simple attention-based neural network to point to the slot values within the conversation.
What is left to be understood in ATIS?
TLDR
It is concluded that even with such low error rates, ATIS test set still includes many unseen example categories and sequences, hence requires more data, and new annotated larger data sets from more complex tasks with realistic utterances can avoid over-tuning in terms of modeling and feature design.
The ICSI/UTD Summarization System at TAC 2009
TLDR
Improvement to the 2008 summarization system to improve sentence boundary detection to avoid damaging errors in preprocessing and focus on high-precision sentence compression to improve readability rather than content.
End-to-End Memory Networks with Knowledge Carryover for Multi-Turn Spoken Language Understanding
TLDR
The experiments on Microsoft Cortana conversational data show that the proposed memory network architecture can effectively extract salient semantics for modeling knowledge carryover in the multi-turn conversations and outperform the results using the state-of-the-art recurrent neural network framework (RNN) designed for single-turn SLU.
...
1
2
3
4
5
...