Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Modeling Coverage for Neural Machine Translation
This paper proposes coverage-based NMT, which maintains a coverage vector to keep track of the attention history and improves both translation quality and alignment quality over standard attention- based NMT.
Target-dependent Twitter Sentiment Classification
This paper proposes to improve target-dependent Twitter sentiment classification by incorporating target- dependent features; and taking related tweets into consideration; and according to the experimental results, this approach greatly improves the performance of target- dependence sentiment classification.
Recognizing Named Entities in Tweets
This work proposes to combine a K-Nearest Neighbors classifier with a linear Conditional Random Fields model under a semi-supervised learning framework to tackle the challenges of Named Entities Recognition for tweets.
Topic sentiment analysis in twitter: a graph-based hashtag sentiment classification approach
This study focuses on hashtag-level sentiment classification, which aims to automatically generate the overall sentiment polarity for a given hashtag in a certain time period, and proposes a novel graph model and three approximate collective classification algorithms for inference.
Neural Machine Translation with Reconstruction
Experiments show that the proposed framework significantly improves the adequacy of NMT output and achieves superior translation result over state-of-the-art NMT and statistical MT systems.
Context Gates for Neural Machine Translation
- Zhaopeng Tu, Yang Liu, Zhengdong Lu, Xiaohua Liu, Hang Li
- Computer ScienceTransactions of the Association for Computational…
- 22 August 2016
Context gates are proposed which dynamically control the ratios at which source and target contexts contribute to the generation of target words and can enhance both the adequacy and fluency of NMT with more careful control of the information flow from contexts.
Coverage-based Neural Machine Translation
Experiments show that coverage-based NMT significantly improves both alignment and translation quality over NMT without coverage.
Entity Linking for Tweets
This work proposes a collective inference method that simultaneously resolves a set of mentions and integrates three kinds of similarities, i.e., mention-entry similarity, entry- entry similarity, and mention-mention similarity, to enrich the context for entity linking and to address irregular mentions that are not covered by the entity-variation dictionary.
Cross-Lingual Mixture Model for Sentiment Classification
This paper proposes a generative cross-lingual mixture model (CLMM) to leverage unlabeled bilingual parallel data and learns previously unseen sentiment words from the large bilingual Parallel data and improves vocabulary coverage significantly.
Joint Inference of Named Entity Recognition and Normalization for Tweets
A novel graphical model is proposed to simultaneously conduct NER and NEN on multiple tweets to address the problem of named entity normalization for tweets, which introduces a binary random variable for each pair of words with the same lemma across similar tweets.