Dialog State Tracking: A Neural Reading Comprehension Approach
- Shuyang Gao, Abhishek Sethi, Sanchit Agarwal, Tagyoung Chung, Dilek Z. Hakkani-Tür
- Computer ScienceSIGDIAL Conferences
- 6 August 2019
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.
Effects of Empty Categories on Machine Translation
- Tagyoung Chung, D. Gildea
- Computer ScienceConference on Empirical Methods in Natural…
- 9 October 2010
It is shown that even when automatic prediction of null elements is not highly accurate, it nevertheless improves the end translation result and inclusion of some empty categories in training data improves the translation result.
Unsupervised Tokenization for Machine Translation
- Tagyoung Chung, D. Gildea
- Computer ScienceConference on Empirical Methods in Natural…
- 6 August 2009
This paper presents unsupervised methods to solve tokenization problem and incorporates information available from parallel corpus to determine a good tokenization for machine translation.
MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension
- Di Jin, Shuyang Gao, Jiun-Yu Kao, Tagyoung Chung, Dilek Z. Hakkani-Tür
- Computer ScienceAAAI Conference on Artificial Intelligence
- 1 October 2019
This work introduces MMM, a Multi-stage Multi-task learning framework for Multi-choice reading comprehension, and proposes a novel multi-step attention network (MAN) as the top-level classifier for this task.
From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
- Shuyang Gao, Sanchit Agarwal, Tagyoung Chung, Di Jin, Dilek Z. Hakkani-Tür
- Computer ScienceNLP4CONVAI
- 13 April 2020
This paper proposes using machine reading comprehension (RC) in state tracking from two perspectives: model architectures and datasets, and divides the slot types in dialogue state into categorical or extractive to borrow the advantages from both multiple-choice and span-based reading comprehension models.
Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE
- Junya Chen, Zhe Gan, Chenyang Tao
- Computer SciencearXiv.org
- 2 July 2021
This work reveals mathematically why contrastive learners fail in the small-batch-size regime, and presents a novel simple, non-trivial contrastive objective named FlatNCE, which fixes this issue.
Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators
- Sanghyun Yi, Rahul Goel, Dilek Z. Hakkani-Tür
- Computer ScienceInternational Conference on Natural Language…
- 30 April 2019
The studies show that a response generation model that incorporates these combined feedback mechanisms produce more engaging and coherent responses in an open-domain spoken dialog setting, significantly improving the response quality using both automatic and human evaluation.
Simple Question Answering with Subgraph Ranking and Joint-Scoring
- Wenbo Zhao, Tagyoung Chung, Anuj Goyal, A. Metallinou
- Computer ScienceNorth American Chapter of the Association for…
- 4 April 2019
Two aspects are focused on: improving subgraph selection through a novel ranking method, and leveraging the subject–relation dependency by proposing a joint scoring CNN model with a novel loss function that enforces the well-order of scores.
Practical Semantic Parsing for Spoken Language Understanding
- Marco Damonte, Rahul Goel, Tagyoung Chung
- Computer ScienceNorth American Chapter of the Association for…
- 11 March 2019
A transfer learning framework for executable semantic parsing is built and it is shown that the framework is effective for Question Answering (Q&A) as well as for Spoken Language Understanding (SLU).
Factors Affecting the Accuracy of Korean Parsing
- Tagyoung Chung, Matt Post, D. Gildea
- LinguisticsSPMRL@NAACL-HLT
- 5 June 2010
It is found that Korean's relatively free word order does not impact parsing results as much as one might expect, but in fact the prevalence of zero pronouns accounts for a large portion of the difference between Korean and English parsing scores.
...
...