Zhiguo Wang

FAQ-based Question Answering via Word Alignment

2015 · arXiv (Cornell University)

In this paper, we propose a novel word-alignment-based method to solve the FAQ-based question answering task. First, we employ a neural network model to calculate question similarity, where the word alignment between two questions is …

A Unified Query-based Generative Model for Question Generation and Question Answering

2017 · arXiv (Cornell University)

We propose a query-based generative model for solving both tasks of question generation (QG) and question an- swering (QA). The model follows the classic encoder- decoder framework. The encoder takes a passage and a query …

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

2019 · arXiv (Cornell University)

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. In this paper, we …

Retrieval, Re-ranking and Multi-task Learning for Knowledge-Base Question Answering

2021

Question answering over knowledge bases (KBQA) usually involves three sub-tasks, namely topic entity detection, entity linking and relation detection. Due to the large number of entities and relations inside knowledge bases (KB), previous work usually …

Entity-level Factual Consistency of Abstractive Text Summarization

2021

Feng Nan, Ramesh Nallapati, Zhiguo Wang, Cicero Nogueira dos Santos, Henghui Zhu, Dejiao Zhang, Kathleen McKeown, Bing Xiang. Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. …

REKnow: Enhanced Knowledge for Joint Entity and Relation Extraction

2022 · arXiv (Cornell University)

Relation extraction is an important but challenging task that aims to extract all hidden relational facts from the text. With the development of deep language models, relation extraction methods have achieved good performance on various …

Sentence Similarity Learning by Lexical Decomposition and Composition

2016 · arXiv (Cornell University)

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. In this work, …

Bilateral Multi-Perspective Matching for Natural Language Sentences

2017 · arXiv (Cornell University)

Natural language sentence matching is a fundamental technology for a variety of tasks. Previous approaches either match sentences from a single direction or only apply single granular (word-by-word or sentence-by-sentence) matching. In this work, we …

R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering

2017 · arXiv (Cornell University)

In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et …

Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks

2018 · arXiv (Cornell University)

The celebrated Sequence to Sequence learning (Seq2Seq) technique and its numerous variants achieve excellent performance on many tasks. However, many machine learning tasks have inputs naturally represented as graphs; existing Seq2Seq models face a significant …

Leveraging Context Information for Natural Question Generation

2018

Linfeng Song, Zhiguo Wang, Wael Hamza, Yue Zhang, Daniel Gildea. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018.

N-ary Relation Extraction using Graph-State LSTM

2018

Cross-sentence n-ary relation extraction detects relations among n entities across multiple sentences. Typical methods formulate an input as a document graph, integrating various intra-sentential and inter-sentential dependencies. The current state-of-the-art method splits the input graph …

Semantic Neural Machine Translation Using AMR

2019 · Transactions of the Association for Computational Linguistics

Abstract 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 …

A Graph-to-Sequence Model for AMR-to-Text Generation

2018

The problem of AMR-to-text generation is to recover a text representing the same meaning as an input AMR graph. The current state-of-the-art method uses a sequence-to-sequence model, leveraging LSTM for encoding a linearized AMR structure. …

Supervised Attentions for Neural Machine Translation

2016

In this paper, we improve the attention or alignment accuracy of neural machine translation by utilizing the alignments of training sentence pairs. We simply compute the distance between the machine attentions and the "true" alignments, …

Coverage Embedding Models for Neural Machine Translation

2016

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. For each source word, our model starts with …

Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

2019

Zhiguo Wang, Patrick Ng, Xiaofei Ma, Ramesh Nallapati, Bing Xiang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Universal Text Representation from BERT: An Empirical Study

2019 · arXiv (Cornell University)

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. Sentence-level embeddings are evaluated against two state-of-the-art …