Existing knowledge graph embedding approaches concentrate on modeling symmetry/asymmetry, inversion, and composition typed relations but overlook the hierarchical nature of relations.
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.
Therefore, we open source a non-IID IoT person detection (NIPD) data set, which is collected from five different cameras.
However, existing CLSP models are separately proposed and evaluated on datasets of limited tasks and applications, impeding a comprehensive and unified evaluation of CLSP on a diverse range of NLs and MRs. To this end, we present XSemPLR, a unified benchmark for cross-lingual semantic parsing featured with 22 natural languages and 8 meaning representations by examining and selecting 9 existing datasets to cover 5 tasks and 164 domains.
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.
no 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.
In this paper, we firstly reveal the fact that the federated ADMM is essentially a client-variance-reduced algorithm.
Question answering over knowledge bases (KBs) aims to answer natural language questions with factual information such as entities and relations in KBs.
When synthesizing a SQL query, there is no explicit semantic information of NLQ available to the parser which leads to undesirable generalization performance.
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.
Network topology inference is a fundamental problem in many applications of network science, such as locating the source of fake news, brain connectivity networks detection, etc.
Then we propose a feature selection method to reduce the size of the model, based on a new metric which trades off the classification accuracy and privacy preserving.
Similar to that encountered in federated supervised learning, class distribution of labeled/unlabeled data could be non-i. i. d.
Differential privacy (DP) is an essential technique for privacy-preserving, which works by adding random noise to the data.
However, a large amount of world's knowledge is stored in structured databases, and need to be accessed using query languages such as SQL.
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.
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.
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.
A key challenge for abstractive summarization is ensuring factual consistency of the generated summary with respect to the original document.
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 #4 on Text-To-SQL on spider
When multiple plausible answers are found, the system should rewrite the question for each answer to resolve the ambiguity.
While many distributed optimization algorithms have been proposed for solving smooth or convex problems over the networks, few of them can handle non-convex and non-smooth problems.
Our model comprises a single transformer-based encoder-decoder network that is trained end-to-end to generate both answers and questions.
In this paper, we find these two methods have complementary properties and larger diversity, which motivates us to propose a new semi-supervised learning method that is able to adaptively combine the strengths of Xgboost and transductive support vector machine.
First, the aggregation strategy chooses one detector as master detector by experience, and sets the remaining detectors as auxiliary detectors.
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.
Triplet loss processes batch construction in a complicated and fussy way and converges slowly.
In this work, we define the problem of conversation structure modeling as identifying the parent utterance(s) to which each utterance in the conversation responds to.
To address these problems, we propose a promotion method: utilize the maximum of block-level GEs on the frame to detect anomaly.
Medical relation extraction discovers relations between entity mentions in text, such as research articles.
The performance of deep neural models can deteriorate substantially when there is a domain shift between training and test data.
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.
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
Self-explaining text categorization requires a classifier to make a prediction along with supporting evidence.
However, extending KV-MemNNs to Knowledge Based Question Answering (KB-QA) is not trivia, which should properly decompose a complex question into a sequence of queries against the memory, and update the query representations to support multi-hop reasoning over the memory.
Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs.
It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models.
Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query.
Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question.
Ranked #2 on Question Answering on COMPLEXQUESTIONS
Existing neural semantic parsers mainly utilize a sequence encoder, i. e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees.
The task of natural question generation is to generate a corresponding question given the input passage (fact) and answer.
Ranked #11 on Question Generation on SQuAD1.1
The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph.
Ranked #1 on Graph-to-Sequence on LDC2015E86: (using extra training data)
Our method first generates the node and graph embeddings using an improved graph-based neural network with a novel aggregation strategy to incorporate edge direction information in the node embeddings.
Ranked #1 on SQL-to-Text on WikiSQL
We propose two methods, namely, strength-based re-ranking and coverage-based re-ranking, to make use of the aggregated evidence from different passages to better determine the answer.
Ranked #1 on Open-Domain Question Answering on Quasar
In the QG task, a question is generated from the system given the passage and the target answer, whereas in the QA task, the answer is generated given the question and the passage.
Second, we propose a novel method that jointly trains the Ranker along with an answer-generation Reader model, based on reinforcement learning.
Ranked #4 on Open-Domain Question Answering on Quasar
However, it lacks the capacity of utilizing instance-level information from individual instances in the training set.
Natural language sentence matching is a fundamental technology for a variety of tasks.
Ranked #17 on Paraphrase Identification on Quora Question Pairs (Accuracy metric)
This paper addresses the task of AMR-to-text generation by leveraging synchronous node replacement grammar.
Based on this dataset, we propose a Multi-Perspective Context Matching (MPCM) model, which is an end-to-end system that directly predicts the answer beginning and ending points in a passage.
Ranked #3 on Open-Domain Question Answering on SQuAD1.1
We present a dependency to constituent tree conversion technique that aims to improve constituent parsing accuracies by leveraging dependency treebanks available in a wide variety in many languages.
The task of AMR-to-text generation is to generate grammatical text that sustains the semantic meaning for a given AMR graph.
We simply compute the distance between the machine attentions and the "true" alignments, and minimize this cost in the training procedure.
In the training stage, our method induces several sense centroids (embedding) for each polysemous word.
Ranked #4 on Word Sense Induction on SemEval 2010 WSI
Our method simply takes into account the translation options of each word or phrase in the source sentence, and picks a very small target vocabulary for each sentence based on a word-to-word translation model or a bilingual phrase library learned from a traditional machine translation model.
In this paper, we enhance the attention-based neural machine translation (NMT) by adding explicit coverage embedding models to alleviate issues of repeating and dropping translations in NMT.
Most conventional sentence similarity methods only focus on similar parts of two input sentences, and simply ignore the dissimilar parts, which usually give us some clues and semantic meanings about the sentences.
Ranked #12 on Question Answering on WikiQA
In this work, we propose a semi-supervised method for short text clustering, where we represent texts as distributed vectors with neural networks, and use a small amount of labeled data to specify our intention for clustering.
When the interval between a transient ash of light (a "cue") and a second visual response signal (a "target") exceeds at least 200ms, responding is slowest in the direction indicated by the first signal.
In this paper, we take dependency cohesion as a soft constraint, and integrate it into a generative model for large-scale word alignment experiments.