Story Cloze Ending Selection Baselines and Data Examination
By Todor Mihaylov, Anette Frank. 2017
11 citations recorded by the source corpus.
This paper describes two supervised baseline systems for the Story Cloze Test Shared Task (Mostafazadeh et al., 2016a). We first build a classifier using features based on word embeddings and semantic similarity computation. We further implement a neural LSTM system with different encoding strategies that try to model the relation between the story and the provided endings. Our experiments show that a model using representation features based on average word embedding vectors over the given story words and the candidate ending sentences words, joint with similarity features between the story and candidate ending representations performed better than the neural models. Our best model based on achieves an accuracy of 72.42, ranking 3rd in the official evaluation.
Subfields: 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 Natural Language Processing
- Ashish Sabharwal
- Tushar Khot
- Peter Clark
- Todor Mihaylov
- Daniel Khashabi
- Hannaneh Hajishirzi
- Kyle Richardson
- Chitta Baral
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 r emb s of the word embeddings of tokens in s , and then computes the cosine similarities between the question and each answer choice, r cos q,c i : For…”
- Pay Attention to the Ending:Strong Neural Baselines for the ROC Story Cloze Task (2017, background): “…set is more effective than learning directly from the training set, as well as noting certain biases in the endings (Schwartz et al., 2017a,b; Bugert et al., 2017; Flor and Somasun-daran, 2017; Schenk and Chiarcos, 2017; Roem-mele et al., 2017; Goel and Singh, 2017; Mihaylov and Frank, 2017).”
- A Multi-Attention based Neural Network with External Knowledge for Story Ending Predicting Task (2018, unknown): “…et al., 2017) 75.2% HCM (Chaturvedi et al., 2017) 77.6% Neural Network Algorithm DSSM (Mostafazadeh et al., 2016) 58.5% CGAN (Wang et al., 2017) 60.9% Lin (Lin et al., 2017) 67.0% LSTM (Mihaylov and Frank, 2017) 72.8% Cai (Cai et al., 2017) 74.7% MANN 78.3% SeqMANN 84.7% Human Performance 100%”