Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings

Mihaylov, Todor; Frank, Anette

doi:10.18653/v1/k16-2014

Cited by 24 publications

(22 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work we adopt the 15 fine-grained discourse relation sense types from the annotation scheme of the Penn Discourse Tree Bank (PDTB) (Prasad et al, 2008). For producing discourse relation annotations we use the discourse relation sense disambiguation system from Mihaylov and Frank (2016) which is trained on the data provided by the CoNLL Shared Task on Shallow Discourse Parsing (Xue et al, 2016). In this annotation scheme discourse relations are divided into two main types: Explicit and Non-Explicit.…”

Section: Events and Their Participantsmentioning

confidence: 99%

Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension

Mihaylov¹,

Frank²

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

In this work, we propose to use linguistic annotations as a basis for a Discourse-Aware Semantic Self-Attention encoder that we employ for reading comprehension on long narrative texts. We extract relations between discourse units, events and their arguments as well as coreferring mentions, using available annotation tools. Our empirical evaluation shows that the investigated structures improve the overall performance (up to +3.4 Rouge-L), especially intra-sentential and cross-sentential discourse relations, sentence-internal semantic role relations, and long-distance coreference relations. We show that dedicating self-attention heads to intra-sentential relations and relations connecting neighboring sentences is beneficial for finding answers to questions in longer contexts. Our findings encourage the use of discourse-semantic annotations to enhance the generalization capacity of self-attention models for reading comprehension.

show abstract

Section: Events and Their Participantsmentioning

confidence: 99%

Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension

Mihaylov¹,

Frank²

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

“…We use the 300-dimensional word vector used in the previous experiment and tune the number of hidden layers and hidden units on the development set. We consider the following models: Bidirectional-LSTM (Akanksha and Eisenstein, 2016), two flavors of convolutional networks (Qin et al, 2016;Wang and Lan, 2016), two variations of simple argument pooling (Mihaylov and Frank, 2016;Schenk et al, 2016), and the best system using surface features alone (Wang and Lan, 2015). The comparison results and brief system descriptions are shown in Table 4.…”

Section: English Discourse Relationsmentioning

confidence: 99%

A Systematic Study of Neural Discourse Models for Implicit Discourse Relation

Rutherford

Demberg

Xue

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

View full text Add to dashboard Cite

Inferring implicit discourse relations in natural language text is the most difficult subtask in discourse parsing. Many neural network models have been proposed to tackle this problem. However, the comparison for this task is not unified, so we could hardly draw clear conclusions about the effectiveness of various architectures. Here, we propose neural network models that are based on feedforward and long-short term memory architecture and systematically study the effects of varying structures. To our surprise, the best-configured feedforward architecture outperforms LSTM-based model in most cases despite thorough tuning. Further, we compare our best feedforward system with competitive convolutional and recurrent networks and find that feedforward can actually be more effective. For the first time for this task, we compile and publish outputs from previous neural and nonneural systems to establish the standard for further comparison.

show abstract

“…We get significant improvement over the base system(*) (based on McNemar's Test) and outperform SemLM, which only utilizes frame information in the semantic sequences. We also rival the top system (Mihaylov and Frank, 2016) in the CoNLL16 Shared Task (connective sense classification subtask). Note that the FES-LM used here is trained on NYT corpus.…”

Section: Application On Newsmentioning

confidence: 99%

“…With added FES-LM features, we get significant improvement (based on McNemar's Test) over the base system(*) and outperform SemLM, which only models frame information. We also rival the top system (Mihaylov and Frank, 2016) in the CoNLL16 Shared Task (connective sense classification subtask).…”

Section: Application On Storiesmentioning

confidence: 99%

A Joint Model for Semantic Sequences: Frames, Entities, Sentiments

Peng¹,

Chaturvedi²,

Roth³

2017

Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)

View full text Add to dashboard Cite

Understanding stories -sequences of events -is a crucial yet challenging natural language understanding task. These events typically carry multiple aspects of semantics including actions, entities and emotions. Not only does each individual aspect contribute to the meaning of the story, so does the interaction among these aspects. Building on this intuition, we propose to jointly model important aspects of semantic knowledge -frames, entities and sentiments -via a semantic language model. We achieve this by first representing these aspects' semantic units at an appropriate level of abstraction and then using the resulting vector representations for each semantic aspect to learn a joint representation via a neural language model. We show that the joint semantic language model is of high quality and can generate better semantic sequences than models that operate on the word level. We further demonstrate that our joint model can be applied to story cloze test and shallow discourse parsing tasks with improved performance and that each semantic aspect contributes to the model.

show abstract

Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings

Cited by 24 publications

References 23 publications

Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension

Discourse-Aware Semantic Self-Attention for Narrative Reading Comprehension

A Systematic Study of Neural Discourse Models for Implicit Discourse Relation

A Joint Model for Semantic Sequences: Frames, Entities, Sentiments

Contact Info

Product

Resources

About