ACL 2018

Hierarchical Neural Story Generation

ACL 2018 facebookresearch/fairseq-py

We explore story generation: creative systems that can build coherent and fluent passages of text about a topic.

Personalizing Dialogue Agents: I have a dog, do you have pets too?

ACL 2018 facebookresearch/ParlAI

Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating.

Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates

ACL 2018 google/sentencepiece

Subword units are an effective way to alleviate the open vocabulary problems in neural machine translation (NMT).

LANGUAGE MODELLING MACHINE TRANSLATION

Chinese NER Using Lattice LSTM

ACL 2018 jiesutd/LatticeLSTM

We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon.

CHINESE NAMED ENTITY RECOGNITION

Marian: Fast Neural Machine Translation in C++

ACL 2018 emjotde/amunmt

We present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs.

MACHINE TRANSLATION

Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

ACL 2018 ChenRocks/fast_abs_rl

Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i. e., compresses and paraphrases) to generate a concise overall summary.

ABSTRACTIVE TEXT SUMMARIZATION

Universal Language Model Fine-tuning for Text Classification

ACL 2018 Socialbird-AILab/BERT-Classification-Tutorial

Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch.

LANGUAGE MODELLING SENTIMENT ANALYSIS TEXT CLASSIFICATION TRANSFER LEARNING

A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings

ACL 2018 artetxem/vecmap

Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training.

WORD EMBEDDINGS