Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings
By Todor Mihaylov, Anette Frank. 2016
28 citations recorded by the source corpus.
This paper describes our system for the CoNLL 2016 Shared Task’s supplementary task on Discourse Relation Sense Classification. Our official submission employs a Logistic Regression classifier with several cross-argument similarity features based on word embeddings and performs with overall F-scores of 64.13 for the Dev set, 63.31 for the Test set and 54.69 for the Blind set, ranking first in the Overall ranking for the task. We compare the feature-based Logistic Regression classifier to different Convolutional Neural Network architectures. After the official submission we enriched our model for Non-Explicit relations by including similarities of explicit connectives with the relation arguments, and part of speech similarities based on modal verbs. This improved our Non-Explicit result by 1.46 points on the Dev set and by 0.36 points on the Blind set.
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ashish Sabharwal
- Peter Clark
- Tushar Khot
- Zhuosheng Zhang
- Todor Mihaylov
- Hannaneh Hajishirzi
- Daniel Khashabi
- Chitta Baral
In Natural Language Processing
- Ashish Sabharwal
- Tushar Khot
- Peter Clark
- Todor Mihaylov
- Zhuosheng Zhang
- Hannaneh Hajishirzi
- Daniel Khashabi
- Kyle Richardson
Citations in the corpus
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering (2018, methodology): “We first experiment with a simple logistic regression model (Mihaylov and Nakov, 2016; Mihaylov and Frank, 2016, 2017) that uses centroid vectors rembs of the word embeddings of tokens in s, and then computes the cosine similarities between the question and each answer choice, rcosq,ci : rembs =…”
- I Know What You Want: Semantic Learning for Text Comprehension (2018, background): “Besides, SRL has been proved to be bene-ficial to a wide range of NLP tasks, including discourse relation sense classification (Mihaylov and Frank 2016), machine translation (Shi et al. 2016) and question answering (Yih et al. 2016).”
- Story Cloze Ending Selection Baselines and Data Examination (2017, methodology): “For tackling the problem of right story ending selection we follow a feature-based classification approach that was previously applied to bi-clausal classification tasks in (Mihaylov and Frank, 2016; Mihaylov and Nakov, 2016).”