• Publications
  • Influence
Bilateral Multi-Perspective Matching for Natural Language Sentences
TLDR
We propose a bilateral multi-perspective matching (BiMPM) model for NLSM tasks under the "matching-aggregation" framework. Expand
Named Entity Recognition through Classifier Combination
TLDR
This paper presents a classifier-combination experimental framework for named entity recognition in which four diverse classifiers (robust linear classifier, maximum entropy, transformation-based learning, and hidden Markov model) are combined under different conditions. Expand
Multi-Perspective Context Matching for Machine Comprehension
TLDR
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. Expand
Transformation Based Learning in the Fast Lane
TLDR
We present a novel and realistic method for speeding up the training time of a transformation-based learner without sacrificing performance. Expand
Overview of TAC-KBP2015 Tri-lingual Entity Discovery and Linking
TLDR
We introduced a new end-to-end Tri-lingual entity discovery and linking task which requires a system to take raw texts from three languages (English, Chinese and Spanish) as input, automatically extract entity mentions, link them to an English knowledge base and cluster NIL mentions across languages. Expand
Neural Cross-Lingual Entity Linking
TLDR
We propose a neural EL model that trains fine-grained similarities and dissimilarities between the query and candidate document from multiple perspectives, combined with convolution and tensor networks. Expand
Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks
TLDR
We introduce a new method for better connecting global evidence with local coreference information, which forms more complex graphs compared to DAGs. Expand
Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection
TLDR
The state-of-the-art named entity recognition (NER) systems are supervised machine learning models that require large amounts of manually annotated data to achieve high accuracy. Expand
A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
TLDR
We present a sentence-compression-based framework for the task, and design a series of learning-based compression models built on parse trees. Expand
A Statistical Model for Multilingual Entity Detection and Tracking
TLDR
We present a statistical language-independent framework for identifying and tracking named, nominal and pronominal references to entities within unrestricted text documents, and chaining them into clusters corresponding to each logical entity present in the text. Expand
...
1
2
3
4
5
...