Dynamic Entity Representation with Max-pooling Improves Machine Reading

Kobayashi, Shunsuke; Tian, Ran; Okazaki, Naoaki; Inui, Kentaro

doi:10.18653/v1/n16-1099

Cited by 35 publications

(64 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other Entity-Centric Study. There are several studies that consider the notion entity in other areas: text comprehension (Kobayashi et al, 2016;Henaff et al, 2016) and language modeling (Ji et al, 2017).…”

Section: Related Workmentioning

confidence: 99%

Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis

Shibata

Kurohashi

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Predicate argument structure analysis is a task of identifying structured events. To improve this field, we need to identify a salient entity, which cannot be identified without performing coreference resolution and predicate argument structure analysis simultaneously. This paper presents an entity-centric joint model for Japanese coreference resolution and predicate argument structure analysis. Each entity is assigned an embedding, and when the result of both analyses refers to an entity, the entity embedding is updated. The analyses take the entity embedding into consideration to access the global information of entities. Our experimental results demonstrate the proposed method can improve the performance of the intersentential zero anaphora resolution drastically, which is a notoriously difficult task in predicate argument structure analysis.

show abstract

Section: Related Workmentioning

confidence: 99%

Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis

Shibata

Kurohashi

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

show abstract

“…What concerns ensembles, we used simple averaging of the answer probabilities predicted by ensemble members. (Hermann et al, 2015), results of models marked with ‡ are taken from (Hill et al, 2015) and results marked with are taken from (Kobayashi et al, 2016). Performance of ‡ and models was evaluated only on CNN dataset.…”

Section: Evaluation Methodsmentioning

confidence: 99%

Text Understanding with the Attention Sum Reader Network

Kadlec¹,

Schmid²,

Bajgar³

et al. 2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

245

254

View full text Add to dashboard Cite

Several large cloze-style context-questionanswer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these datasets, the associated text comprehension task is well suited for deep-learning techniques that currently seem to outperform all alternative approaches. We present a new, simple model that uses attention to directly pick the answer from the context as opposed to computing the answer using a blended representation of words in the document as is usual in similar models. This makes the model particularly suitable for questionanswering problems where the answer is a single word from the document. Ensemble of our models sets new state of the art on all evaluated datasets.

show abstract

“…Character-level embeddings are a typical way deep learning models handle this issue, whether used on their own [14], or in conjunction with word-level embedding Recursive Neural Networks (RNNs) [22], or in conjunction with an n-gram model [6]. Another approach is to learn new word embeddings on-the-fly from context [16].…”

Section: Representing Code As a Graphmentioning

confidence: 99%

Deep Learning On Code with an Unbounded Vocabulary

Cvitkovic¹,

Singh²,

Anandkumar³

2018

EasyChair Preprints

View full text Add to dashboard Cite

A major challenge when using techniques from Natural Language Processing for supervised learning on computer program source code is that many words in code are neologisms. Reasoning over such an unbounded vocabulary is not something NLP methods are typically suited for. We introduce a deep model that contends with an unbounded vocabulary (at training or test time) by embedding new words as nodes in a graph as they are encountered and processing the graph with a Graph Neural Network.

show abstract

Dynamic Entity Representation with Max-pooling Improves Machine Reading

Cited by 35 publications

References 9 publications

Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis

Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis

Text Understanding with the Attention Sum Reader Network

Deep Learning On Code with an Unbounded Vocabulary

Contact Info

Product

Resources

About