学部３年 第一回：商品の属性値抽出タスクにおけるエラー分析 [ pdf][ slide] 第二回：Web 情報からの罹患検出を対象とした事実性解析・主体解析の誤り分析 [ pdf][ slide]
学部４年 第二回：意味集約における相対的特徴を考慮した評価視点の構造化 [ pdf][ slide] 第三回：Building_a_Monolingual_Parallel_Corpus_for_Text_Simplification_Using [ pdf][ slide] 第四回：An Analysis of Crowdsourced Text Simplifications [ pdf][ slide] 第五回：The Language Demographics of Amazon Mechanical Turk [ pdf][ slide] 第六回：What Substitutes Tell Us-Analysis of an “All-Words” Lexical Substitution Corpus [ pdf][ slide]
修士1年 第一回： Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging [pdf] [slide]第二回：End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF [pdf] [slide] 第三回：Understanding the Lexical Simplification Needs of Non-Native Speakers of English [ pdf] [ slide] 第四回：Dict2vec: Learning Word Embeddings using Lexical Dictionaries [pdf] [slide]第五回： Deep contextualized word representations [pdf] [slide]第六回：The Importance of Subword Embeddings in Sentence Pair Modeling [ pdf] [ slide] 第七回：Segmentation-Free Word Embedding for Unsegmented Languages ∗ [ pdf] [ slide] 第八回： When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation? [pdf] [slide]第九回：Intrinsic Evaluation of Word Vectors Fails to Predict Extrinsic Performance [pdf] [slide] 第十回：Split and Rephrase: Better Evaluation and a Stronger Baseline [pdf] [slide] 第十一回：How Transferable are Neural Networks in NLP Applications? [pdf] [slide] 第十二回：Phrase-level Self-Attention Networks for Universal Sentence Encoding [ pdf] [ slide] 第十三回：Named Entity Recognition With Parallel Recurrent Neural Networks [ pdf] [ slide] 第十四回： Unsupervised Statistical Machine Translation [pdf] [slide]第十五回：Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms [pdf] [slide] 第十六回： DSGAN: Generative Adversarial Training for Distant Supervision
Relation Extraction [pdf] [slide]第十七回：A robust self-learning method for
fully unsupervised cross-lingual mappings of word embeddings [pdf] [slide] 第十八回： Rotational Unit of Memory: A Novel Representation
Unit for RNNs with Scalable Applications [pdf] [slide]第十九回： Better Word Embeddings by Disentangling Contextual n-Gram Information [pdf] [slide]第二〇回：Improving Word Embeddings Using Kernel PCA [ pdf] [ slide] 第二一回：Character Eyes: Seeing Language through Character-Level Taggers [ pdf] [ slide] 第二二回： Retrofitting Contextualized Word Embeddings with Paraphrases [pdf] [slide]第二三回： Simple task-specific bilingual word embeddings [pdf] [slide]第二四回：Simple and Effective Paraphrastic Similarity from Parallel Translations [pdf] [slide] 第二五回： What does BERT learn about the structure of language? [pdf] [slide]
| 