A Unified Linear-Time Framework for Sentence-Level Discourse Parsing

Lin, Xiang; Joty, Shafiq; Jwalapuram, Prathyusha; Bari, Mehwish

doi:10.18653/v1/p19-1410

Cited by 55 publications

(78 citation statements)

References 24 publications

(74 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In all, the training data contains 7321 sentences, and the testing data contains 951 sentences. These numbers match the statistics reported by Lin et al (2019). We follow the same settings as in their experiments and randomly choose 10% of the training data for hyperparameter tuning.…”

Section: Discourse Parsingmentioning

confidence: 63%

“…For discourse parsing, our model uses the same structure as Lin et al (2019). 3 The encoder is a 5-layer bidirectional RNN based on Gated Recurrent Units (BiGRU) (Cho et al, 2014).…”

Section: Model Specifics For Discourse Parsingmentioning

confidence: 99%

“…Same as Ma et al (2018) and Lin et al (2019), our parsers are trained to minimize the total log loss (cross entropy) for building the right tree structure for a given sentence X. The structure loss L is the pointing loss for the pointer network:…”

Section: Objective Functionmentioning

confidence: 99%

“…Since our goal is to evaluate our parsing method, we conduct the experiments based on gold EDU segmentations. We compare our results with the recently proposed pointer network based parser of Lin et al (2019) (Pointer Net). However, unlike their paper, we report results for both cases: (i) when the model was selected based on the best performance on Span identification; and (ii) when it was selected based on the relation labeling performance on the development set.…”

Section: Discourse Parsingmentioning

confidence: 99%

“…Recently, transition-based top-down parsing with Pointer Networks (Vinyals et al, 2015) has attained state-of-the-art results in both dependency and discourse parsing tasks with the same computational efficiency (Ma et al, 2018;Lin et al, 2019); thanks to the encoder-decoder architecture that makes it possible to capture information from the whole text and the previously derived subtrees, while limiting the number of parsing steps to linear. However, the decoder of these parsers has a sequential structure, which may not yield the most appropriate inductive bias for deriving a hierarchical structure.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Hierarchical Pointer Net Parsing

Liu¹,

Lin²,

Joty³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

Transition-based top-down parsing with pointer networks has achieved state-of-the-art results in multiple parsing tasks, while having a linear time complexity.However, the decoder of these parsers has a sequential structure, which does not yield the most appropriate inductive bias for deriving tree structures. In this paper, we propose hierarchical pointer network parsers, and apply them to dependency and sentence-level discourse parsing tasks. Our results on standard benchmark datasets demonstrate the effectiveness of our approach, outperforming existing methods and setting a new state-of-the-art.

show abstract

Section: Discourse Parsingmentioning

confidence: 63%

“…For discourse parsing, our model uses the same structure as Lin et al (2019). 3 The encoder is a 5-layer bidirectional RNN based on Gated Recurrent Units (BiGRU) (Cho et al, 2014).…”

Section: Model Specifics For Discourse Parsingmentioning

confidence: 99%

Section: Objective Functionmentioning

confidence: 99%

Section: Discourse Parsingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Hierarchical Pointer Net Parsing

Liu¹,

Lin²,

Joty³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

show abstract

Structure-Aware Generation Network for Recipe Generation from Images

Lin

Hoi

Chen

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Sharing food has become very popular with the development of social media. For many real-world applications, people are keen to know the underlying recipes of a food item. In this paper, we are interested in automatically generating cooking instructions for food. We investigate an open research task of generating cooking instructions based on only food images and ingredients, which is similar to the image captioning task. However, compared with image captioning datasets, the target recipes are long-length paragraphs and do not have annotations on structure information. To address the above limitations, we propose a novel framework of Structure-aware Generation Network (SGN) to tackle the food recipe generation task. Our approach brings together several novel ideas in a systematic framework: (1) exploiting an unsupervised learning approach to obtain the sentence-level tree structure labels before training; (2) generating trees of target recipes from images with the supervision of tree structure labels learned from (1); and (3) integrating the inferred tree structures with the recipe generation procedure. Our proposed model can produce high-quality and coherent recipes, and achieve the state-of-the-art performance on the benchmark Recipe1M dataset.

show abstract