News

Dec 2020 We released CKIP Transformers — traditional Chinese transformers models (including ALBERT, BERT, GPT2) and NLP tools.
Jul 2020 Our research paper — “Semantic Guidance of Dialogue Generation with Reinforcement Learning” has been accepted by “SIGDIAL 2020”.
May 2020 Our research paper — “Headword-Oriented Entity Linking: A New Entity Linking Task with Dataset and Baseline” has been accepted by “LREC 2020”.
May 2020 Our research paper — “CA-EHN: Commonsense Analogy from E-HowNet” has been accepted by “LREC 2020”.
Feb 2020 Our research paper — “Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER” has been accepted by “AAAI 2020”.
Feb 2020 Our research paper — “Relation Extraction Exploiting Full Dependency Forests” has been accepted by “AAAI 2020”.
Aug 2019 We released CKIP Tagger — a new open-source word segmentation, POS tagging, and name-entity recognition system.
July 2019 Our research paper — “GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction” has been accepted by “ACL 2019”.
March 2019 We won the 3rd place in the “Formosa Grand Challenge” held by MOST.
June 2019 Our research paper — “iComposer: An Automatic Songwriting System for Chinese Popular Music” has been accepted by “NAACL Demo Track 2019”.
January 2019 Our research paper — “HWE: Word Embedding with Heterogeneous Features” has been accepted by “IEEE ICSC 2019”.
October 2018 Our research paper — “Speed Reading: Learning to Read ForBackward via Shuttle” has been accepted by “EMNLP 2018”.
May 2018 Our research paper — “Extended HowNet 2.0 – An Entity-Relation Common-Sense Representation Model” has been accepted by “LREC 2018”.
May 2018 Our research paper — “Word Embedding Evaluation Datasets and Wikipedia Title Embedding for Chinese” has been accepted by “LREC 2018”.
December 2017 Our research paper — “Embedding Wikipedia Title Based on Its Wikipedia Text and Categories” has been accepted by “IALP 2017”, and received “Best Paper Award (Top1 out of 96 accepted papers)”.
November 2017 參加 2017 年 IJCNLP 舉辦的中文情緒預測國際競賽,13 強中在短語的激動程度預測項目中榮獲第1名,總成績則名列第3。
November 2017 Our research paper — “Guess What: A Question Answering Game via On-demand Knowledge Validation” has been accepted by “IJCNLP 2017”.
September 2017 我們開發的美妝保養聊天機器人 — PerMu 是個人化的美妝保養顧問,榮獲 PIXNET 2017 聊天機器人大賽應用類別的冠軍(最佳產品獎),已在Facebook上對外開放。
September 2017 Our research paper — “Leveraging Linguistic Structures for Named Entity Recognition with Bidirectional Recursive Neural Networks” has been accepted by “EMNLP 2017”.
April 2017 Our research paper — “IExM: Information Extraction System for Movies” has been accepted by “WWW 2017”, and received “Best Demo – Special Mention Award”.
April 2017 Our research paper — “Integrating Semantic Knowledge into Lexical Embeddings Based on Information Content Measurement” has been accepted by “EACL 2017”.
January 2017 Our research paper — “A Deep Learning Framework for Coreference Resolution Based on Convolutional Neural Network” has been accepted by “ICSC 2016”.
November 2016 在2016 年 IALP 的一項詞彙知識表達的國際競賽-自動化預測情緒詞彙的兩個情緒維度 (valance and arousal) 當中,馬博士帶領的團隊在國際22個隊伍中奪得 valance 的冠軍,並於 IALP 2016 發表相關文章。
November 2016 Our research paper — “A Unified Representation of Attributes and Their Semantic Composition” has been accepted by “ICALP 2016”.
October 2016 Our research paper — “N-best Parse Rescoring Based on Dependency-Based Word Embeddings” has been accepted by “ROCLING 2016”.
October 2016 Our research paper — “Building a Corpus for Developing the Chinese Elementary School Math Word Problem Solver” has been accepted by “ROCLING 2016”.
September 2015 Our research paper — “System Combination for Machine Translation through Paraphrasing” has been accepted by “EMNLP 2015”.