In this paper, we firstly empirically find that existing models struggle to handle hard mentions due to their insufficient contexts, which consequently limits their overall typing performance.
In this work, we propose a novel BiTIIMT system, Bilingual Text-Infilling for Interactive Neural Machine Translation.
Existing work on Fine-grained Entity Typing (FET) typically trains automatic models on the datasets obtained by using Knowledge Bases (KB) as distant supervision.
Auxiliary information from multiple sources has been demonstrated to be effective in zero-shot fine-grained entity typing (ZFET).
Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs).
We find that although NMT models are difficult to capture word alignment for CFT words but these words do not sacrifice translation quality significantly, which provides an explanation why NMT is more successful for translation yet worse for word alignment compared to statistical machine translation.
Current practices in metric evaluation focus on one single dataset, e. g., Newstest dataset in each year's WMT Metrics Shared Task.
To this end, we study the dynamic relationship between the encoded linguistic information and task performance from the viewpoint of Pareto Optimality.
Specifically, we transfer the knowledge from a teacher model to its student model by locally matching their predictions on all sub-structures, instead of the whole output space.
(2) reference-free metrics outperform reference-based metrics, indicating that the standard references are unnecessary to evaluate the paraphrase's quality.
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community.
It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models.
Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions.
no code implementations • • Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, Zhanhui Kang, Shuming Shi
This paper introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
It is generally believed that a translation memory (TM) should be beneficial for machine translation tasks.
In this paper, we propose the task of general word-level autocompletion (GWLAN) from a real-world CAT scenario, and construct the first public benchmark to facilitate research in this topic.
Automatic machine translation is super efficient to produce translations yet their quality is not guaranteed.
An important aspect of developing dialogue systems is how to evaluate and compare the performance of different systems.
Unsupervised Neural Machine Translation or UNMT has received great attention in recent years.
no code implementations • 31 Dec 2020 • Haisong Zhang, Lemao Liu, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Jianchen Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, Zhanhui Kang, Shuming Shi
This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Experiments on synthetic datasets and real-world datasets show that our model is robust to unlabeled entity problem and surpasses prior baselines.
We propose a touch-based editing method for translation, which is more flexible than traditional keyboard-mouse-based translation postediting.
Many efforts have been devoted to extracting constituency trees from pre-trained language models, often proceeding in two stages: feature definition and parsing.
Recently many efforts have been devoted to interpreting the black-box NMT models, but little progress has been made on metrics to evaluate explanation methods.
Generalization to unseen instances is our eternal pursuit for all data-driven models.
Despite the great success of NMT, there still remains a severe challenge: it is hard to interpret the internal dynamics during its training process.
Many Data Augmentation (DA) methods have been proposed for neural machine translation.
This paper first provides a method to identify source and target contexts and then introduce a gate mechanism to control the source and target contributions in Transformer.
Experiments show that our approach can indeed improve the translation quality with the automatically generated constraints.
Prior researches suggest that neural machine translation (NMT) captures word alignment through its attention mechanism, however, this paper finds attention may almost fail to capture word alignment for some NMT models.
Multilayer architectures are currently the gold standard for large-scale neural machine translation.
In neural machine translation, an attention model is used to identify the aligned source words for a target word (target foresight word) in order to select translation context, but it does not make use of any information of this target foresight word at all.
Source dependency information has been successfully introduced into statistical machine translation.
Instance weighting has been widely applied to phrase-based machine translation domain adaptation.
The attention mechanisim is appealing for neural machine translation, since it is able to dynam- ically encode a source sentence by generating a alignment between a target word and source words.