SemanticZ at SemEval-2016 Task 3: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings

By Todor Mihaylov, Preslav Nakov. 2016

60 citations recorded by the source corpus.

We describe our system for finding good answers in a community forum, as defined in SemEval-2016, ask 3 on Community Question Answering. Our approach relies on several semantic similarity features based on fine-tuned word embeddings and topics similarities. In the main Subtask C, our primary submission was ranked third, with a MAP of 51.68 and accuracy of 69.94. In Subtask A, our primary submission was also third, with MAP of 77.58 and accuracy of 73.39.

Subfields: Artificial Intelligence, Information Systems, Information Retrieval & Search, 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

1. Ashish Sabharwal
2. Peter Clark
3. Tushar Khot
4. Todor Mihaylov
5. Hannaneh Hajishirzi
6. Yonatan Belinkov
7. Anette Frank
8. Preslav Nakov

In Information Systems

1. Ashish Sabharwal
2. Tushar Khot
3. Anette Frank
4. Peter Clark
5. Todor Mihaylov
6. Preslav Nakov
7. James R. Glass
8. Alessandro Moschitti

In Information Retrieval & Search

1. Ashish Sabharwal
2. Tushar Khot
3. Peter Clark
4. Anette Frank
5. Todor Mihaylov
6. James R. Glass
7. Preslav Nakov
8. Alessandro Moschitti

In Natural Language Processing

1. Ashish Sabharwal
2. Peter Clark
3. Tushar Khot
4. Todor Mihaylov
5. Anette Frank
6. Yonatan Belinkov
7. Hannaneh Hajishirzi
8. Preslav Nakov

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 =…”
• Discourse Relation Sense Classification Using Cross-argument Semantic Similarity Based on Word Embeddings (2016, methodology): “Combining features based on word embeddings and similarity between arguments in Mihaylov and Nakov (2016) yielded state-of-the art performance in a similar task setup in Community Question Answering (Nakov et al., 2016), where two text arguments (question and answer) are to be ranked.”
• 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).”
• SemEval-2016 Task 3: Community Question Answering (2019, background): “66, SemanticZ (Mihaylov and Nakov, 2016b) with 77.”