ACL'17 まとめ

聴講＆ポスターを見ていて気になった論文をセッションごとに。読んで記事書いたら随時リンクを更新。 全体感想なんかもあとで。

Quastion Answering

• An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge (Hao+)
• [TACL] Domain-Targeted, High Precision Knowledge Extraction (Dalvi+)

Dialogue

• Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings (He+)

• Domain Attention with an Ensemble of Experts (Kim+)

Information Extraction

• Adversarial Multi-task Learning for Text Classification (Liu+)

Semantics

• Skip-Gram - Zipf + Uniform = Vector Additivity (Gittens+)

Outstanding Papers

• Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses (Lowe+)
• Abstract Syntax Networks for Code Generation and Semantic Parsing (Rabinovich+)

Poster, Workshop, etc.

• Building a Non-Trivial Paraphrase Corpus using Multiple Machine Translation Systems (Suzuki+)
• [NMT1st] Stronger Baselines for Trustable Results in Neural Machine Translation
• [CoNLL'17] Named Entity Disambiguation for Noisy Text (Eshel+)