no code implementations • 24 Apr 2024 • Jiaqing Yuan, Lin Pan, Chung-Wei Hang, Jiang Guo, Jiarong Jiang, Bonan Min, Patrick Ng, Zhiguo Wang
By further decoupling model known and unknown knowledge, we find the degradation is attributed to exemplars that contradict a model's known knowledge, as well as the number of such exemplars.
no code implementations • 31 Jan 2024 • Wenyue Hua, Jiang Guo, Mingwen Dong, Henghui Zhu, Patrick Ng, Zhiguo Wang
Our analysis over the chain-of-thought generation of edited models further uncover key reasons behind the inadequacy of existing knowledge editing methods from a reasoning standpoint, involving aspects on fact-wise editing, fact recall ability, and coherence in generation.
no code implementations • 10 Aug 2023 • Alexander Hanbo Li, Mingyue Shang, Evangelia Spiliopoulou, Jie Ma, Patrick Ng, Zhiguo Wang, Bonan Min, William Wang, Kathleen McKeown, Vittorio Castelli, Dan Roth, Bing Xiang
We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data.
no code implementations • 30 May 2023 • Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henghui Zhu, Yuhao Zhang, Alexander Hanbo Li, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang
The open-ended Visual Question Answering (VQA) task requires AI models to jointly reason over visual and natural language inputs using world knowledge.
no code implementations • 27 May 2023 • Sijia Wang, Alexander Hanbo Li, Henry Zhu, Sheng Zhang, Chung-Wei Hang, Pramuditha Perera, Jie Ma, William Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng
Entities can be expressed in diverse formats, such as texts, images, or column names and cell values in tables.
1 code implementation • 25 May 2023 • Wuwei Lan, Zhiguo Wang, Anuj Chauhan, Henghui Zhu, Alexander Li, Jiang Guo, Sheng Zhang, Chung-Wei Hang, Joseph Lilien, Yiqun Hu, Lin Pan, Mingwen Dong, Jun Wang, Jiarong Jiang, Stephen Ash, Vittorio Castelli, Patrick Ng, Bing Xiang
A practical text-to-SQL system should generalize well on a wide variety of natural language questions, unseen database schemas, and novel SQL query structures.
2 code implementations • 21 Jan 2023 • Shuaichen Chang, Jun Wang, Mingwen Dong, Lin Pan, Henghui Zhu, Alexander Hanbo Li, Wuwei Lan, Sheng Zhang, Jiarong Jiang, Joseph Lilien, Steve Ash, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Bing Xiang
Neural text-to-SQL models have achieved remarkable performance in translating natural language questions into SQL queries.
no code implementations • 17 Dec 2022 • Yiyun Zhao, Jiarong Jiang, Yiqun Hu, Wuwei Lan, Henry Zhu, Anuj Chauhan, Alexander Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Marvin Dong, Joe Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang
In this paper, we first examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data.
no code implementations • 17 Dec 2022 • Jifan Chen, Yuhao Zhang, Lan Liu, Rui Dong, Xinchi Chen, Patrick Ng, William Yang Wang, Zhiheng Huang
There has been great progress in unifying various table-to-text tasks using a single encoder-decoder model trained via multi-task learning (Xie et al., 2022).
1 code implementation • 30 Sep 2022 • Donghan Yu, Sheng Zhang, Patrick Ng, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Yiqun Hu, William Wang, Zhiguo Wang, Bing Xiang
Question answering over knowledge bases (KBs) aims to answer natural language questions with factual information such as entities and relations in KBs.
no code implementations • 28 Sep 2022 • Jun Wang, Patrick Ng, Alexander Hanbo Li, Jiarong Jiang, Zhiguo Wang, Ramesh Nallapati, Bing Xiang, Sudipta Sengupta
When synthesizing a SQL query, there is no explicit semantic information of NLQ available to the parser which leads to undesirable generalization performance.
no code implementations • 10 Jun 2022 • Sheng Zhang, Patrick Ng, Zhiguo Wang, Bing Xiang
Our generative model is a unified framework to sequentially generate relational triplets under various relation extraction settings and explicitly utilizes relevant knowledge from Knowledge Graph (KG) to resolve ambiguities.
1 code implementation • ACL 2021 • Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang
However, a large amount of world's knowledge is stored in structured databases, and need to be accessed using query languages such as SQL.
no code implementations • 17 Jun 2021 • Peng Shi, Tao Yu, Patrick Ng, Zhiguo Wang
Furthermore, we propose two value filling methods to build the bridge from the existing zero-shot semantic parsers to real-world applications, considering most of the existing parsers ignore the values filling in the synthesized SQL.
1 code implementation • ACL 2021 • Feng Nan, Cicero Nogueira dos santos, Henghui Zhu, Patrick Ng, Kathleen McKeown, Ramesh Nallapati, Dejiao Zhang, Zhiguo Wang, Andrew O. Arnold, Bing Xiang
A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents.
no code implementations • EMNLP 2021 • Dheeru Dua, Cicero Nogueira dos santos, Patrick Ng, Ben Athiwaratkun, Bing Xiang, Matt Gardner, Sameer Singh
Compositional reasoning tasks like multi-hop question answering, require making latent decisions to get the final answer, given a question.
no code implementations • EACL 2021 • Zhiguo Wang, Patrick Ng, Ramesh Nallapati, Bing Xiang
Experiments show that: (1) Our IR-based retrieval method is able to collect high-quality candidates efficiently, thus enables our method adapt to large-scale KBs easily; (2) the BERT model improves the accuracy across all three sub-tasks; and (3) benefiting from multi-task learning, the unified model obtains further improvements with only 1/3 of the original parameters.
3 code implementations • 18 Dec 2020 • Peng Shi, Patrick Ng, Zhiguo Wang, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Cicero Nogueira dos santos, Bing Xiang
Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM).
Ranked #7 on Text-To-SQL on spider (Exact Match Accuracy (Dev) metric)
1 code implementation • ACL 2021 • Yifan Gao, Henghui Zhu, Patrick Ng, Cicero Nogueira dos santos, Zhiguo Wang, Feng Nan, Dejiao Zhang, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang
When multiple plausible answers are found, the system should rewrite the question for each answer to resolve the ambiguity.
1 code implementation • EMNLP 2020 • Siamak Shakeri, Cicero Nogueira dos santos, Henry Zhu, Patrick Ng, Feng Nan, Zhiguo Wang, Ramesh Nallapati, Bing Xiang
Our model comprises a single transformer-based encoder-decoder network that is trained end-to-end to generate both answers and questions.
1 code implementation • ACL 2020 • Alexander R. Fabbri, Patrick Ng, Zhiguo Wang, Ramesh Nallapati, Bing Xiang
Training a QA model on this data gives a relative improvement over a previous unsupervised model in F1 score on the SQuAD dataset by about 14%, and 20% when the answer is a named entity, achieving state-of-the-art performance on SQuAD for unsupervised QA.
no code implementations • 17 Oct 2019 • Xiaofei Ma, Zhiguo Wang, Patrick Ng, Ramesh Nallapati, Bing Xiang
We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks.
no code implementations • IJCNLP 2019 • Zhiguo Wang, Patrick Ng, Xiaofei Ma, Ramesh Nallapati, Bing Xiang
To tackle this issue, we propose a multi-passage BERT model to globally normalize answer scores across all passages of the same question, and this change enables our QA model find better answers by utilizing more passages.
Ranked #3 on Open-Domain Question Answering on SearchQA
2 code implementations • 23 Jan 2017 • Patrick Ng
One of the ubiquitous representation of long DNA sequence is dividing it into shorter k-mer components.