Skip to search formSkip to main contentSkip to account menu
  • Publications
  • Influence
ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks
TLDR
The first large-scale manually-annotated corpus for scientific papers is developed and released by enabling faster annotation and summarization methods that integrate the authors’ original highlights and the article’s actual impacts on the community are proposed, to create comprehensive, hybrid summaries.
View PDF on arXiv
XOR QA: Cross-lingual Open-Retrieval Question Answering
TLDR
This work constructs a large-scale dataset built on 40K information-seeking questions across 7 diverse non-English languages that TyDi QA could not find same-language answers for and introduces a task framework, called Cross-lingual Open-Retrieval Question Answering (XOR QA), that consists of three new tasks involving cross-lingually document retrieval from multilingual and English resources.
View on ACL
Low-resource Deep Entity Resolution with Transfer and Active Learning
TLDR
This paper develops a deep learning-based method that targets low-resource settings for ER through a novel combination of transfer learning and active learning and designs an architecture that allows us to learn a transferable model from a high-resource setting to a low- resource one.
View on ACL
Robust Multilingual Part-of-Speech Tagging via Adversarial Training
TLDR
It is found that AT not only improves the overall tagging accuracy, but also prevents over-fitting well in low resource languages and boosts tagging accuracy for rare / unseen words.
View on ACL
TAG Parsing with Neural Networks and Vector Representations of Supertags
TLDR
It is demonstrated that the embedding vector representations the parser induces for supertags possess linguistically interpretable structure, supporting analogies between grammatical structures like those familiar from recent work in distributional semantics.
View on ACL
One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval
We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without…
View PDF on arXiv
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation
TLDR
The speed disadvantage for autoregressive baselines compared to non-autoregressive methods has been overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation.
View PDF on arXiv
Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation
TLDR
The findings suggest that the latency disadvantage for autoregressive translation has been overestimated due to a suboptimal choice of layer allocation, and a new speed-quality baseline for future research toward fast, accurate translation is provided.
Parallel Machine Translation with Disentangled Context Transformer
TLDR
This work proposes an attention-masking based model, called Disentangled Context (DisCo) transformer, that simultaneously generates all tokens given different contexts, and develops the parallel easy-first inference algorithm, which iteratively refines every token in parallel and reduces the number of required iterations.
View PDF on arXiv
Polyglot Contextual Representations Improve Crosslingual Transfer
TLDR
Rosita is introduced, a method to produce multilingual contextual word representations by training a single language model on text from multiple languages, which provides further evidence for the benefits of polyglot learning, in which representations are shared across multiple languages.
View on ACL
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License