127 citations · 498 across the 73 of their papers we have counts for
28 papers · 1 filter
BURT: BERT-inspired Universal Representation from Learning Meaningful Segment
Yian Li, Hai Zhao
Although pre-trained contextualized language models such as BERT achieve significant performance on various downstream tasks, current language representation still only focuses on…
Accurate Word Representations with Universal Visual Guidance
Zhuosheng Zhang, Haojie Yu, Hai Zhao +2
Word representation is a fundamental component in neural language understanding models. Recently, pre-trained language models (PrLMs) offer a new performant method of contextualize…
Enhancing Pre-trained Language Model with Lexical Simplification
Rongzhou Bao, Jiayi Wang, Zhuosheng Zhang +1
For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given…
Adaptive Convolution for Semantic Role Labeling
Kashif Munir, Hai Zhao, Zuchao Li
Semantic role labeling (SRL) aims at elaborating the meaning of a sentence by forming a predicate-argument structure. Recent researches depicted that the effective use of syntax ca…
Dialogue Graph Modeling for Conversational Machine Reading
Siru Ouyang, Zhuosheng Zhang, Hai Zhao
Conversational Machine Reading (CMR) aims at answering questions in a complicated manner. Machine needs to answer questions through interactions with users based on given rule docu…
Cross-lingual Universal Dependency Parsing Only from One Monolingual Treebank
Kailai Sun, Zuchao Li, Hai Zhao
Syntactic parsing is a highly linguistic processing task whose parser requires training on treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for…
Reference Knowledgeable Network for Machine Reading Comprehension
Yilin Zhao, Zhuosheng Zhang, Hai Zhao
Multi-choice Machine Reading Comprehension (MRC) as a challenge requires models to select the most appropriate answer from a set of candidates with a given passage and question. Mo…
SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
Zuchao Li, Hai Zhao, Rui Wang +3
In this paper, we introduced our joint team SJTU-NICT 's participation in the WMT 2020 machine translation shared task. In this shared task, we participated in four translation dir…
High-order Semantic Role Labeling
Zuchao Li, Hai Zhao, Rui Wang +1
Semantic role labeling is primarily used to identify predicates, arguments, and their semantic relationships. Due to the limitations of modeling methods and the conditions of pre-i…
Document-level Neural Machine Translation with Document Embeddings
Shu Jiang, Hai Zhao, Zuchao Li +1
Standard neural machine translation (NMT) is on the assumption of document-level context independent. Most existing document-level NMT methods are satisfied with a smattering sense…
Graph-to-Sequence Neural Machine Translation
Sufeng Duan, Hai Zhao, Rui Wang
Neural machine translation (NMT) usually works in a seq2seq learning way by viewing either source or target sentence as a linear sequence of words, which can be regarded as a speci…
Syntax Role for Neural Semantic Role Labeling
Zuchao Li, Hai Zhao, Shexia He +1
Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument structure of a sentence. Previous studies in terms of traditional models have shown syntact…
Learning Universal Representations from Word to Sentence
Yian Li, Hai Zhao
Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific level of linguistic unit, which cause great…
Topic-Aware Multi-turn Dialogue Modeling
Yi Xu, Hai Zhao, Zhuosheng Zhang
In the retrieval-based multi-turn dialogue modeling, it remains a challenge to select the most appropriate response according to extracting salient features in context utterances.…
Multi-span Style Extraction for Generative Reading Comprehension
Junjie Yang, Zhuosheng Zhang, Hai Zhao
Generative machine reading comprehension (MRC) requires a model to generate well-formed answers. For this type of MRC, answer generation method is crucial to the model performance.…
Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue
Longxiang Liu, Zhuosheng Zhang, Hai Zhao +2
A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. Thus utterance- and speaker-aware clues are supposed to be well captured in model…
Composing Answer from Multi-spans for Reading Comprehension
Zhuosheng Zhang, Yiqing Zhang, Hai Zhao +2
This paper presents a novel method to generate answers for non-extraction machine reading comprehension (MRC) tasks whose answers cannot be simply extracted as one span from the gi…
Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
Zhuosheng Zhang, Hai Zhao, Rui Wang
Machine reading comprehension (MRC) aims to teach machines to read and comprehend human languages, which is a long-standing goal of natural language processing (NLP). With the burs…
Bipartite Flat-Graph Network for Nested Named Entity Recognition
Ying Luo, Hai Zhao
In this paper, we propose a novel bipartite flat-graph network (BiFlaG) for nested named entity recognition (NER), which contains two subgraph modules: a flat NER module for outerm…
Capsule-Transformer for Neural Machine Translation
Sufeng Duan, Juncheng Cao, Hai Zhao
Transformer hugely benefits from its key design of the multi-head self-attention network (SAN), which extracts information from various perspectives through transforming the given…
Syntax-aware Data Augmentation for Neural Machine Translation
Sufeng Duan, Hai Zhao, Dongdong Zhang +1
Data augmentation is an effective performance enhancement in neural machine translation (NMT) by generating additional bilingual data. In this paper, we propose a novel data augmen…
Semantics-Aware Inferential Network for Natural Language Understanding
Shuailiang Zhang, Hai Zhao, Junru Zhou
For natural language understanding tasks, either machine reading comprehension or natural language inference, both semantics-aware and inference are favorable features of the conce…
Knowledgeable Dialogue Reading Comprehension on Key Turns
Junlong Li, Zhuosheng Zhang, Hai Zhao
Multi-choice machine reading comprehension (MRC) requires models to choose the correct answer from candidate options given a passage and a question. Our research focuses dialogue-b…
BURT: BERT-inspired Universal Representation from Twin Structure
Yian Li, Hai Zhao
Pre-trained contextualized language models such as BERT have shown great effectiveness in a wide range of downstream Natural Language Processing (NLP) tasks. However, the effective…