• Publications
  • Influence
MuTual: A Dataset for Multi-Turn Dialogue Reasoning
TLDR
MuTual is introduced, a novel dataset for Multi-Turn dialogue Reasoning, consisting of 8,860 manually annotated dialogues based on Chinese student English listening comprehension exams, which shows that there is ample room for improving reasoning ability.
Hierarchically-Refined Label Attention Network for Sequence Labeling
TLDR
A hierarchically-refined label attention network is investigated, which explicitly leverages label embeddings and captures potential long-term label dependency by giving each word incrementally refined label distributions with hierarchical attention.
LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning
TLDR
A comprehensive dataset, named LogiQA, is built, which is sourced from expert-written questions for testing human Logical reasoning, and shows that state-of-the-art neural models perform by far worse than human ceiling.
Template-Based Named Entity Recognition Using BART
TLDR
A template-based method for NER, treating NER as a language model ranking problem in a sequence-to-sequence framework, where original sentences and statement templates filled by candidate named entity span are regarded as the source sequence and the target sequence, respectively.
Evaluating Commonsense in Pre-trained Language Models
TLDR
This work studies the commonsense ability of GPT, BERT, XLNet, and RoBERTa by testing them on seven challenging benchmarks, finding that language modeling and its variants are effective objectives for promoting models' commonsens ability while bi-directional context and larger training set are bonuses.
What Have We Achieved on Text Summarization?
TLDR
It is found that under similar settings, extractive summarizers are in general better than their abstractive counterparts thanks to strength in faithfulness and factual-consistency, and pre-training techniques, and in particular sequence-to-sequence pre- training, are highly effective for improving text summarization, with BART giving the best results.
Does BERT Solve Commonsense Task via Commonsense Knowledge?
TLDR
This work proposes two attention-based methods to analyze commonsense knowledge inside BERT, and finds that attention heads successfully capture the structured commonsenseknowledge encoded in ConceptNet, which helps BERT solve commonsense tasks directly.
Natural Language Inference in Context - Investigating Contextual Reasoning over Long Texts
TLDR
ConTRoL is a new dataset for ConTextual Reasoning over Long texts, a passage-level NLI dataset with a focus on complex contextual reasoning types such as logical reasoning, derived from competitive selection and recruitment test for police recruitment with expert level quality.
How Can BERT Help Lexical Semantics Tasks
TLDR
This work makes use of dynamic embeddings as word representations in training staticembeddings, thereby leveraging their strong representation power for disambiguating context information and shows that this method leads to improvements over traditional static embedDings on a range of lexical semantics tasks.
Using Dynamic Embeddings to Improve Static Embeddings
TLDR
This work uses contextualized embeddings to facilitate training of static embedding lookup tables, and shows that the resultingembeddings outperform existingstatic embedding methods on various lexical semantics tasks.
...
1
2
...