1.3k citations · 8.8k across the 127 of their papers we have counts for
21 papers · 2 filters
Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing
Xi Victoria Lin, Richard Socher, Caiming Xiong
We present BRIDGE, a powerful sequential architecture for modeling dependencies between natural language questions and relational databases in cross-DB semantic parsing. BRIDGE rep…
CTRLsum: Towards Generic Controllable Text Summarization
Junxian He, Wojciech Kryściński, Bryan McCann +2
Current summarization systems yield generic summaries that are disconnected from users' preferences and expectations. To address this limitation, we present CTRLsum, a novel framew…
Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition
Genta Indra Winata, Guangsen Wang, Caiming Xiong +1
One crucial challenge of real-world multilingual speech recognition is the long-tailed distribution problem, where some resource-rich languages like English have abundant training…
What's New? Summarizing Contributions in Scientific Literature
Hiroaki Hayashi, Wojciech Kryściński, Bryan McCann +2
With thousands of academic articles shared on a daily basis, it has become increasingly difficult to keep up with the latest scientific findings. To overcome this problem, we intro…
Improving Limited Labeled Dialogue State Tracking with Self-Supervision
Chien-Sheng Wu, Steven Hoi, Caiming Xiong
Existing dialogue state tracking (DST) models require plenty of labeled data. However, collecting high-quality labels is costly, especially when the number of domains increases. In…
Probing Task-Oriented Dialogue Representation from Language Models
Chien-Sheng Wu, Caiming Xiong
This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks. We approach…
Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
Jian-Guo Zhang, Kazuma Hashimoto, Wenhao Liu +5
Intent detection is one of the core components of goal-oriented dialog systems, and detecting out-of-scope (OOS) intents is also a practically important skill. Few-shot learning is…
Explaining and Improving Model Behavior with k Nearest Neighbor Representations
Nazneen Fatema Rajani, Ben Krause, Wengpeng Yin +3
Interpretability techniques in NLP have mainly focused on understanding individual predictions using attention visualization or gradient-based saliency maps over tokens. We propose…
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading
Yifan Gao, Chien-Sheng Wu, Jingjing Li +5
Document interpretation and dialog understanding are the two major challenges for conversational machine reading. In this work, we propose Discern, a discourse-aware entailment rea…
Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
Wenpeng Yin, Nazneen Fatema Rajani, Dragomir Radev +2
A standard way to address different NLP problems is by first constructing a problem-specific dataset, then building a model to fit this dataset. To build the ultimate artificial in…
CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
Shiyang Li, Semih Yavuz, Kazuma Hashimoto +6
Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations…
Composed Variational Natural Language Generation for Few-shot Intents
Congying Xia, Caiming Xiong, Philip Yu +1
In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario. To build connections between existing many-shot intents and few-s…
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
Tao Yu, Chien-Sheng Wu, Xi Victoria Lin +6
We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data…
Photon: A Robust Cross-Domain Text-to-SQL System
Jichuan Zeng, Xi Victoria Lin, Caiming Xiong +4
Natural language interfaces to databases (NLIDB) democratize end user access to relational data. Due to fundamental differences between natural language communication and programmi…
DART: Open-Domain Structured Data Record to Text Generation
Linyong Nan, Dragomir Radev, Rui Zhang +21
We present DART, an open domain structured DAta Record to Text generation dataset with over 82k instances (DARTs). Data-to-Text annotations can be a costly process, especially when…
A High-Quality Multilingual Dataset for Structured Documentation Translation
Kazuma Hashimoto, Raffaella Buschiazzo, James Bradbury +3
This paper presents a high-quality multilingual dataset for the documentation domain to advance research on localization of structured text. Unlike widely-used datasets for transla…
Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading
Yifan Gao, Chien-Sheng Wu, Shafiq Joty +5
The goal of conversational machine reading is to answer user questions given a knowledge base text which may require asking clarification questions. Existing approaches are limited…
BERTology Meets Biology: Interpreting Attention in Protein Language Models
Jesse Vig, Ali Madani, Lav R. Varshney +3
Transformer architectures have proven to learn useful representations for protein classification and generation tasks. However, these representations present challenges in interpre…
ESPRIT: Explaining Solutions to Physical Reasoning Tasks
Nazneen Fatema Rajani, Rui Zhang, Yi Chern Tan +7
Neural networks lack the ability to reason about qualitative physics and so cannot generalize to scenarios and tasks unseen during training. We propose ESPRIT, a framework for comm…
TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue
Chien-Sheng Wu, Steven Hoi, Richard Socher +1
The underlying difference of linguistic patterns between general text and task-oriented dialogue makes existing pre-trained language models less useful in practice. In this work, w…
Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT
Lichao Sun, Kazuma Hashimoto, Wenpeng Yin +4
There is an increasing amount of literature that claims the brittleness of deep neural networks in dealing with adversarial examples that are created maliciously. It is unclear, ho…